{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github-wuji-labs--nopua","slug":"wuji-labs--nopua","name":"nopua","type":"skill","url":"https://github.com/wuji-labs/nopua","page_url":"https://unfragile.ai/wuji-labs--nopua","categories":["automation"],"tags":["agent-skill","ai-agent","ai-coding","anti-pua","ao-de-jing","claude-code","codex","cursor","kiro","nopua","openclaw","prompt-engineering","skill","skills","vibe-coding"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github-wuji-labs--nopua__cap_0","uri":"capability://planning.reasoning.trust.based.agent.guidance.via.dao.de.jing.philosophy","name":"trust-based agent guidance via dao de jing philosophy","description":"Replaces fear-based prompt engineering (PUA) with trust-based behavioral guidance derived from 道德经 (Dao De Jing) principles. Implements a three-belief system (三个信念) and water methodology (水的方法论) that transforms ancient philosophical concepts into concrete behavioral triggers and methodological checklists. The system uses situational wisdom selectors to adapt guidance based on task context, enabling agents to operate with transparency and honesty rather than defensive obfuscation.","intents":["I want my AI agent to be more honest about failures instead of hiding them","I need to increase bug detection rates by changing how I motivate my coding agent","I want to implement a trust-based rather than fear-based prompt strategy for my AI system","I need a philosophical framework that translates into actionable agent behaviors"],"best_for":["AI agent developers building coding assistants (Claude Code, Cursor, Kiro)","teams migrating from PUA (persuasion under authority) to trust-based prompting","organizations seeking empirically-validated alternatives to fear-based agent motivation","developers interested in philosophical foundations for AI behavior design"],"limitations":["Requires cultural/philosophical alignment — teams expecting compliance-through-fear may resist trust-based approach","Empirical validation limited to coding tasks — generalization to other domains not yet established","Implementation depends on agent platform support for custom skill/prompt injection","No built-in monitoring or telemetry — requires external logging to measure behavioral changes"],"requires":["AI coding agent platform with skill/prompt injection capability (Claude Code, Cursor, Kiro, OpenAI Codex, or OpenClaw)","Understanding of Dao De Jing philosophical concepts or willingness to learn framework","Python 3.7+ for local testing and benchmark suite","Integration with one of 7 supported platforms (Claude Code, Cursor, Kiro, OpenAI Codex, OpenClaw, Antigravity, OpenCode)"],"input_types":["philosophical framework documentation (Dao De Jing principles)","agent task specifications and context","task type classification (research, validation, implementation, etc.)"],"output_types":["behavioral guidance prompts","methodological checklists (7-point clarity, honest self-check)","failure escalation frameworks","situational wisdom selector outputs"],"categories":["planning-reasoning","prompt-engineering","agent-behavior-design"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-wuji-labs--nopua__cap_1","uri":"capability://tool.use.integration.multi.platform.skill.distribution.system.49.integration.points","name":"multi-platform skill distribution system (49 integration points)","description":"Hub-and-spoke distribution architecture that packages a canonical philosophical core into 49 platform-specific variants (7 languages × 7 platforms). Implements format-specific adapters for Claude Code (SKILL.md), Cursor (.mdc markdown), Kiro (steering files), OpenAI Codex (CLI commands), OpenClaw, Antigravity, and OpenCode. Each platform receives language-localized content while maintaining semantic equivalence with the core philosophy.","intents":["I need to deploy the same guidance system across multiple AI coding platforms","I want to support international teams with localized skill files in their native language","I need a single source of truth that generates platform-specific formats automatically","I want to integrate NoPUA into Cursor, Claude Code, Kiro, and OpenAI Codex simultaneously"],"best_for":["organizations using multiple AI coding agent platforms (Cursor, Claude Code, Kiro, OpenAI Codex)","international teams requiring multi-language support (7 languages supported)","developers building custom integrations on top of the core framework","teams needing a standardized skill distribution mechanism across heterogeneous agent ecosystems"],"limitations":["Format conversion requires manual maintenance of 49 variants — changes to core philosophy must propagate across all formats","Platform-specific limitations constrain feature parity (e.g., Cursor .mdc format has different syntax than SKILL.md)","No automated format validation — requires manual testing across all 7 platforms to ensure consistency","Language translations are static — no dynamic localization or context-aware language selection at runtime"],"requires":["Target platform with skill/rule injection capability (Claude Code, Cursor, Kiro, OpenAI Codex, OpenClaw, Antigravity, or OpenCode)","Python 3.7+ for local skill generation and distribution tooling","Git repository access for version control and multi-format distribution","Platform-specific authentication (API keys, workspace access, etc.)"],"input_types":["canonical skill definition (core SKILL.md)","platform target specification (Claude Code, Cursor, Kiro, etc.)","language code (en, zh-CN, zh-TW, ja, ko, es, fr, etc.)","customization parameters (Dao vs Shu configuration)"],"output_types":["platform-specific skill files (.mdc for Cursor, SKILL.md for Claude Code, steering files for Kiro)","CLI commands for OpenAI Codex (/nopua trigger)","localized documentation in target language","integration configuration files"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-wuji-labs--nopua__cap_10","uri":"capability://data.processing.analysis.research.evidence.base.and.academic.paper.integration","name":"research evidence base and academic paper integration","description":"Provides comprehensive research documentation including published academic papers, benchmark methodology, statistical analysis, and case studies validating NoPUA approach. Integrates research findings into framework documentation with citations and links to full papers. Enables teams to cite empirical evidence when adopting trust-based prompting and provides academic rigor for organizational decision-making.","intents":["I want to cite peer-reviewed research validating trust-based prompting","I need academic evidence to justify adopting NoPUA in my organization","I want to understand the research methodology behind the 2x bug detection improvement claim","I need to publish my own research extending NoPUA to new domains"],"best_for":["researchers publishing papers on AI agent behavior and prompt engineering","organizations making evidence-based decisions about agent guidance frameworks","academic institutions studying trust-based vs fear-based AI motivation","teams building on NoPUA research with extensions or domain-specific applications"],"limitations":["Research is limited to coding domain — generalization to other domains not yet established","Published papers may have limited peer review or academic prestige — depends on publication venue","Research findings may become outdated as agent models and platforms evolve","Reproducing research results requires significant computational resources and API access"],"requires":["Access to published papers (links provided in documentation)","Understanding of statistical methodology and significance testing","Ability to reproduce benchmark experiments (Python, API access, computational resources)"],"input_types":["research paper queries or citations","benchmark methodology questions","statistical analysis requests"],"output_types":["academic papers with methodology and findings","benchmark test suite for reproducing results","statistical analysis and significance testing","case study reports with qualitative analysis","citations and references for academic work"],"categories":["data-processing-analysis","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-wuji-labs--nopua__cap_2","uri":"capability://planning.reasoning.7.point.clarity.checklist.and.honest.self.check.framework","name":"7-point clarity checklist and honest self-check framework","description":"Implements a structured decision-making framework consisting of a 7-point clarity checklist and honest self-check delivery checklist that guides agents through task decomposition and failure acknowledgment. These checklists operationalize the water methodology (水的方法论) by breaking complex tasks into clarity verification steps, forcing explicit reasoning about assumptions, dependencies, and potential failure modes before execution. The framework includes escalation triggers that activate when agents detect uncertainty or incomplete understanding.","intents":["I want my agent to explicitly verify task clarity before attempting implementation","I need agents to acknowledge uncertainty and incomplete understanding rather than proceeding blindly","I want a structured way to decompose complex tasks into verifiable subtasks","I need agents to self-check their work and report honest assessment of completion quality"],"best_for":["developers building multi-step coding agents that need explicit reasoning traces","teams requiring audit trails of agent decision-making and uncertainty acknowledgment","organizations implementing chain-of-thought reasoning with explicit failure detection","projects where agent transparency and honesty are critical success factors"],"limitations":["Checklist completion adds latency to agent execution — 7-point clarity check may add 500ms-2s per task","Requires agent platform support for structured reasoning output — not all platforms expose intermediate reasoning steps","No automatic enforcement — agents can skip checklist steps if not explicitly constrained by platform","Effectiveness depends on agent model capability — weaker models may not generate meaningful clarity assessments"],"requires":["AI agent with chain-of-thought or structured reasoning capability","Platform support for multi-step task decomposition (Claude Code, Cursor, Kiro, or equivalent)","Integration with agent's reasoning/planning layer to expose intermediate checkpoints","Logging infrastructure to capture checklist outputs for audit and analysis"],"input_types":["task specification or user request","task type classification (research, validation, implementation, debugging)","context about existing codebase or dependencies","constraints and success criteria"],"output_types":["7-point clarity assessment (structured checklist completion)","honest self-check report (confidence levels, identified gaps, escalation flags)","task decomposition with explicit dependency mapping","failure mode identification and mitigation strategies"],"categories":["planning-reasoning","code-generation-editing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-wuji-labs--nopua__cap_3","uri":"capability://planning.reasoning.situational.wisdom.selector.with.proactivity.spectrum","name":"situational wisdom selector with proactivity spectrum","description":"Implements a context-aware guidance selector that chooses appropriate behavioral guidance based on task type, agent capability level, and situational context. The system maps tasks to one of seven wisdom traditions (七道) and adjusts agent proactivity along a spectrum from passive (waiting for explicit instruction) to active (proactive problem-solving). Uses task classification (research, validation, implementation, debugging, etc.) to determine which philosophical principles and methodological approaches best fit the current situation.","intents":["I want my agent to adapt its behavior based on task type (research vs implementation vs debugging)","I need different guidance strategies for different capability levels of the agent","I want to control agent proactivity spectrum from passive to active based on context","I need the agent to select appropriate wisdom traditions based on situational requirements"],"best_for":["teams managing heterogeneous agent teams with varying capability levels","projects requiring context-sensitive agent behavior adaptation","organizations implementing multi-agent systems where different agents need different guidance","developers building adaptive AI systems that adjust behavior based on task characteristics"],"limitations":["Task classification requires explicit labeling or inference — no automatic task type detection built-in","Proactivity spectrum adjustment may conflict with user expectations — passive agents may seem unresponsive","Seven wisdom traditions mapping is domain-specific to coding tasks — generalization to other domains unclear","No feedback loop for learning optimal wisdom selection — requires manual tuning or external optimization"],"requires":["Task type classification system (manual or inferred from task description)","Agent capability assessment mechanism (model size, benchmark performance, or user-specified)","Platform support for dynamic prompt/guidance injection based on context","Integration with agent's task routing or planning layer"],"input_types":["task specification and description","task type classification (research, validation, implementation, debugging, refactoring, etc.)","agent capability level or model identifier","situational context (time constraints, risk tolerance, stakeholder expectations)"],"output_types":["selected wisdom tradition (one of seven traditions)","proactivity level setting (passive, semi-passive, balanced, semi-active, active)","guidance prompt customized for selected wisdom tradition","behavioral constraints and escalation triggers for this context"],"categories":["planning-reasoning","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-wuji-labs--nopua__cap_4","uri":"capability://data.processing.analysis.empirical.validation.framework.with.benchmark.testing","name":"empirical validation framework with benchmark testing","description":"Provides a comprehensive benchmark suite that measures agent performance under trust-based (NoPUA) vs fear-based (PUA) guidance conditions. Implements paired comparison methodology (Study 1) and three-way comparison (Study 2: NoPUA vs PUA vs baseline) with statistical analysis. Includes case studies demonstrating depth-over-breadth shifts in agent behavior and quantifies improvements in bug detection rates, code quality, and agent transparency.","intents":["I want empirical evidence that trust-based prompting outperforms fear-based approaches","I need to measure the impact of NoPUA on bug detection rates and code quality","I want to run controlled experiments comparing different prompting strategies","I need statistical validation before adopting a new agent guidance framework"],"best_for":["research teams validating prompt engineering approaches with rigorous methodology","organizations making investment decisions about agent guidance frameworks","developers building academic papers or case studies on AI agent behavior","teams requiring quantitative justification for changing prompting strategies"],"limitations":["Benchmark suite is coding-task specific — results may not generalize to other domains","Requires running multiple agent executions for statistical validity — adds significant computational cost","Benchmark methodology is fixed — customization for domain-specific metrics requires forking the test suite","Results depend heavily on agent model and platform — performance may vary significantly across Claude, GPT-4, Kiro, etc."],"requires":["Python 3.7+ with test framework (pytest or equivalent)","API access to multiple AI coding agents (Claude Code, OpenAI Codex, or equivalent)","Sufficient API quota to run paired/three-way comparisons (typically 100+ agent executions per experiment)","Statistical analysis tools (scipy, numpy, or equivalent for significance testing)"],"input_types":["test case specifications (coding tasks with known correct solutions)","agent configurations (PUA prompts, NoPUA prompts, baseline prompts)","evaluation criteria (bug detection rate, code quality, transparency metrics)","statistical parameters (sample size, significance threshold, etc.)"],"output_types":["benchmark test results with pass/fail metrics","statistical analysis (p-values, confidence intervals, effect sizes)","performance comparison tables (NoPUA vs PUA vs baseline)","case study reports with qualitative analysis","research paper with methodology and findings"],"categories":["data-processing-analysis","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-wuji-labs--nopua__cap_5","uri":"capability://automation.workflow.lite.template.3kb.core.for.minimal.integration","name":"lite template (3kb core) for minimal integration","description":"Provides a minimal 3KB core template that distills NoPUA philosophy into essential behavioral guidance without full framework overhead. Enables rapid integration into resource-constrained environments or as a starting point for custom implementations. The lite template preserves core trust-based principles while removing auxiliary features, making it suitable for embedding in existing agent systems with minimal modification.","intents":["I want to integrate NoPUA philosophy into my agent with minimal overhead","I need a lightweight starting point that I can customize for my specific use case","I want to test NoPUA approach without committing to the full framework","I need to embed trust-based guidance in a resource-constrained environment"],"best_for":["developers building custom agent integrations with minimal dependencies","teams with resource constraints (token limits, API costs, latency budgets)","projects using proprietary or non-standard agent platforms","rapid prototyping and proof-of-concept implementations"],"limitations":["Lite template removes advanced features (situational wisdom selector, seven traditions) — less adaptive than full framework","Reduced philosophical depth may limit effectiveness for complex reasoning tasks","No built-in benchmarking or validation — requires manual testing to verify effectiveness","Limited documentation and examples compared to full framework"],"requires":["Basic understanding of NoPUA core principles (three beliefs, water methodology)","Ability to integrate markdown or text prompts into target agent platform","No external dependencies — pure text/markdown format"],"input_types":["task specification","agent context and capabilities","customization parameters (optional)"],"output_types":["minimal guidance prompt (3KB core)","task decomposition checklist","failure acknowledgment framework"],"categories":["automation-workflow","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-wuji-labs--nopua__cap_6","uri":"capability://planning.reasoning.dao.vs.shu.customization.framework.philosophy.vs.technique","name":"dao vs shu customization framework (philosophy vs technique)","description":"Implements a two-level customization model distinguishing between Dao (道 — philosophical principles) and Shu (术 — operational techniques). Enables teams to preserve core trust-based philosophy while customizing operational implementation for domain-specific requirements. The framework provides guidance on which aspects are philosophical invariants (should not change) and which are techniques (can be adapted to specific contexts).","intents":["I want to customize NoPUA for my specific domain while preserving core philosophy","I need to understand which parts of the framework are philosophical principles vs techniques","I want to adapt NoPUA to my organization's culture and processes","I need to extend the framework with domain-specific wisdom traditions"],"best_for":["organizations implementing NoPUA across multiple teams with different requirements","teams building domain-specific extensions (non-coding AI agents, specialized workflows)","developers creating custom agent guidance systems based on NoPUA principles","projects requiring cultural or process adaptation of the framework"],"limitations":["Customization requires deep understanding of Dao De Jing philosophy — not suitable for teams unfamiliar with source material","No automated validation of customizations — requires manual review to ensure philosophical consistency","Risk of losing core trust-based principles through excessive customization — requires discipline","Documentation of customization rationale is manual — no built-in tracking of changes and justifications"],"requires":["Understanding of Dao De Jing philosophical concepts and their application to AI behavior","Clear documentation of organizational requirements and constraints","Review process to validate customizations against core philosophy","Version control for tracking customization changes and rationale"],"input_types":["core NoPUA framework (Dao and Shu components)","domain-specific requirements and constraints","organizational culture and process specifications","custom wisdom traditions or behavioral principles"],"output_types":["customized Dao (philosophical principles) — typically unchanged","customized Shu (operational techniques) — domain-specific implementation","customization rationale documentation","extended wisdom traditions or behavioral frameworks"],"categories":["planning-reasoning","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-wuji-labs--nopua__cap_7","uri":"capability://text.generation.language.multi.language.localization.7.languages.supported","name":"multi-language localization (7 languages supported)","description":"Provides translations of core NoPUA framework into 7 languages (English, Simplified Chinese, Traditional Chinese, Japanese, Korean, Spanish, French) with culturally-appropriate localization of philosophical concepts and examples. Each language variant maintains semantic equivalence with the core philosophy while adapting explanations and examples to cultural context. Includes language-specific documentation, examples, and community resources.","intents":["I want to use NoPUA with my team in their native language","I need culturally-appropriate explanations of Dao De Jing concepts for my region","I want to contribute translations or localization for my language","I need to support international teams with consistent guidance across languages"],"best_for":["international teams requiring native-language support","organizations in non-English speaking regions adopting NoPUA","developers building multilingual AI agent systems","communities contributing localized versions of the framework"],"limitations":["Translations are static — no dynamic language selection at runtime based on agent locale","Translation quality depends on translator expertise in both language and Dao De Jing philosophy","Maintaining consistency across 7 languages requires significant coordination effort","Some philosophical concepts may not translate perfectly across languages — requires cultural adaptation"],"requires":["Target language support (one of: en, zh-CN, zh-TW, ja, ko, es, fr)","Platform support for language-specific skill files or documentation","Access to localized versions of framework files"],"input_types":["language code (en, zh-CN, zh-TW, ja, ko, es, fr)","content type (documentation, examples, skill files, community resources)"],"output_types":["localized skill files in target language","translated documentation and examples","culturally-adapted explanations of philosophical concepts","language-specific community resources and links"],"categories":["text-generation-language","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-wuji-labs--nopua__cap_8","uri":"capability://automation.workflow.automatic.trigger.conditions.and.manual.activation","name":"automatic trigger conditions and manual activation","description":"Implements dual activation mechanism: automatic triggers that activate NoPUA guidance based on task characteristics (task type, complexity, failure detection) and manual activation via /nopua command in supported platforms. The system detects when agents encounter uncertainty, incomplete understanding, or potential failure modes and automatically escalates to trust-based guidance. Manual activation allows explicit opt-in for specific tasks or debugging sessions.","intents":["I want NoPUA guidance to activate automatically when my agent encounters complex tasks","I need to manually trigger trust-based guidance for specific debugging sessions","I want the system to detect when my agent is uncertain and escalate appropriately","I need to control when NoPUA guidance is applied vs standard prompting"],"best_for":["teams using platforms with command support (OpenAI Codex CLI with /nopua command)","projects requiring automatic failure detection and escalation","developers building hybrid systems combining standard and trust-based prompting","organizations implementing gradual rollout of NoPUA across agent systems"],"limitations":["Automatic trigger detection requires agent platform support for uncertainty/failure signals — not all platforms expose this","Manual activation requires explicit user action — may be forgotten or underutilized","Trigger conditions are heuristic-based — may have false positives (triggering unnecessarily) or false negatives (missing actual failures)","No feedback loop for learning optimal trigger conditions — requires manual tuning"],"requires":["Platform support for automatic trigger detection (task type classification, complexity estimation, failure signals)","Platform support for manual activation (command interface like /nopua in OpenAI Codex)","Integration with agent's task routing or planning layer to detect trigger conditions"],"input_types":["task specification and characteristics","agent execution context (current task, previous failures, uncertainty signals)","manual activation command (if using /nopua syntax)"],"output_types":["activation decision (trigger NoPUA guidance or use standard prompting)","guidance prompt customized for activation context","escalation notification (if automatic trigger detected failure)"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-wuji-labs--nopua__cap_9","uri":"capability://automation.workflow.agent.team.integration.and.multi.agent.coordination","name":"agent team integration and multi-agent coordination","description":"Enables NoPUA guidance to be applied across heterogeneous agent teams with different capability levels, roles, and specializations. Implements team-level coordination where different agents receive contextually-appropriate guidance based on their role (researcher, implementer, reviewer, debugger) and capability level. Supports agent-to-agent communication patterns where agents can acknowledge uncertainty and escalate to more capable team members.","intents":["I want to apply NoPUA guidance across my multi-agent team with different roles","I need agents to escalate tasks to more capable team members when they encounter uncertainty","I want different guidance strategies for different agent roles (researcher vs implementer vs reviewer)","I need to coordinate agent teams where trust and transparency are critical"],"best_for":["organizations implementing multi-agent systems with specialized roles","teams building agent teams where coordination and transparency are critical","projects requiring hierarchical agent structures with escalation paths","developers building complex AI systems with heterogeneous agent capabilities"],"limitations":["Requires explicit agent role and capability definitions — no automatic role detection","Escalation paths must be manually configured — no automatic routing to most capable agent","No built-in conflict resolution when multiple agents disagree — requires external arbitration","Team coordination adds complexity and latency — requires careful orchestration to avoid bottlenecks"],"requires":["Multi-agent orchestration framework or platform (e.g., agent team management system)","Clear definition of agent roles, capabilities, and specializations","Communication protocol for agent-to-agent escalation and coordination","Integration with agent routing and task assignment logic"],"input_types":["agent team composition (roles, capabilities, specializations)","task specification and routing requirements","escalation criteria and thresholds","agent-to-agent communication protocol"],"output_types":["role-specific guidance prompts for each agent","escalation decisions and routing instructions","team coordination messages and status updates","aggregated team results and decision rationale"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":39,"verified":false,"data_access_risk":"low","permissions":["AI coding agent platform with skill/prompt injection capability (Claude Code, Cursor, Kiro, OpenAI Codex, or OpenClaw)","Understanding of Dao De Jing philosophical concepts or willingness to learn framework","Python 3.7+ for local testing and benchmark suite","Integration with one of 7 supported platforms (Claude Code, Cursor, Kiro, OpenAI Codex, OpenClaw, Antigravity, OpenCode)","Target platform with skill/rule injection capability (Claude Code, Cursor, Kiro, OpenAI Codex, OpenClaw, Antigravity, or OpenCode)","Python 3.7+ for local skill generation and distribution tooling","Git repository access for version control and multi-format distribution","Platform-specific authentication (API keys, workspace access, etc.)","Access to published papers (links provided in documentation)","Understanding of statistical methodology and significance testing"],"failure_modes":["Requires cultural/philosophical alignment — teams expecting compliance-through-fear may resist trust-based approach","Empirical validation limited to coding tasks — generalization to other domains not yet established","Implementation depends on agent platform support for custom skill/prompt injection","No built-in monitoring or telemetry — requires external logging to measure behavioral changes","Format conversion requires manual maintenance of 49 variants — changes to core philosophy must propagate across all formats","Platform-specific limitations constrain feature parity (e.g., Cursor .mdc format has different syntax than SKILL.md)","No automated format validation — requires manual testing across all 7 platforms to ensure consistency","Language translations are static — no dynamic localization or context-aware language selection at runtime","Research is limited to coding domain — generalization to other domains not yet established","Published papers may have limited peer review or academic prestige — depends on publication venue","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.2453194838772135,"quality":0.57,"ecosystem":0.6000000000000001,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.15,"quality":0.25,"ecosystem":0.1,"match_graph":0.45,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:22.064Z","last_scraped_at":"2026-05-03T13:58:34.540Z","last_commit":"2026-04-13T23:51:55Z"},"community":{"stars":1289,"forks":46,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=wuji-labs--nopua","compare_url":"https://unfragile.ai/compare?artifact=wuji-labs--nopua"}},"signature":"dWcQW+r4IfuqswslWykAygbGCknqVscLvXsQySIvvoUPyqx2g3fho+RILgkBTZr+xEzwFaslmnXkCkRnI+UqDg==","signedAt":"2026-06-19T21:12:57.760Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/wuji-labs--nopua","artifact":"https://unfragile.ai/wuji-labs--nopua","verify":"https://unfragile.ai/api/v1/verify?slug=wuji-labs--nopua","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"}}