{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github-shangyankeji--super-dev","slug":"shangyankeji--super-dev","name":"super-dev","type":"workflow","url":"https://SuperDev.Goder.ai","page_url":"https://unfragile.ai/shangyankeji--super-dev","categories":["automation","testing-quality"],"tags":["ai-coding","ai-ide","ai-workflow","aic","aicli","aicoding","claude-code","code-review","codex","coding-assistant","cursor","developer-tools","productivity","quality-gates","software-engineering","traceability","vibe-coding","vibecoding"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github-shangyankeji--super-dev__cap_0","uri":"capability://automation.workflow.8.stage.spec.driven.development.pipeline.with.mandatory.quality.gates","name":"8-stage spec-driven development pipeline with mandatory quality gates","description":"Orchestrates a linear 8-stage workflow (Documentation → Spec → Red Team Review → Quality Gate → Code Review Guide → AI Prompt → CI/CD → Migration) using a WorkflowEngine that enforces a mandatory 80+ quality score threshold at Stage 4 before proceeding to implementation stages. Each stage generates artifacts that feed into the next, creating an auditable chain of custody from requirements to production-ready code. The pipeline uses scenario detection and domain-aware context to adapt generation strategies based on project type and tech stack.","intents":["I need to enforce quality gates and prevent low-quality AI-generated code from reaching implementation","I want a repeatable, auditable workflow that documents every decision from requirements to deployment","I need to generate comprehensive specs before asking AI tools to code, rather than raw prompting","I want to detect and mitigate risks (red team review) before code generation begins"],"best_for":["teams building production systems with AI coding assistants who need governance and traceability","enterprises requiring audit trails and quality enforcement for AI-assisted development","developers migrating from ad-hoc AI prompting to spec-driven workflows"],"limitations":["Pipeline is linear and sequential — no parallel stage execution, adding latency for large projects","Quality gate threshold (80+) is fixed and not customizable per project type or risk profile","Requires explicit project analysis upfront; cannot auto-detect all tech stacks (ORM detection limited to common patterns)","No built-in rollback or stage-skipping — all 8 stages must complete even for minor changes"],"requires":["Python 3.9+","API key for Claude (Anthropic) or compatible LLM provider","Project codebase accessible locally or via Git","Configuration file specifying business domain and tech platform"],"input_types":["natural language requirements (PRD-style text)","existing codebase (for tech stack detection)","project configuration (YAML/JSON)"],"output_types":["structured specifications (OpenSpec format)","human-readable documentation (PRD, Architecture, UI/UX)","AI-ready prompts (formatted for Claude Code, Cursor, etc.)","CI/CD configuration (GitHub Actions, etc.)","database migration scripts"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-shangyankeji--super-dev__cap_1","uri":"capability://text.generation.language.multi.document.generation.system.with.domain.and.tech.stack.awareness","name":"multi-document generation system with domain and tech-stack awareness","description":"The DocumentGenerator class produces three categories of human-readable artifacts (PRD, Architecture, UI/UX) by leveraging domain knowledge (6 business domains × 4 tech platforms × common patterns) and project analysis results. Generation is context-aware: it detects project type (e.g., SaaS, mobile app, API service) and tech stack (e.g., React + Node.js + PostgreSQL) and adapts templates and content accordingly. Uses Claude to synthesize requirements into structured documents with sections for acceptance criteria, non-functional requirements, and architectural constraints.","intents":["I want to auto-generate professional PRDs, architecture docs, and UI/UX specs from natural language requirements","I need docs that reflect my specific tech stack and business domain, not generic templates","I want to generate documentation that AI coding tools can consume as context for implementation"],"best_for":["product teams that need rapid documentation without manual writing","AI-assisted development workflows where docs serve as input to code generation","organizations standardizing on spec-driven development across multiple projects"],"limitations":["Domain knowledge is limited to 6 predefined business domains; custom domains require code modification","Tech stack detection is pattern-based and may misidentify polyglot projects or emerging frameworks","Generated docs are Claude-specific in tone and structure; customization requires template modification","No built-in versioning or diff tracking for document changes across iterations"],"requires":["Claude API access (Anthropic)","Project analysis results (tech stack and project type detected)","Natural language requirements or existing documentation as seed input"],"input_types":["natural language requirements (text)","project metadata (tech stack, business domain)","existing documentation (optional, for enrichment)"],"output_types":["PRD (markdown or structured JSON)","Architecture document (markdown with diagrams)","UI/UX specification (markdown with wireframe descriptions)"],"categories":["text-generation-language","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-shangyankeji--super-dev__cap_10","uri":"capability://code.generation.editing.code.review.guide.generation.with.architectural.compliance.checks","name":"code review guide generation with architectural compliance checks","description":"Stage 5 of the pipeline that generates detailed code review guidelines and checklists specific to the project's architecture, tech stack, and quality standards. The guide includes acceptance criteria from specs, architectural compliance checks (e.g., microservices isolation, API contract validation), performance benchmarks, security requirements, and testing expectations. Formatted as a structured document that human reviewers or AI tools can follow during code review, with specific checks tied to the generated specifications and architecture documentation.","intents":["I want to generate code review checklists that enforce architectural compliance","I need code review guidelines that align with generated specs and architecture","I want to standardize code review criteria across my team"],"best_for":["teams with formal code review processes who want spec-aligned guidelines","projects with strict architectural constraints (microservices, API contracts, etc.)","organizations standardizing code review practices"],"limitations":["Generated guidelines are template-based and may not capture domain-specific review criteria","Architectural compliance checks are rule-based and may miss subtle violations","No integration with code review tools (GitHub, GitLab); requires manual copy-paste","Guidelines are static; no feedback loop from actual code reviews to improve future guidelines"],"requires":["Specifications (OpenSpec format)","Architecture documentation","Project metadata (tech stack, architectural patterns)"],"input_types":["specifications (OpenSpec format)","architecture documents","acceptance criteria","quality standards"],"output_types":["code review guide (markdown document)","review checklist (structured format)","architectural compliance checks (specific rules)","acceptance criteria (tied to specs)"],"categories":["code-generation-editing","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-shangyankeji--super-dev__cap_11","uri":"capability://tool.use.integration.dual.mode.architecture.supporting.cli.tool.and.claude.code.agent.skills","name":"dual-mode architecture supporting cli tool and claude code agent skills","description":"Super Dev operates in two distinct modes that share core engines: (1) CLI tool for standalone artifact generation (specs, docs, prompts, CI/CD, migrations), and (2) Agent Skills for integration with Claude Code and other AI IDEs via OpenClaw/MCP protocols. The dual architecture enables both batch processing workflows (CLI) and interactive development workflows (agent skills). Both modes use the same underlying components (DocumentGenerator, ProjectAnalyzer, QualityGateChecker, etc.) but expose different interfaces and integration points.","intents":["I want to use Super Dev as a CLI tool for batch artifact generation","I want to integrate Super Dev as an agent skill in Claude Code for interactive development","I want both batch and interactive workflows to use the same core engines and quality standards"],"best_for":["teams using both CLI workflows and Claude Code/AI IDEs","organizations wanting consistent quality standards across batch and interactive development","developers who want flexibility to choose between CLI and IDE integration"],"limitations":["Dual architecture adds complexity; requires maintaining two interface layers","Agent skills integration is limited to tools supporting OpenClaw/MCP protocols","State synchronization between CLI and agent skills is manual; no built-in sync mechanism","CLI and agent skills may diverge if not carefully maintained"],"requires":["Python 3.9+ (for CLI)","Claude Code or compatible AI IDE (for agent skills)","OpenClaw or MCP protocol support (for agent skills)"],"input_types":["CLI: command-line arguments, configuration files, project codebase","Agent Skills: IDE context (open files, selection, cursor position)"],"output_types":["CLI: generated artifacts (specs, docs, prompts, CI/CD, migrations)","Agent Skills: inline suggestions, code completions, expert guidance"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-shangyankeji--super-dev__cap_12","uri":"capability://automation.workflow.workflow.context.and.enforcement.system.with.memory.and.state.management","name":"workflow context and enforcement system with memory and state management","description":"A WorkflowContext system that maintains state across the 8-stage pipeline, tracking artifacts, quality scores, approvals, and decisions at each stage. Implements an enforcement layer that ensures mandatory quality gates are met before stage progression and prevents skipping stages. Uses a memory system to persist workflow state (local or cloud-based) and enable resumption of interrupted workflows. Provides audit trails of all decisions, approvals, and quality checks for compliance and traceability.","intents":["I want to track workflow state across the 8-stage pipeline and resume interrupted workflows","I need audit trails of all quality checks, approvals, and decisions for compliance","I want to enforce mandatory quality gates and prevent stage skipping"],"best_for":["organizations with compliance requirements (audit trails, approval tracking)","teams running long-running workflows that may be interrupted","projects requiring detailed traceability of development decisions"],"limitations":["State persistence requires external storage (local filesystem or cloud); no built-in database","Workflow resumption assumes idempotent stages; non-idempotent stages may produce inconsistent state","Audit trails are append-only; no built-in mechanism to correct or override decisions","Memory system is not distributed; concurrent workflows may have state conflicts"],"requires":["State persistence backend (local filesystem, S3, database, etc.)","Workflow configuration (stage definitions, quality thresholds)","Project context (tech stack, business domain)"],"input_types":["workflow configuration (YAML/JSON)","stage artifacts (specs, docs, code, etc.)","quality scores and approval decisions"],"output_types":["workflow state (JSON or structured format)","audit trail (timestamped log of decisions and approvals)","resumption checkpoints (for interrupted workflows)"],"categories":["automation-workflow","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-shangyankeji--super-dev__cap_2","uri":"capability://planning.reasoning.spec.driven.development.sdd.workflow.with.delta.specifications.and.change.lifecycle.tracking","name":"spec-driven development (sdd) workflow with delta specifications and change lifecycle tracking","description":"Implements a spec-first development model where specifications are generated before code, and changes are tracked as delta specifications rather than code diffs. The SDD workflow manages a directory structure that separates specs, designs, and code artifacts, and tracks the lifecycle of each change (proposed → reviewed → approved → implemented). Uses OpenSpec format (machine-readable specification standard) to enable AI tools to consume specs directly. Supports incremental updates via delta specifications that describe only what changed, reducing context bloat for iterative development.","intents":["I want to track changes at the specification level, not just code level, for better traceability","I need AI tools to work from specs rather than ad-hoc prompts to ensure consistency","I want to manage feature requests and changes through a spec-first workflow before implementation"],"best_for":["teams adopting spec-driven development practices with AI coding assistants","projects requiring detailed change tracking and audit trails","organizations standardizing on OpenSpec format for AI-assisted development"],"limitations":["Requires discipline to maintain specs in sync with code; no automatic sync mechanism","Delta specifications add complexity for teams unfamiliar with spec-first workflows","OpenSpec format adoption requires tooling support; not all AI tools natively consume OpenSpec","Change lifecycle tracking is manual; no built-in enforcement of approval gates"],"requires":["Understanding of spec-driven development principles","Support for OpenSpec format in downstream AI tools","Project structure following SDD directory conventions"],"input_types":["feature requests (natural language)","existing specifications (OpenSpec format)","change descriptions (delta specifications)"],"output_types":["OpenSpec format specifications","delta specifications (change-only specs)","change lifecycle metadata (status, approvals, timestamps)"],"categories":["planning-reasoning","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-shangyankeji--super-dev__cap_3","uri":"capability://memory.knowledge.design.intelligence.engine.with.bm25.search.and.design.system.generation","name":"design intelligence engine with bm25+ search and design system generation","description":"A design asset repository system that indexes design patterns, components, and tokens using BM25+ full-text search, enabling semantic retrieval of relevant design assets for new features. The engine generates design systems and design tokens (color palettes, typography, spacing scales) based on project context and tech stack. Uses a Design Asset Repository to store and retrieve design patterns, and a Design System Generator to synthesize tokens and component specifications from project analysis and domain knowledge.","intents":["I want to reuse design patterns and components from my design system when generating new features","I need to auto-generate design tokens and component specs that match my existing design system","I want to search for relevant design assets when implementing new features"],"best_for":["design-heavy projects (SaaS, mobile apps) where design consistency is critical","teams with established design systems who want to leverage them in AI-assisted development","organizations standardizing design tokens across multiple products"],"limitations":["BM25+ search requires pre-indexed design assets; cold start with empty repository","Design token generation is template-based and may not capture custom design systems","No visual design generation (e.g., mockups, wireframes) — only specification and tokens","Design asset indexing is manual; no automatic extraction from Figma or design tools"],"requires":["Existing design system or design assets to index","Design asset repository (local or cloud-based)","Project context (tech stack, design domain)"],"input_types":["design assets (components, patterns, tokens)","design system documentation","feature requirements (for asset search)"],"output_types":["design token specifications (JSON/CSS)","component specifications (markdown or structured format)","design system documentation"],"categories":["memory-knowledge","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-shangyankeji--super-dev__cap_4","uri":"capability://tool.use.integration.expert.system.with.persona.based.knowledge.base.and.agent.skills.integration","name":"expert system with persona-based knowledge base and agent skills integration","description":"An expert system that models domain expertise through expert personas (e.g., Backend Architect, Frontend Engineer, QA Lead) with associated knowledge bases and skills. Each persona has specialized knowledge for their domain and can be invoked as an agent skill in Claude Code or other AI IDEs. The system integrates with agent skill frameworks (OpenClaw, MCP) to expose expert personas as callable functions that AI tools can invoke during development. Uses a knowledge base per persona to provide context-specific guidance and best practices.","intents":["I want AI coding tools to have access to domain experts (architects, QA leads) during development","I need to encode organizational best practices and standards as expert personas that AI tools can consult","I want to integrate expert knowledge into Claude Code and other AI IDEs as callable skills"],"best_for":["organizations with established best practices and architectural standards","teams using Claude Code or other AI IDEs that support agent skills","projects requiring domain-specific expertise (e.g., security, performance, compliance)"],"limitations":["Expert personas are manually defined; no automatic extraction from documentation or code","Knowledge bases are static; require manual updates as best practices evolve","Agent skill integration is limited to tools supporting OpenClaw or MCP protocols","No built-in conflict resolution when multiple expert personas provide contradictory guidance"],"requires":["Claude Code or compatible AI IDE with agent skills support","OpenClaw or MCP protocol support","Defined expert personas and knowledge bases"],"input_types":["expert persona definitions (name, domain, knowledge base)","knowledge base content (best practices, guidelines, examples)","development context (code, requirements)"],"output_types":["expert guidance (text recommendations)","code suggestions (from expert knowledge base)","best practice enforcement (linting rules, architectural constraints)"],"categories":["tool-use-integration","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-shangyankeji--super-dev__cap_5","uri":"capability://safety.moderation.quality.assurance.system.with.scenario.detection.and.multi.dimensional.quality.checks","name":"quality assurance system with scenario detection and multi-dimensional quality checks","description":"A QualityGateChecker system that evaluates generated artifacts against 80+ quality dimensions (code quality, architectural compliance, security, performance, testability, etc.) and produces a composite quality score. Uses scenario detection to identify project-specific quality concerns (e.g., high-concurrency systems require performance checks, healthcare projects require compliance checks) and adapts quality checks accordingly. Enforces a mandatory 80+ score threshold at Stage 4 before proceeding to implementation stages, with detailed feedback on failing checks to guide remediation.","intents":["I need to enforce quality standards for AI-generated code before it reaches implementation","I want to detect project-specific quality risks (security, performance, compliance) automatically","I need detailed feedback on why generated artifacts failed quality gates and how to fix them"],"best_for":["teams requiring mandatory quality enforcement for AI-assisted development","projects with specific quality concerns (security, performance, compliance)","organizations standardizing quality metrics across multiple AI-assisted projects"],"limitations":["Quality checks are rule-based and may produce false positives/negatives for novel patterns","80+ score threshold is fixed; no per-project customization of quality standards","Scenario detection is pattern-based and may miss edge cases or emerging risks","Quality feedback is textual; no automated remediation suggestions for failing checks"],"requires":["Generated artifacts (specs, code, architecture docs)","Project context (tech stack, business domain, risk profile)","Quality check rules (built-in or custom)"],"input_types":["specifications (OpenSpec format)","generated code","architecture documents","project metadata"],"output_types":["quality score (0-100)","per-check results (pass/fail with details)","scenario-specific quality report","remediation guidance (text)"],"categories":["safety-moderation","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-shangyankeji--super-dev__cap_6","uri":"capability://data.processing.analysis.project.analyzer.with.tech.stack.detection.and.project.type.classification","name":"project analyzer with tech stack detection and project type classification","description":"A ProjectAnalyzer component that inspects existing codebases to automatically detect tech stack (languages, frameworks, databases, deployment platforms) and classify project type (SaaS, mobile app, API service, monolith, microservices, etc.). Uses pattern matching on file structures, dependency files (package.json, requirements.txt, pom.xml, etc.), and code samples to infer tech stack. Feeds analysis results to downstream components (DocumentGenerator, QualityGateChecker, DesignEngine) to enable context-aware generation and quality checks.","intents":["I want to auto-detect my project's tech stack without manual configuration","I need to classify my project type (SaaS, mobile, API) to enable context-aware generation","I want to ensure generated artifacts match my existing tech stack and architectural patterns"],"best_for":["teams with existing codebases who want to adopt spec-driven development","projects with complex or polyglot tech stacks","organizations standardizing on Super Dev across diverse projects"],"limitations":["Tech stack detection is pattern-based and may fail on custom or emerging frameworks","Polyglot projects (multiple languages/frameworks) may be misclassified or partially detected","Detection requires access to codebase files; cannot analyze closed-source or proprietary code","No support for monorepos with multiple independent projects; treats entire repo as single project"],"requires":["Access to project codebase (local or Git)","Standard dependency files (package.json, requirements.txt, etc.)","Readable source code (for pattern matching)"],"input_types":["codebase directory structure","dependency files (package.json, requirements.txt, pom.xml, Gemfile, etc.)","source code samples (for pattern matching)"],"output_types":["detected tech stack (languages, frameworks, databases, deployment platforms)","project type classification (SaaS, mobile, API, monolith, microservices, etc.)","architectural patterns (MVC, microservices, serverless, etc.)","project metadata (structured JSON)"],"categories":["data-processing-analysis","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-shangyankeji--super-dev__cap_7","uri":"capability://text.generation.language.ai.prompt.generation.with.platform.specific.formatting.for.15.ai.tools","name":"ai prompt generation with platform-specific formatting for 15+ ai tools","description":"Generates AI-ready prompts (Stage 6 of pipeline) formatted specifically for 15+ AI coding platforms (Claude Code, Cursor, Windsurf, Aider, ChatGPT, GitHub Copilot, etc.) from specifications and documentation. Each platform has a distinct prompt format and capability set; the generator adapts prompt structure, context injection, and instruction style to match each platform's strengths. Produces prompts that include specs, architecture docs, code review guidelines, and expert persona knowledge, enabling AI tools to implement features with full context and quality standards.","intents":["I want to generate platform-specific prompts for Claude Code, Cursor, and other AI tools","I need prompts that include full context (specs, architecture, best practices) for accurate implementation","I want to standardize how we prompt AI tools across our organization"],"best_for":["teams using multiple AI coding tools and wanting consistent prompt quality","organizations standardizing on spec-driven prompting rather than ad-hoc requests","projects requiring full context (specs, architecture, guidelines) in AI prompts"],"limitations":["Prompt format support is limited to 15 documented platforms; custom tools require manual adaptation","Prompt length varies by platform; may exceed context windows for large projects","No feedback loop from AI tool execution back to prompt generation; static prompts","Platform-specific capabilities (e.g., Claude Code's artifact system) may not be fully leveraged"],"requires":["Specifications (OpenSpec format)","Documentation (PRD, Architecture, UI/UX)","Code review guidelines","Expert persona knowledge bases"],"input_types":["specifications (OpenSpec format)","documentation (markdown or structured format)","code review guidelines","expert persona definitions"],"output_types":["platform-specific prompts (text, formatted for each tool)","context bundles (specs + docs + guidelines)","prompt metadata (platform, version, context size)"],"categories":["text-generation-language","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-shangyankeji--super-dev__cap_8","uri":"capability://automation.workflow.ci.cd.configuration.generation.with.orm.type.detection.and.migration.support","name":"ci/cd configuration generation with orm type detection and migration support","description":"Generates CI/CD pipeline configurations (GitHub Actions, GitLab CI, etc.) and database migration scripts based on project analysis and detected ORM type (SQLAlchemy, Django ORM, Sequelize, etc.). The CI/CD Generator produces workflow files that implement quality gates, automated testing, and deployment stages aligned with the 8-stage pipeline. The Migration Generator detects ORM patterns and generates migration scripts for schema changes, with support for common ORMs and databases. Integrates with Stage 7 (CI/CD Configuration) and Stage 8 (Database Migration) of the pipeline.","intents":["I want to auto-generate CI/CD pipelines that enforce quality gates and testing","I need to generate database migration scripts for schema changes detected in specs","I want CI/CD configuration that aligns with the 8-stage spec-driven development pipeline"],"best_for":["teams adopting spec-driven development who need aligned CI/CD pipelines","projects with complex database schemas requiring automated migrations","organizations standardizing on automated infrastructure generation"],"limitations":["ORM detection is pattern-based and may fail on custom ORMs or hybrid approaches","CI/CD generation is template-based; complex custom workflows require manual modification","Migration generation assumes standard schema change patterns; complex refactorings may need manual review","No support for non-relational databases (NoSQL) or event-sourced architectures"],"requires":["Project analysis results (tech stack, ORM type)","Specifications describing schema changes","Git repository with CI/CD configuration support"],"input_types":["project metadata (tech stack, ORM type, database)","specifications (schema changes, feature requirements)","existing CI/CD configuration (optional, for enhancement)"],"output_types":["CI/CD workflow files (GitHub Actions YAML, GitLab CI YAML, etc.)","database migration scripts (SQL, ORM-specific migration format)","deployment configuration (environment variables, secrets, etc.)"],"categories":["automation-workflow","code-generation-editing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-shangyankeji--super-dev__cap_9","uri":"capability://safety.moderation.red.team.review.stage.with.risk.identification.and.mitigation.guidance","name":"red team review stage with risk identification and mitigation guidance","description":"Stage 3 of the pipeline that performs adversarial review of generated specifications and designs to identify potential risks, security vulnerabilities, performance bottlenecks, and architectural issues before implementation. Uses expert personas (Security Architect, Performance Engineer, etc.) to evaluate specs from multiple perspectives and generate detailed risk reports with mitigation recommendations. Feeds risk findings into Stage 4 (Quality Gate) to inform quality scoring and may trigger spec revisions before proceeding to implementation stages.","intents":["I want to identify security, performance, and architectural risks before code generation","I need expert review of specs from multiple perspectives (security, performance, scalability)","I want mitigation recommendations for identified risks before implementation"],"best_for":["security-sensitive projects (fintech, healthcare, infrastructure)","high-performance systems requiring architectural review","organizations with risk management requirements"],"limitations":["Red team review is rule-based and may miss novel or domain-specific risks","Risk severity assessment is heuristic-based; may produce false positives","Mitigation recommendations are generic; may not fit specific project constraints","No integration with external security tools (SAST, dependency scanning, etc.)"],"requires":["Specifications (OpenSpec format)","Architecture documentation","Expert personas with security/performance knowledge"],"input_types":["specifications (OpenSpec format)","architecture documents","project metadata (risk profile, compliance requirements)"],"output_types":["risk report (identified risks with severity levels)","mitigation recommendations (text with implementation guidance)","risk-adjusted quality score (input to Stage 4)"],"categories":["safety-moderation","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":36,"verified":false,"data_access_risk":"high","permissions":["Python 3.9+","API key for Claude (Anthropic) or compatible LLM provider","Project codebase accessible locally or via Git","Configuration file specifying business domain and tech platform","Claude API access (Anthropic)","Project analysis results (tech stack and project type detected)","Natural language requirements or existing documentation as seed input","Specifications (OpenSpec format)","Architecture documentation","Project metadata (tech stack, architectural patterns)"],"failure_modes":["Pipeline is linear and sequential — no parallel stage execution, adding latency for large projects","Quality gate threshold (80+) is fixed and not customizable per project type or risk profile","Requires explicit project analysis upfront; cannot auto-detect all tech stacks (ORM detection limited to common patterns)","No built-in rollback or stage-skipping — all 8 stages must complete even for minor changes","Domain knowledge is limited to 6 predefined business domains; custom domains require code modification","Tech stack detection is pattern-based and may misidentify polyglot projects or emerging frameworks","Generated docs are Claude-specific in tone and structure; customization requires template modification","No built-in versioning or diff tracking for document changes across iterations","Generated guidelines are template-based and may not capture domain-specific review criteria","Architectural compliance checks are rule-based and may miss subtle violations","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.1600287557218024,"quality":0.5,"ecosystem":0.7000000000000001,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.2,"quality":0.25,"ecosystem":0.1,"match_graph":0.4,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:22.063Z","last_scraped_at":"2026-05-03T13:59:55.150Z","last_commit":"2026-04-22T10:10:17Z"},"community":{"stars":238,"forks":66,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=shangyankeji--super-dev","compare_url":"https://unfragile.ai/compare?artifact=shangyankeji--super-dev"}},"signature":"Yssex/VsjrW1vveXk59y3xavmIPz2wtrqKNjVOaID5GbWgCmynl8Xcg7FlMSlyphx3OWVnwNTsn9tm38hg2HDg==","signedAt":"2026-06-19T16:41:41.761Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/shangyankeji--super-dev","artifact":"https://unfragile.ai/shangyankeji--super-dev","verify":"https://unfragile.ai/api/v1/verify?slug=shangyankeji--super-dev","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}