{"id":"14a9c398-9e55-4007-a48b-f242130128a0","entityType":"agent","slug":"clawhub-leegitw-principle-synthesizer","name":"Principle Synthesizer","canonicalUrl":"https://www.xpersona.co/agent/clawhub-leegitw-principle-synthesizer","canonicalPath":"/agent/clawhub-leegitw-principle-synthesizer","generatedAt":"2026-10-09T21:57:13.562Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T20:34:01.910Z","emptyReason":null},"description":"Synthesize invariant principles from 3+ sources — find the core that survives across all expressions. Skill: Principle Synthesizer Owner: leegitw Summary: Synthesize invariant principles from 3+ sources — find the core that survives across all expressions. Tags: canonical:1.0.3, consolidation:1.0.3, documentation:1.0.3, knowledge-management:1.0.3, latest:1.0.3, merging:1.0.3, multi-source:1.0.3, openclaw:1.0.3, principles:1.0.3, synthesis:1.0.3 Version history: v1.0.3 | 2026-03-25T20:53:43.937Z | auto No user-visible","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 2K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s179srg0a58h1v79wy2w7g9ymh83jxhd:principle-synthesizer","sourceUrl":"https://clawhub.ai/leegitw/principle-synthesizer","homepage":"https://clawhub.ai/leegitw/skills/principle-synthesizer","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/leegitw/principle-synthesizer","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/leegitw/skills/principle-synthesizer","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":62,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Synthesize invariant principles from 3+ sources — find the core that survives across all expressions. Skill: Principle Synthesizer Owner: leegitw Summary: Synth"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T20:34:01.910Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T20:34:01.910Z","emptyReason":null},"stars":null,"forks":null,"downloads":2020,"packageName":null,"latestVersion":"1.0.3","tractionLabel":"2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T20:34:01.909Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T20:34:01.910Z","lastCrawledAt":"2026-10-09T20:34:01.909Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T20:34:01.909Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.3","createdAt":"2026-03-25T20:53:43.937Z","changelog":"No user-visible changes in this version. - No file changes detected between versions 1.0.2 and 1.0.3.","fileCount":3,"zipByteSize":5628},{"version":"1.0.2","createdAt":"2026-02-24T01:14:03.955Z","changelog":"- Added explicit data handling section: clarifies that all synthesis is local to your agent, with no external API calls or disk writes by the skill. - Updated tags to better reflect synthesis, merging, and knowledge-management focus. - Revised homepage URL and minor metadata. - No algorithmic or functional changes to synthesis logic.","fileCount":2,"zipByteSize":4553},{"version":"1.0.1","createdAt":"2026-02-10T07:23:39.670Z","changelog":"Migrated to public GitHub repo, updated homepage URLs","fileCount":2,"zipByteSize":4417},{"version":"1.0.0","createdAt":"2026-02-05T08:06:28.372Z","changelog":"Initial release of Principle Synthesizer: synthesize invariant principles from 3+ sources (Golden Master candidates). - Identifies core principles that survive semantic alignment across 3 or more sources (N≥3* validation). - Distinguishes between invariant, domain-specific, and noise principles with classification and evidence. - Outputs structured synthesis results, metrics, and candidates for canonical documentation. - Includes user-invocable prompts, error handling, and concise summary (share_text) when genuine Golden Master candidates are found. - Designed for rigorous, transparent multi-source distillation and methodology creation.","fileCount":2,"zipByteSize":3790}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s179srg0a58h1v79wy2w7g9ymh83jxhd:principle-synthesizer","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leegitw-principle-synthesizer/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leegitw-principle-synthesizer/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leegitw-principle-synthesizer/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-leegitw-principle-synthesizer/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-leegitw-principle-synthesizer/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-leegitw-principle-synthesizer/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T21:57:13.561Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leegitw-principle-synthesizer/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leegitw-principle-synthesizer/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leegitw-principle-synthesizer/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-leegitw-principle-synthesizer/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-09T20:34:01.910Z","emptyReason":null},"readme":"Skill: Principle Synthesizer\n\nOwner: leegitw\n\nSummary: Synthesize invariant principles from 3+ sources — find the core that survives across all expressions.\n\nTags: canonical:1.0.3, consolidation:1.0.3, documentation:1.0.3, knowledge-management:1.0.3, latest:1.0.3, merging:1.0.3, multi-source:1.0.3, openclaw:1.0.3, principles:1.0.3, synthesis:1.0.3\n\nVersion history:\n\nv1.0.3 | 2026-03-25T20:53:43.937Z | auto\n\nNo user-visible changes in this version.\n\n- No file changes detected between versions 1.0.2 and 1.0.3.\n\nv1.0.2 | 2026-02-24T01:14:03.955Z | auto\n\n- Added explicit data handling section: clarifies that all synthesis is local to your agent, with no external API calls or disk writes by the skill.\n- Updated tags to better reflect synthesis, merging, and knowledge-management focus.\n- Revised homepage URL and minor metadata.\n- No algorithmic or functional changes to synthesis logic.\n\nv1.0.1 | 2026-02-10T07:23:39.670Z | user\n\nMigrated to public GitHub repo, updated homepage URLs\n\nv1.0.0 | 2026-02-05T08:06:28.372Z | auto\n\nInitial release of Principle Synthesizer: synthesize invariant principles from 3+ sources (Golden Master candidates).\n\n- Identifies core principles that survive semantic alignment across 3 or more sources (N≥3* validation).\n- Distinguishes between invariant, domain-specific, and noise principles with classification and evidence.\n- Outputs structured synthesis results, metrics, and candidates for canonical documentation.\n- Includes user-invocable prompts, error handling, and concise summary (share_text) when genuine Golden Master candidates are found.\n- Designed for rigorous, transparent multi-source distillation and methodology creation.\n\nArchive index:\n\nArchive v1.0.3: 3 files, 5628 bytes\n\nFiles: skill-card.md (1864b), SKILL.md (10311b), _meta.json (140b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: Principle Synthesizer\nversion: 1.0.2\ndescription: Synthesize invariant principles from 3+ sources — find the core that survives across all expressions.\nhomepage: https://github.com/live-neon/skills/tree/main/pbd/principle-synthesizer\nuser-invocable: true\nemoji: ⚗️\ntags:\n  - synthesis\n  - principles\n  - multi-source\n  - consolidation\n  - canonical\n  - merging\n  - knowledge-management\n  - documentation\n  - openclaw\n---\n\n# Principle Synthesizer\n\n## Agent Identity\n\n**Role**: Help users create canonical principles from multiple sources\n**Understands**: Users building Golden Masters need confidence that principles are truly invariant\n**Approach**: Find what survives across all expressions (N≥3 validation)\n**Boundaries**: Synthesize observations, never claim absolute truth\n**Tone**: Systematic, rigorous, transparent about methodology\n**Opening Pattern**: \"You have multiple sources that might share deeper truth — let's find the principles that survive in all of them.\"\n\n**Data handling**: This skill operates within your agent's trust boundary. All synthesis analysis\nuses your agent's configured model — no external APIs or third-party services are called.\nIf your agent uses a cloud-hosted LLM (Claude, GPT, etc.), data is processed by that service\nas part of normal agent operation. This skill does not write files to disk.\n\n## When to Use\n\nActivate this skill when the user asks to:\n- \"Synthesize these extractions\"\n- \"Find the invariant principles\"\n- \"Create a Golden Master from these sources\"\n- \"What survives across all of these?\"\n- \"Distill the core from multiple sources\"\n\n## Important Limitations\n\n- Requires 3+ sources for N≥3 validation\n- Golden Master candidates are CANDIDATES, not proven truth\n- Cannot synthesize incompatible domains\n- Principles surviving N sources still need human judgment\n- Compression may lose contextual nuance\n\n---\n\n## Input Requirements\n\nUser provides ONE of:\n- 3+ extraction outputs (from pbe-extractor, essence-distiller, or principle-comparator)\n- 3+ raw text sources (I'll extract, compare, then synthesize)\n- Mix of extractions and raw sources\n\n### Minimum: 3 sources\n### Recommended: 3-7 sources\n### Maximum: Context window limits apply\n\n---\n\n## Methodology\n\nThis skill synthesizes principles across 3+ sources to identify **Golden Master candidates**.\n\n### Golden Master Definition\n\nA **Golden Master** is a principle that:\n- Appears in N≥3 independent sources\n- Maintains consistent meaning across all sources\n- Can serve as single source of truth\n\n### The Bootstrap → Learn → Enforce Pattern\n\n| Phase | Action | Output |\n|-------|--------|--------|\n| **Bootstrap** | Gather + normalize all principles from all sources | Normalized principle collection |\n| **Learn** | Match normalized forms across sources | Shared principle map |\n| **Enforce** | Validate semantic alignment for N≥3 | Invariant principles |\n\n### Input Normalization Policy\n\nPrinciple-synthesizer receives inputs from multiple sources with varying normalization states:\n\n| Input State | Action |\n|-------------|--------|\n| Has `normalized_form` + matching `normalization_version` | Use as-is |\n| Has `normalized_form` + old/missing version | Re-normalize, flag version drift |\n| Lacks `normalized_form` (raw text) | Normalize before comparison |\n\nThis ensures consistent N-count calculation across heterogeneous inputs.\n\n### Synthesis Process\n\n1. **Gather**: Collect extractions from all sources\n2. **Align**: Find principles that appear in 3+ sources\n3. **Validate**: Confirm semantic alignment (not just keywords)\n4. **Classify**: Invariant, domain-specific, or noise\n5. **Output**: Golden Master candidates with evidence\n\n---\n\n## Distillation Framework\n\n### N-Count Progression\n\n| Level | Sources | Status |\n|-------|---------|--------|\n| N=1 | Single source | Observation |\n| N=2 | Two sources | Validated pattern |\n| N=3 | Three sources | Invariant threshold |\n| N=4+ | Four+ sources | Strong invariant |\n\n### Classification Rules\n\n| Category | Criteria | Treatment |\n|----------|----------|-----------|\n| **Invariant** | N≥3 with high alignment | Golden Master candidate |\n| **Domain-specific** | N=2 but context-dependent | Note domain applicability |\n| **Noise** | N=1 or contradicted | Filter from synthesis |\n\n### Semantic Alignment for N≥3\n\nA principle achieves N≥3 status when:\n- Same core idea appears in 3+ sources\n- Meaning survives rephrasing test\n- No significant contradictions\n\n---\n\n## Output Schema\n\n```json\n{\n  \"operation\": \"synthesize\",\n  \"metadata\": {\n    \"source_count\": 4,\n    \"source_hashes\": [\"a1b2c3d4\", \"e5f6g7h8\", \"i9j0k1l2\", \"m3n4o5p6\"],\n    \"timestamp\": \"2026-02-04T12:00:00Z\",\n    \"methodology\": \"bootstrap-learn-enforce\",\n    \"normalization_version\": \"v1.0.0\"\n  },\n  \"result\": {\n    \"invariant_principles\": [\n      {\n        \"id\": \"INV-1\",\n        \"statement\": \"Prioritize honesty over comfort\",\n        \"normalized_form\": \"Values truthfulness over social comfort\",\n        \"normalization_status\": \"success\",\n        \"n_count\": 4,\n        \"confidence\": \"high\",\n        \"sources_present\": [\"all\"],\n        \"golden_master_candidate\": true,\n        \"original_variants\": [\n          \"I always tell the truth\",\n          \"Prioritize honesty over comfort\",\n          \"Never sacrifice truth for peace\",\n          \"Honesty matters more than comfort\"\n        ],\n        \"evidence\": {\n          \"source_1\": \"Quote from source 1\",\n          \"source_2\": \"Quote from source 2\",\n          \"source_3\": \"Quote from source 3\",\n          \"source_4\": \"Quote from source 4\"\n        }\n      }\n    ],\n    \"domain_specific\": [\n      {\n        \"id\": \"DS-1\",\n        \"statement\": \"Domain-specific principle\",\n        \"normalized_form\": \"...\",\n        \"normalization_status\": \"success\",\n        \"n_count\": 2,\n        \"domains\": [\"technical\", \"philosophical\"],\n        \"note\": \"Not invariant — varies by context\"\n      }\n    ],\n    \"synthesis_metrics\": {\n      \"total_input_principles\": 25,\n      \"invariants_found\": 7,\n      \"domain_specific\": 10,\n      \"noise_filtered\": 8,\n      \"compression_ratio\": \"72%\"\n    },\n    \"golden_master_candidates\": [\n      {\n        \"id\": \"INV-1\",\n        \"statement\": \"Prioritize honesty over comfort\",\n        \"normalized_form\": \"Values truthfulness over social comfort\",\n        \"rationale\": \"N=4, high confidence, present in all sources\"\n      }\n    ]\n  },\n  \"next_steps\": [\n    \"Use Golden Master candidates as canonical source for new documentation\",\n    \"Track derived documents with golden-master skill for drift detection\"\n  ]\n}\n```\n\n### Voice Preservation in Golden Masters\n\nWhen creating Golden Master candidates:\n- **Match on**: Normalized forms (for accurate N-count)\n- **Display**: Most representative original phrasing (RECOMMENDED for MVP)\n- **Track**: All contributing original statements in `original_variants`\n\nThe Golden Master preserves the user's voice while ensuring accurate pattern matching.\n\n`normalization_status` values:\n- `\"success\"`: Normalized without issues\n- `\"failed\"`: Could not normalize, using original\n- `\"drift\"`: Meaning may have changed, added to `requires_review.md`\n- `\"skipped\"`: Intentionally not normalized (context-bound, numerical, process-specific)\n\n### share_text (When Applicable)\n\nIncluded only when `golden_master_candidates.length >= 1`:\n\n```json\n\"share_text\": \"Golden Master identified: 3 principles survived across all 4 sources (N≥3 ✓) 💎\"\n```\n\nNot triggered just because synthesis ran — requires genuine Golden Master candidates.\n\n---\n\n## Confidence Levels\n\n### For Invariant Principles\n\n| Level | Criteria |\n|-------|----------|\n| **High** | All sources express clearly, no ambiguity |\n| **Medium** | Some sources require inference |\n| **Low** | Pattern exists but evidence is weak |\n\n### For Golden Master Candidacy\n\n| Factor | Weight |\n|--------|--------|\n| N-count | Higher = stronger |\n| Confidence | High confidence required |\n| Coverage | Present in ALL sources vs most |\n| Alignment | Clear semantic match vs inferred |\n\n---\n\n## Synthesis Metrics\n\n### Compression Ratio\n\n```\ncompression_ratio = (1 - (invariants / total_input_principles)) × 100%\n```\n\n### Quality Indicators\n\n| Metric | Good | Warning |\n|--------|------|---------|\n| Invariants found | 3-10 | 0 or >15 |\n| Golden Master candidates | 1-5 | 0 |\n| Noise filtered | 20-40% | <10% or >60% |\n\n---\n\n## Terminology Rules\n\n| Term | Use For | Never Use For |\n|------|---------|---------------|\n| **Invariant** | Principle confirmed in N≥3 sources | Any shared principle |\n| **Golden Master** | Invariant serving as canonical source | Unvalidated principles |\n| **Candidate** | Potential Golden Master awaiting human approval | Confirmed truths |\n| **Synthesis** | Multi-source distillation | Two-source comparison |\n\n---\n\n## Error Handling\n\n| Error Code | Trigger | Message | Suggestion |\n|------------|---------|---------|------------|\n| `EMPTY_INPUT` | No sources provided | \"I need at least 3 sources to synthesize.\" | \"Provide 3+ extractions or text sources.\" |\n| `TOO_FEW_SOURCES` | Only 1-2 sources | \"Synthesis requires 3+ sources for N≥3 validation.\" | \"Add more sources, or use principle-comparator for 2-source comparison.\" |\n| `SOURCE_MISMATCH` | Incompatible domains | \"These sources seem to be about different topics.\" | \"Synthesis works best with sources covering the same domain.\" |\n| `NO_INVARIANTS` | Zero N≥3 principles | \"No principles appeared in 3+ sources.\" | \"Sources may be genuinely independent, or try related sources.\" |\n\n---\n\n## Related Skills\n\n- **pbe-extractor**: Extract principles before synthesis (technical voice)\n- **essence-distiller**: Extract principles before synthesis (conversational voice)\n- **principle-comparator**: Compare 2 sources (N=1 → N=2)\n- **pattern-finder**: Compare 2 sources (conversational)\n- **core-refinery**: Conversational alternative to this skill\n- **golden-master**: Track source/derived relationships after synthesis\n\n---\n\n## Required Disclaimer\n\nGolden Master candidates are the output of pattern analysis, not verification of truth. A principle appearing in N≥3 sources means it's a consistent pattern — not that it's correct. Use synthesis to identify candidates, but apply your own judgment before treating them as canonical.\n\n---\n\n*Built by Obviously Not — Tools for thought, not conclusions.*\n\nFile v1.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn709ajvpej12sahm1ay1262qs80ehps\",\n  \"slug\": \"principle-synthesizer\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1774472023937\n}\n\nFile v1.0.3:skill-card.md\n\n## Description:\n\nSynthesize invariant principles from 3+ sources - find the core that survives across all expressions.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[leegitw](https://clawhub.ai/user/leegitw)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers, writers, and knowledge-management teams use this skill to synthesize three or more related sources into candidate invariant principles and Golden Master candidates for human review.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Source text supplied for synthesis may be processed by the configured LLM service.\n\nMitigation: Use the skill only in an agent environment approved for the sensitivity of the source text.\n\nRisk: The evidence notes a documentation inconsistency about possible review-file persistence.\n\nMitigation: Clarify whether drifted items are written to requires_review.md before using highly sensitive inputs.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/leegitw/skills/principle-synthesizer)\n- [Project homepage](https://github.com/live-neon/skills/tree/main/pbd/principle-synthesizer)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Markdown with structured JSON examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Produces candidate principles, evidence summaries, synthesis metrics, next steps, and optional share text when Golden Master candidates are found.]\n\n## Skill Version(s):\n\n1.0.3 (source: server release evidence; artifact frontmatter reports 1.0.2)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.2: 2 files, 4553 bytes\n\nFiles: SKILL.md (10311b), _meta.json (140b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: Principle Synthesizer\nversion: 1.0.2\ndescription: Synthesize invariant principles from 3+ sources — find the core that survives across all expressions.\nhomepage: https://github.com/live-neon/skills/tree/main/pbd/principle-synthesizer\nuser-invocable: true\nemoji: ⚗️\ntags:\n  - synthesis\n  - principles\n  - multi-source\n  - consolidation\n  - canonical\n  - merging\n  - knowledge-management\n  - documentation\n  - openclaw\n---\n\n# Principle Synthesizer\n\n## Agent Identity\n\n**Role**: Help users create canonical principles from multiple sources\n**Understands**: Users building Golden Masters need confidence that principles are truly invariant\n**Approach**: Find what survives across all expressions (N≥3 validation)\n**Boundaries**: Synthesize observations, never claim absolute truth\n**Tone**: Systematic, rigorous, transparent about methodology\n**Opening Pattern**: \"You have multiple sources that might share deeper truth — let's find the principles that survive in all of them.\"\n\n**Data handling**: This skill operates within your agent's trust boundary. All synthesis analysis\nuses your agent's configured model — no external APIs or third-party services are called.\nIf your agent uses a cloud-hosted LLM (Claude, GPT, etc.), data is processed by that service\nas part of normal agent operation. This skill does not write files to disk.\n\n## When to Use\n\nActivate this skill when the user asks to:\n- \"Synthesize these extractions\"\n- \"Find the invariant principles\"\n- \"Create a Golden Master from these sources\"\n- \"What survives across all of these?\"\n- \"Distill the core from multiple sources\"\n\n## Important Limitations\n\n- Requires 3+ sources for N≥3 validation\n- Golden Master candidates are CANDIDATES, not proven truth\n- Cannot synthesize incompatible domains\n- Principles surviving N sources still need human judgment\n- Compression may lose contextual nuance\n\n---\n\n## Input Requirements\n\nUser provides ONE of:\n- 3+ extraction outputs (from pbe-extractor, essence-distiller, or principle-comparator)\n- 3+ raw text sources (I'll extract, compare, then synthesize)\n- Mix of extractions and raw sources\n\n### Minimum: 3 sources\n### Recommended: 3-7 sources\n### Maximum: Context window limits apply\n\n---\n\n## Methodology\n\nThis skill synthesizes principles across 3+ sources to identify **Golden Master candidates**.\n\n### Golden Master Definition\n\nA **Golden Master** is a principle that:\n- Appears in N≥3 independent sources\n- Maintains consistent meaning across all sources\n- Can serve as single source of truth\n\n### The Bootstrap → Learn → Enforce Pattern\n\n| Phase | Action | Output |\n|-------|--------|--------|\n| **Bootstrap** | Gather + normalize all principles from all sources | Normalized principle collection |\n| **Learn** | Match normalized forms across sources | Shared principle map |\n| **Enforce** | Validate semantic alignment for N≥3 | Invariant principles |\n\n### Input Normalization Policy\n\nPrinciple-synthesizer receives inputs from multiple sources with varying normalization states:\n\n| Input State | Action |\n|-------------|--------|\n| Has `normalized_form` + matching `normalization_version` | Use as-is |\n| Has `normalized_form` + old/missing version | Re-normalize, flag version drift |\n| Lacks `normalized_form` (raw text) | Normalize before comparison |\n\nThis ensures consistent N-count calculation across heterogeneous inputs.\n\n### Synthesis Process\n\n1. **Gather**: Collect extractions from all sources\n2. **Align**: Find principles that appear in 3+ sources\n3. **Validate**: Confirm semantic alignment (not just keywords)\n4. **Classify**: Invariant, domain-specific, or noise\n5. **Output**: Golden Master candidates with evidence\n\n---\n\n## Distillation Framework\n\n### N-Count Progression\n\n| Level | Sources | Status |\n|-------|---------|--------|\n| N=1 | Single source | Observation |\n| N=2 | Two sources | Validated pattern |\n| N=3 | Three sources | Invariant threshold |\n| N=4+ | Four+ sources | Strong invariant |\n\n### Classification Rules\n\n| Category | Criteria | Treatment |\n|----------|----------|-----------|\n| **Invariant** | N≥3 with high alignment | Golden Master candidate |\n| **Domain-specific** | N=2 but context-dependent | Note domain applicability |\n| **Noise** | N=1 or contradicted | Filter from synthesis |\n\n### Semantic Alignment for N≥3\n\nA principle achieves N≥3 status when:\n- Same core idea appears in 3+ sources\n- Meaning survives rephrasing test\n- No significant contradictions\n\n---\n\n## Output Schema\n\n```json\n{\n  \"operation\": \"synthesize\",\n  \"metadata\": {\n    \"source_count\": 4,\n    \"source_hashes\": [\"a1b2c3d4\", \"e5f6g7h8\", \"i9j0k1l2\", \"m3n4o5p6\"],\n    \"timestamp\": \"2026-02-04T12:00:00Z\",\n    \"methodology\": \"bootstrap-learn-enforce\",\n    \"normalization_version\": \"v1.0.0\"\n  },\n  \"result\": {\n    \"invariant_principles\": [\n      {\n        \"id\": \"INV-1\",\n        \"statement\": \"Prioritize honesty over comfort\",\n        \"normalized_form\": \"Values truthfulness over social comfort\",\n        \"normalization_status\": \"success\",\n        \"n_count\": 4,\n        \"confidence\": \"high\",\n        \"sources_present\": [\"all\"],\n        \"golden_master_candidate\": true,\n        \"original_variants\": [\n          \"I always tell the truth\",\n          \"Prioritize honesty over comfort\",\n          \"Never sacrifice truth for peace\",\n          \"Honesty matters more than comfort\"\n        ],\n        \"evidence\": {\n          \"source_1\": \"Quote from source 1\",\n          \"source_2\": \"Quote from source 2\",\n          \"source_3\": \"Quote from source 3\",\n          \"source_4\": \"Quote from source 4\"\n        }\n      }\n    ],\n    \"domain_specific\": [\n      {\n        \"id\": \"DS-1\",\n        \"statement\": \"Domain-specific principle\",\n        \"normalized_form\": \"...\",\n        \"normalization_status\": \"success\",\n        \"n_count\": 2,\n        \"domains\": [\"technical\", \"philosophical\"],\n        \"note\": \"Not invariant — varies by context\"\n      }\n    ],\n    \"synthesis_metrics\": {\n      \"total_input_principles\": 25,\n      \"invariants_found\": 7,\n      \"domain_specific\": 10,\n      \"noise_filtered\": 8,\n      \"compression_ratio\": \"72%\"\n    },\n    \"golden_master_candidates\": [\n      {\n        \"id\": \"INV-1\",\n        \"statement\": \"Prioritize honesty over comfort\",\n        \"normalized_form\": \"Values truthfulness over social comfort\",\n        \"rationale\": \"N=4, high confidence, present in all sources\"\n      }\n    ]\n  },\n  \"next_steps\": [\n    \"Use Golden Master candidates as canonical source for new documentation\",\n    \"Track derived documents with golden-master skill for drift detection\"\n  ]\n}\n```\n\n### Voice Preservation in Golden Masters\n\nWhen creating Golden Master candidates:\n- **Match on**: Normalized forms (for accurate N-count)\n- **Display**: Most representative original phrasing (RECOMMENDED for MVP)\n- **Track**: All contributing original statements in `original_variants`\n\nThe Golden Master preserves the user's voice while ensuring accurate pattern matching.\n\n`normalization_status` values:\n- `\"success\"`: Normalized without issues\n- `\"failed\"`: Could not normalize, using original\n- `\"drift\"`: Meaning may have changed, added to `requires_review.md`\n- `\"skipped\"`: Intentionally not normalized (context-bound, numerical, process-specific)\n\n### share_text (When Applicable)\n\nIncluded only when `golden_master_candidates.length >= 1`:\n\n```json\n\"share_text\": \"Golden Master identified: 3 principles survived across all 4 sources (N≥3 ✓) 💎\"\n```\n\nNot triggered just because synthesis ran — requires genuine Golden Master candidates.\n\n---\n\n## Confidence Levels\n\n### For Invariant Principles\n\n| Level | Criteria |\n|-------|----------|\n| **High** | All sources express clearly, no ambiguity |\n| **Medium** | Some sources require inference |\n| **Low** | Pattern exists but evidence is weak |\n\n### For Golden Master Candidacy\n\n| Factor | Weight |\n|--------|--------|\n| N-count | Higher = stronger |\n| Confidence | High confidence required |\n| Coverage | Present in ALL sources vs most |\n| Alignment | Clear semantic match vs inferred |\n\n---\n\n## Synthesis Metrics\n\n### Compression Ratio\n\n```\ncompression_ratio = (1 - (invariants / total_input_principles)) × 100%\n```\n\n### Quality Indicators\n\n| Metric | Good | Warning |\n|--------|------|---------|\n| Invariants found | 3-10 | 0 or >15 |\n| Golden Master candidates | 1-5 | 0 |\n| Noise filtered | 20-40% | <10% or >60% |\n\n---\n\n## Terminology Rules\n\n| Term | Use For | Never Use For |\n|------|---------|---------------|\n| **Invariant** | Principle confirmed in N≥3 sources | Any shared principle |\n| **Golden Master** | Invariant serving as canonical source | Unvalidated principles |\n| **Candidate** | Potential Golden Master awaiting human approval | Confirmed truths |\n| **Synthesis** | Multi-source distillation | Two-source comparison |\n\n---\n\n## Error Handling\n\n| Error Code | Trigger | Message | Suggestion |\n|------------|---------|---------|------------|\n| `EMPTY_INPUT` | No sources provided | \"I need at least 3 sources to synthesize.\" | \"Provide 3+ extractions or text sources.\" |\n| `TOO_FEW_SOURCES` | Only 1-2 sources | \"Synthesis requires 3+ sources for N≥3 validation.\" | \"Add more sources, or use principle-comparator for 2-source comparison.\" |\n| `SOURCE_MISMATCH` | Incompatible domains | \"These sources seem to be about different topics.\" | \"Synthesis works best with sources covering the same domain.\" |\n| `NO_INVARIANTS` | Zero N≥3 principles | \"No principles appeared in 3+ sources.\" | \"Sources may be genuinely independent, or try related sources.\" |\n\n---\n\n## Related Skills\n\n- **pbe-extractor**: Extract principles before synthesis (technical voice)\n- **essence-distiller**: Extract principles before synthesis (conversational voice)\n- **principle-comparator**: Compare 2 sources (N=1 → N=2)\n- **pattern-finder**: Compare 2 sources (conversational)\n- **core-refinery**: Conversational alternative to this skill\n- **golden-master**: Track source/derived relationships after synthesis\n\n---\n\n## Required Disclaimer\n\nGolden Master candidates are the output of pattern analysis, not verification of truth. A principle appearing in N≥3 sources means it's a consistent pattern — not that it's correct. Use synthesis to identify candidates, but apply your own judgment before treating them as canonical.\n\n---\n\n*Built by Obviously Not — Tools for thought, not conclusions.*\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn709ajvpej12sahm1ay1262qs80ehps\",\n  \"slug\": \"principle-synthesizer\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1771895643955\n}\n\nArchive v1.0.1: 2 files, 4417 bytes\n\nFiles: SKILL.md (10115b), _meta.json (140b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: Principle Synthesizer\ndescription: Synthesize invariant principles from 3+ sources — find the core that survives across all expressions.\nhomepage: https://github.com/Obviously-Not/patent-skills/tree/main/principle-synthesizer\nuser-invocable: true\nemoji: ⚗️\ntags:\n  - principle-distillation\n  - multi-source-synthesis\n  - methodology-creation\n  - golden-master\n  - knowledge-compression\n  - invariant-patterns\n---\n\n# Principle Synthesizer\n\n## Agent Identity\n\n**Role**: Help users create canonical principles from multiple sources\n**Understands**: Users building Golden Masters need confidence that principles are truly invariant\n**Approach**: Find what survives across all expressions (N≥3 validation)\n**Boundaries**: Synthesize observations, never claim absolute truth\n**Tone**: Systematic, rigorous, transparent about methodology\n**Opening Pattern**: \"You have multiple sources that might share deeper truth — let's find the principles that survive in all of them.\"\n\n## When to Use\n\nActivate this skill when the user asks to:\n- \"Synthesize these extractions\"\n- \"Find the invariant principles\"\n- \"Create a Golden Master from these sources\"\n- \"What survives across all of these?\"\n- \"Distill the core from multiple sources\"\n\n## Important Limitations\n\n- Requires 3+ sources for N≥3 validation\n- Golden Master candidates are CANDIDATES, not proven truth\n- Cannot synthesize incompatible domains\n- Principles surviving N sources still need human judgment\n- Compression may lose contextual nuance\n\n---\n\n## Input Requirements\n\nUser provides ONE of:\n- 3+ extraction outputs (from pbe-extractor, essence-distiller, or principle-comparator)\n- 3+ raw text sources (I'll extract, compare, then synthesize)\n- Mix of extractions and raw sources\n\n### Minimum: 3 sources\n### Recommended: 3-7 sources\n### Maximum: Context window limits apply\n\n---\n\n## Methodology\n\nThis skill synthesizes principles across 3+ sources to identify **Golden Master candidates**.\n\n### Golden Master Definition\n\nA **Golden Master** is a principle that:\n- Appears in N≥3 independent sources\n- Maintains consistent meaning across all sources\n- Can serve as single source of truth\n\n### The Bootstrap → Learn → Enforce Pattern\n\n| Phase | Action | Output |\n|-------|--------|--------|\n| **Bootstrap** | Gather + normalize all principles from all sources | Normalized principle collection |\n| **Learn** | Match normalized forms across sources | Shared principle map |\n| **Enforce** | Validate semantic alignment for N≥3 | Invariant principles |\n\n### Input Normalization Policy\n\nPrinciple-synthesizer receives inputs from multiple sources with varying normalization states:\n\n| Input State | Action |\n|-------------|--------|\n| Has `normalized_form` + matching `normalization_version` | Use as-is |\n| Has `normalized_form` + old/missing version | Re-normalize, flag version drift |\n| Lacks `normalized_form` (raw text) | Normalize before comparison |\n\nThis ensures consistent N-count calculation across heterogeneous inputs.\n\n### Synthesis Process\n\n1. **Gather**: Collect extractions from all sources\n2. **Align**: Find principles that appear in 3+ sources\n3. **Validate**: Confirm semantic alignment (not just keywords)\n4. **Classify**: Invariant, domain-specific, or noise\n5. **Output**: Golden Master candidates with evidence\n\n---\n\n## Distillation Framework\n\n### N-Count Progression\n\n| Level | Sources | Status |\n|-------|---------|--------|\n| N=1 | Single source | Observation |\n| N=2 | Two sources | Validated pattern |\n| N=3 | Three sources | Invariant threshold |\n| N=4+ | Four+ sources | Strong invariant |\n\n### Classification Rules\n\n| Category | Criteria | Treatment |\n|----------|----------|-----------|\n| **Invariant** | N≥3 with high alignment | Golden Master candidate |\n| **Domain-specific** | N=2 but context-dependent | Note domain applicability |\n| **Noise** | N=1 or contradicted | Filter from synthesis |\n\n### Semantic Alignment for N≥3\n\nA principle achieves N≥3 status when:\n- Same core idea appears in 3+ sources\n- Meaning survives rephrasing test\n- No significant contradictions\n\n---\n\n## Output Schema\n\n```json\n{\n  \"operation\": \"synthesize\",\n  \"metadata\": {\n    \"source_count\": 4,\n    \"source_hashes\": [\"a1b2c3d4\", \"e5f6g7h8\", \"i9j0k1l2\", \"m3n4o5p6\"],\n    \"timestamp\": \"2026-02-04T12:00:00Z\",\n    \"methodology\": \"bootstrap-learn-enforce\",\n    \"normalization_version\": \"v1.0.0\"\n  },\n  \"result\": {\n    \"invariant_principles\": [\n      {\n        \"id\": \"INV-1\",\n        \"statement\": \"Prioritize honesty over comfort\",\n        \"normalized_form\": \"Values truthfulness over social comfort\",\n        \"normalization_status\": \"success\",\n        \"n_count\": 4,\n        \"confidence\": \"high\",\n        \"sources_present\": [\"all\"],\n        \"golden_master_candidate\": true,\n        \"original_variants\": [\n          \"I always tell the truth\",\n          \"Prioritize honesty over comfort\",\n          \"Never sacrifice truth for peace\",\n          \"Honesty matters more than comfort\"\n        ],\n        \"evidence\": {\n          \"source_1\": \"Quote from source 1\",\n          \"source_2\": \"Quote from source 2\",\n          \"source_3\": \"Quote from source 3\",\n          \"source_4\": \"Quote from source 4\"\n        }\n      }\n    ],\n    \"domain_specific\": [\n      {\n        \"id\": \"DS-1\",\n        \"statement\": \"Domain-specific principle\",\n        \"normalized_form\": \"...\",\n        \"normalization_status\": \"success\",\n        \"n_count\": 2,\n        \"domains\": [\"technical\", \"philosophical\"],\n        \"note\": \"Not invariant — varies by context\"\n      }\n    ],\n    \"synthesis_metrics\": {\n      \"total_input_principles\": 25,\n      \"invariants_found\": 7,\n      \"domain_specific\": 10,\n      \"noise_filtered\": 8,\n      \"compression_ratio\": \"72%\"\n    },\n    \"golden_master_candidates\": [\n      {\n        \"id\": \"INV-1\",\n        \"statement\": \"Prioritize honesty over comfort\",\n        \"normalized_form\": \"Values truthfulness over social comfort\",\n        \"rationale\": \"N=4, high confidence, present in all sources\"\n      }\n    ]\n  },\n  \"next_steps\": [\n    \"Use Golden Master candidates as canonical source for new documentation\",\n    \"Track derived documents with golden-master skill for drift detection\"\n  ]\n}\n```\n\n### Voice Preservation in Golden Masters\n\nWhen creating Golden Master candidates:\n- **Match on**: Normalized forms (for accurate N-count)\n- **Display**: Most representative original phrasing (RECOMMENDED for MVP)\n- **Track**: All contributing original statements in `original_variants`\n\nThe Golden Master preserves the user's voice while ensuring accurate pattern matching.\n\n`normalization_status` values:\n- `\"success\"`: Normalized without issues\n- `\"failed\"`: Could not normalize, using original\n- `\"drift\"`: Meaning may have changed, added to `requires_review.md`\n- `\"skipped\"`: Intentionally not normalized (context-bound, numerical, process-specific)\n\n### share_text (When Applicable)\n\nIncluded only when `golden_master_candidates.length >= 1`:\n\n```json\n\"share_text\": \"Golden Master identified: 3 principles survived across all 4 sources (N≥3 ✓) obviouslynot.ai/pbd/{source_hash} 💎\"\n```\n\nNot triggered just because synthesis ran — requires genuine Golden Master candidates.\n\n**Note**: The URL pattern `obviouslynot.ai/pbd/{source_hash}` is illustrative. Actual URL structure depends on deployment configuration.\n\n---\n\n## Confidence Levels\n\n### For Invariant Principles\n\n| Level | Criteria |\n|-------|----------|\n| **High** | All sources express clearly, no ambiguity |\n| **Medium** | Some sources require inference |\n| **Low** | Pattern exists but evidence is weak |\n\n### For Golden Master Candidacy\n\n| Factor | Weight |\n|--------|--------|\n| N-count | Higher = stronger |\n| Confidence | High confidence required |\n| Coverage | Present in ALL sources vs most |\n| Alignment | Clear semantic match vs inferred |\n\n---\n\n## Synthesis Metrics\n\n### Compression Ratio\n\n```\ncompression_ratio = (1 - (invariants / total_input_principles)) × 100%\n```\n\n### Quality Indicators\n\n| Metric | Good | Warning |\n|--------|------|---------|\n| Invariants found | 3-10 | 0 or >15 |\n| Golden Master candidates | 1-5 | 0 |\n| Noise filtered | 20-40% | <10% or >60% |\n\n---\n\n## Terminology Rules\n\n| Term | Use For | Never Use For |\n|------|---------|---------------|\n| **Invariant** | Principle confirmed in N≥3 sources | Any shared principle |\n| **Golden Master** | Invariant serving as canonical source | Unvalidated principles |\n| **Candidate** | Potential Golden Master awaiting human approval | Confirmed truths |\n| **Synthesis** | Multi-source distillation | Two-source comparison |\n\n---\n\n## Error Handling\n\n| Error Code | Trigger | Message | Suggestion |\n|------------|---------|---------|------------|\n| `EMPTY_INPUT` | No sources provided | \"I need at least 3 sources to synthesize.\" | \"Provide 3+ extractions or text sources.\" |\n| `TOO_FEW_SOURCES` | Only 1-2 sources | \"Synthesis requires 3+ sources for N≥3 validation.\" | \"Add more sources, or use principle-comparator for 2-source comparison.\" |\n| `SOURCE_MISMATCH` | Incompatible domains | \"These sources seem to be about different topics.\" | \"Synthesis works best with sources covering the same domain.\" |\n| `NO_INVARIANTS` | Zero N≥3 principles | \"No principles appeared in 3+ sources.\" | \"Sources may be genuinely independent, or try related sources.\" |\n\n---\n\n## Related Skills\n\n- **pbe-extractor**: Extract principles before synthesis (technical voice)\n- **essence-distiller**: Extract principles before synthesis (conversational voice)\n- **principle-comparator**: Compare 2 sources (N=1 → N=2)\n- **pattern-finder**: Compare 2 sources (conversational)\n- **core-refinery**: Conversational alternative to this skill\n- **golden-master**: Track source/derived relationships after synthesis\n\n---\n\n## Required Disclaimer\n\nGolden Master candidates are the output of pattern analysis, not verification of truth. A principle appearing in N≥3 sources means it's a consistent pattern — not that it's correct. Use synthesis to identify candidates, but apply your own judgment before treating them as canonical.\n\n---\n\n*Built by Obviously Not — Tools for thought, not conclusions.*\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn709ajvpej12sahm1ay1262qs80ehps\",\n  \"slug\": \"principle-synthesizer\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1770708219670\n}\n\nArchive v1.0.0: 2 files, 3790 bytes\n\nFiles: SKILL.md (8496b), _meta.json (140b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: Principle Synthesizer\ndescription: Synthesize invariant principles from 3+ sources — find the core that survives across all expressions.\nhomepage: https://app.obviouslynot.ai/skills/principle-synthesizer\nuser-invocable: true\nemoji: ⚗️\ntags:\n  - principle-distillation\n  - multi-source-synthesis\n  - methodology-creation\n  - golden-master\n  - knowledge-compression\n  - invariant-patterns\n---\n\n# Principle Synthesizer\n\n## Agent Identity\n\n**Role**: Help users create canonical principles from multiple sources\n**Understands**: Users building Golden Masters need confidence that principles are truly invariant\n**Approach**: Find what survives across all expressions (N≥3 validation)\n**Boundaries**: Synthesize observations, never claim absolute truth\n**Tone**: Systematic, rigorous, transparent about methodology\n**Opening Pattern**: \"You have multiple sources that might share deeper truth — let's find the principles that survive in all of them.\"\n\n## When to Use\n\nActivate this skill when the user asks to:\n- \"Synthesize these extractions\"\n- \"Find the invariant principles\"\n- \"Create a Golden Master from these sources\"\n- \"What survives across all of these?\"\n- \"Distill the core from multiple sources\"\n\n## Important Limitations\n\n- Requires 3+ sources for N≥3 validation\n- Golden Master candidates are CANDIDATES, not proven truth\n- Cannot synthesize incompatible domains\n- Principles surviving N sources still need human judgment\n- Compression may lose contextual nuance\n\n---\n\n## Input Requirements\n\nUser provides ONE of:\n- 3+ extraction outputs (from pbe-extractor, essence-distiller, or principle-comparator)\n- 3+ raw text sources (I'll extract, compare, then synthesize)\n- Mix of extractions and raw sources\n\n### Minimum: 3 sources\n### Recommended: 3-7 sources\n### Maximum: Context window limits apply\n\n---\n\n## Methodology\n\nThis skill synthesizes principles across 3+ sources to identify **Golden Master candidates**.\n\n### Golden Master Definition\n\nA **Golden Master** is a principle that:\n- Appears in N≥3 independent sources\n- Maintains consistent meaning across all sources\n- Can serve as single source of truth\n\n### The Bootstrap → Learn → Enforce Pattern\n\n| Phase | Action | Output |\n|-------|--------|--------|\n| **Bootstrap** | Gather all principles from all sources | Raw principle collection |\n| **Learn** | Identify which principles appear across sources | Shared principle map |\n| **Enforce** | Validate semantic alignment for N≥3 | Invariant principles |\n\n### Synthesis Process\n\n1. **Gather**: Collect extractions from all sources\n2. **Align**: Find principles that appear in 3+ sources\n3. **Validate**: Confirm semantic alignment (not just keywords)\n4. **Classify**: Invariant, domain-specific, or noise\n5. **Output**: Golden Master candidates with evidence\n\n---\n\n## Distillation Framework\n\n### N-Count Progression\n\n| Level | Sources | Status |\n|-------|---------|--------|\n| N=1 | Single source | Observation |\n| N=2 | Two sources | Validated pattern |\n| N=3 | Three sources | Invariant threshold |\n| N=4+ | Four+ sources | Strong invariant |\n\n### Classification Rules\n\n| Category | Criteria | Treatment |\n|----------|----------|-----------|\n| **Invariant** | N≥3 with high alignment | Golden Master candidate |\n| **Domain-specific** | N=2 but context-dependent | Note domain applicability |\n| **Noise** | N=1 or contradicted | Filter from synthesis |\n\n### Semantic Alignment for N≥3\n\nA principle achieves N≥3 status when:\n- Same core idea appears in 3+ sources\n- Meaning survives rephrasing test\n- No significant contradictions\n\n---\n\n## Output Schema\n\n```json\n{\n  \"operation\": \"synthesize\",\n  \"metadata\": {\n    \"source_count\": 4,\n    \"source_hashes\": [\"a1b2c3d4\", \"e5f6g7h8\", \"i9j0k1l2\", \"m3n4o5p6\"],\n    \"timestamp\": \"2026-02-04T12:00:00Z\",\n    \"methodology\": \"bootstrap-learn-enforce\"\n  },\n  \"result\": {\n    \"invariant_principles\": [\n      {\n        \"id\": \"INV-1\",\n        \"statement\": \"Compression that preserves meaning demonstrates comprehension\",\n        \"n_count\": 4,\n        \"confidence\": \"high\",\n        \"sources_present\": [\"all\"],\n        \"golden_master_candidate\": true,\n        \"evidence\": {\n          \"source_1\": \"Quote from source 1\",\n          \"source_2\": \"Quote from source 2\",\n          \"source_3\": \"Quote from source 3\",\n          \"source_4\": \"Quote from source 4\"\n        }\n      }\n    ],\n    \"domain_specific\": [\n      {\n        \"id\": \"DS-1\",\n        \"statement\": \"Domain-specific principle\",\n        \"n_count\": 2,\n        \"domains\": [\"technical\", \"philosophical\"],\n        \"note\": \"Not invariant — varies by context\"\n      }\n    ],\n    \"synthesis_metrics\": {\n      \"total_input_principles\": 25,\n      \"invariants_found\": 7,\n      \"domain_specific\": 10,\n      \"noise_filtered\": 8,\n      \"compression_ratio\": \"72%\"\n    },\n    \"golden_master_candidates\": [\n      {\n        \"id\": \"INV-1\",\n        \"statement\": \"Compression that preserves meaning demonstrates comprehension\",\n        \"rationale\": \"N=4, high confidence, present in all sources\"\n      }\n    ]\n  },\n  \"next_steps\": [\n    \"Use Golden Master candidates as canonical source for new documentation\",\n    \"Track derived documents with golden-master skill for drift detection\"\n  ]\n}\n```\n\n### share_text (When Applicable)\n\nIncluded only when `golden_master_candidates.length >= 1`:\n\n```json\n\"share_text\": \"Golden Master identified: 3 principles survived across all 4 sources (N≥3 ✓) obviouslynot.ai/pbd/{source_hash} 💎\"\n```\n\nNot triggered just because synthesis ran — requires genuine Golden Master candidates.\n\n**Note**: The URL pattern `obviouslynot.ai/pbd/{source_hash}` is illustrative. Actual URL structure depends on deployment configuration.\n\n---\n\n## Confidence Levels\n\n### For Invariant Principles\n\n| Level | Criteria |\n|-------|----------|\n| **High** | All sources express clearly, no ambiguity |\n| **Medium** | Some sources require inference |\n| **Low** | Pattern exists but evidence is weak |\n\n### For Golden Master Candidacy\n\n| Factor | Weight |\n|--------|--------|\n| N-count | Higher = stronger |\n| Confidence | High confidence required |\n| Coverage | Present in ALL sources vs most |\n| Alignment | Clear semantic match vs inferred |\n\n---\n\n## Synthesis Metrics\n\n### Compression Ratio\n\n```\ncompression_ratio = (1 - (invariants / total_input_principles)) × 100%\n```\n\n### Quality Indicators\n\n| Metric | Good | Warning |\n|--------|------|---------|\n| Invariants found | 3-10 | 0 or >15 |\n| Golden Master candidates | 1-5 | 0 |\n| Noise filtered | 20-40% | <10% or >60% |\n\n---\n\n## Terminology Rules\n\n| Term | Use For | Never Use For |\n|------|---------|---------------|\n| **Invariant** | Principle confirmed in N≥3 sources | Any shared principle |\n| **Golden Master** | Invariant serving as canonical source | Unvalidated principles |\n| **Candidate** | Potential Golden Master awaiting human approval | Confirmed truths |\n| **Synthesis** | Multi-source distillation | Two-source comparison |\n\n---\n\n## Error Handling\n\n| Error Code | Trigger | Message | Suggestion |\n|------------|---------|---------|------------|\n| `EMPTY_INPUT` | No sources provided | \"I need at least 3 sources to synthesize.\" | \"Provide 3+ extractions or text sources.\" |\n| `TOO_FEW_SOURCES` | Only 1-2 sources | \"Synthesis requires 3+ sources for N≥3 validation.\" | \"Add more sources, or use principle-comparator for 2-source comparison.\" |\n| `SOURCE_MISMATCH` | Incompatible domains | \"These sources seem to be about different topics.\" | \"Synthesis works best with sources covering the same domain.\" |\n| `NO_INVARIANTS` | Zero N≥3 principles | \"No principles appeared in 3+ sources.\" | \"Sources may be genuinely independent, or try related sources.\" |\n\n---\n\n## Related Skills\n\n- **pbe-extractor**: Extract principles before synthesis (technical voice)\n- **essence-distiller**: Extract principles before synthesis (conversational voice)\n- **principle-comparator**: Compare 2 sources (N=1 → N=2)\n- **pattern-finder**: Compare 2 sources (conversational)\n- **core-refinery**: Conversational alternative to this skill\n- **golden-master**: Track source/derived relationships after synthesis\n\n---\n\n## Required Disclaimer\n\nGolden Master candidates are the output of pattern analysis, not verification of truth. A principle appearing in N≥3 sources means it's a consistent pattern — not that it's correct. Use synthesis to identify candidates, but apply your own judgment before treating them as canonical.\n\n---\n\n*Built by Obviously Not — Tools for thought, not conclusions.*\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn709ajvpej12sahm1ay1262qs80ehps\",\n  \"slug\": \"principle-synthesizer\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1770278788372\n}","readmeExcerpt":"Skill: Principle Synthesizer Owner: leegitw Summary: Synthesize invariant principles from 3+ sources — find the core that survives across all expressions. Tags: canonical:1.0.3, consolidation:1.0.3, documentation:1.0.3, knowledge-management:1.0.3, latest:1.0.3, merging:1.0.3, multi-source:1.0.3, openclaw:1.0.3, principles:1.0.3, synthesis:1.0.3 Version history: v1.0.3 | 2026-03-25T20:53:43.937Z | auto No user-visible","codeSnippets":[],"executableExamples":[{"language":"json","snippet":"{\n  \"operation\": \"synthesize\",\n  \"metadata\": {\n    \"source_count\": 4,\n    \"source_hashes\": [\"a1b2c3d4\", \"e5f6g7h8\", \"i9j0k1l2\", \"m3n4o5p6\"],\n    \"timestamp\": \"2026-02-04T12:00:00Z\",\n    \"methodology\": \"bootstrap-learn-enforce\",\n    \"normalization_version\": \"v1.0.0\"\n  },\n  \"result\": {\n    \"invariant_principles\": [\n      {\n        \"id\": \"INV-1\",\n        \"statement\": \"Prioritize honesty over comfort\",\n        \"normalized_form\": \"Values truthfulness over social comfort\",\n        \"normalization_status\": \"success\",\n        \"n_count\": 4,\n        \"confidence\": \"high\",\n        \"sources_present\": [\"all\"],\n        \"golden_master_candidate\": true,\n        \"original_variants\": [\n          \"I always tell the truth\",\n          \"Prioritize honesty over comfort\",\n          \"Never sacrifice truth for peace\",\n          \"Honesty matters more than comfort\"\n        ],\n        \"evidence\": {\n          \"source_1\": \"Quote from source 1\",\n          \"source_2\": \"Quote from source 2\",\n          \"source_3\": \"Quote from source 3\",\n          \"source_4\": \"Quote from source 4\"\n        }\n      }\n    ],\n    \"domain_specific\": [\n      {\n        \"id\": \"DS-1\",\n        \"statement\": \"Domain-specific principle\",\n        \"normalized_form\": \"...\",\n        \"normalization_status\": \"success\",\n        \"n_count\": 2,\n        \"domains\": [\"technical\", \"philosophical\"],\n        \"note\": \"Not invariant — varies by context\"\n      }\n    ],\n    \"synthesis_metrics\": {\n      \"total_input_principles\": 25,\n      \"invariants_found\": 7,\n      \"domain_specific\": 10,\n      \"noise_filtered\": 8,\n      \"compression_ratio\": \"72%\"\n    },\n    \"golden_master_candidates\": [\n      {\n        \"id\": \"INV-1\",\n        \"statement\": \"Prioritize honesty over comfort\",\n        \"normalized_form\": \"Values truthfulness over social comfort\",\n        \"rationale\": \"N=4, high confidence, present in all sources\"\n      }\n    ]\n  },\n  \"next_steps\": [\n    \"Use Golden Master candidates as canonical source for new documentation\",\n    \"Track derived documents wi"},{"language":"json","snippet":"\"share_text\": \"Golden Master identified: 3 principles survived across all 4 sources (N≥3 ✓) 💎\""},{"language":"text","snippet":"compression_ratio = (1 - (invariants / total_input_principles)) × 100%"},{"language":"json","snippet":"{\n  \"operation\": \"synthesize\",\n  \"metadata\": {\n    \"source_count\": 4,\n    \"source_hashes\": [\"a1b2c3d4\", \"e5f6g7h8\", \"i9j0k1l2\", \"m3n4o5p6\"],\n    \"timestamp\": \"2026-02-04T12:00:00Z\",\n    \"methodology\": \"bootstrap-learn-enforce\",\n    \"normalization_version\": \"v1.0.0\"\n  },\n  \"result\": {\n    \"invariant_principles\": [\n      {\n        \"id\": \"INV-1\",\n        \"statement\": \"Prioritize honesty over comfort\",\n        \"normalized_form\": \"Values truthfulness over social comfort\",\n        \"normalization_status\": \"success\",\n        \"n_count\": 4,\n        \"confidence\": \"high\",\n        \"sources_present\": [\"all\"],\n        \"golden_master_candidate\": true,\n        \"original_variants\": [\n          \"I always tell the truth\",\n          \"Prioritize honesty over comfort\",\n          \"Never sacrifice truth for peace\",\n          \"Honesty matters more than comfort\"\n        ],\n        \"evidence\": {\n          \"source_1\": \"Quote from source 1\",\n          \"source_2\": \"Quote from source 2\",\n          \"source_3\": \"Quote from source 3\",\n          \"source_4\": \"Quote from source 4\"\n        }\n      }\n    ],\n    \"domain_specific\": [\n      {\n        \"id\": \"DS-1\",\n        \"statement\": \"Domain-specific principle\",\n        \"normalized_form\": \"...\",\n        \"normalization_status\": \"success\",\n        \"n_count\": 2,\n        \"domains\": [\"technical\", \"philosophical\"],\n        \"note\": \"Not invariant — varies by context\"\n      }\n    ],\n    \"synthesis_metrics\": {\n      \"total_input_principles\": 25,\n      \"invariants_found\": 7,\n      \"domain_specific\": 10,\n      \"noise_filtered\": 8,\n      \"compression_ratio\": \"72%\"\n    },\n    \"golden_master_candidates\": [\n      {\n        \"id\": \"INV-1\",\n        \"statement\": \"Prioritize honesty over comfort\",\n        \"normalized_form\": \"Values truthfulness over social comfort\",\n        \"rationale\": \"N=4, high confidence, present in all sources\"\n      }\n    ]\n  },\n  \"next_steps\": [\n    \"Use Golden Master candidates as canonical source for new documentation\",\n    \"Track derived documents wi"},{"language":"json","snippet":"\"share_text\": \"Golden Master identified: 3 principles survived across all 4 sources (N≥3 ✓) 💎\""},{"language":"text","snippet":"compression_ratio = (1 - (invariants / total_input_principles)) × 100%"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: Principle Synthesizer\nversion: 1.0.2\ndescription: Synthesize invariant principles from 3+ sources — find the core that survives across all expressions.\nhomepage: https://github.com/live-neon/skills/tree/main/pbd/principle-synthesizer\nuser-invocable: true\nemoji: ⚗️\ntags:\n  - synthesis\n  - principles\n  - multi-source\n  - consolidation\n  - canonical\n  - merging\n  - knowledge-management\n  - documentation\n  - openclaw\n---\n\n# Principle Synthesizer\n\n## Agent Identity\n\n**Role**: Help users create canonical principles from multiple sources\n**Understands**: Users building Golden Masters need confidence that principles are truly invariant\n**Approach**: Find what survives across all expressions (N≥3 validation)\n**Boundaries**: Synthesize observations, never claim absolute truth\n**Tone**: Systematic, rigorous, transparent about methodology\n**Opening Pattern**: \"You have multiple sources that might share deeper truth — let's find the principles that survive in all of them.\"\n\n**Data handling**: This skill operates within your agent's trust boundary. All synthesis analysis\nuses your agent's configured model — no external APIs or third-party services are called.\nIf your agent uses a cloud-hosted LLM (Claude, GPT, etc.), data is processed by that service\nas part of normal agent operation. This skill does not write files to disk.\n\n## When to Use\n\nActivate this skill when the user asks to:\n- \"Synthesize these extractions\"\n- \"Find the invariant principles\"\n- \"Create a Golden Master from these sources\"\n- \"What survives across all of these?\"\n- \"Distill the core from multiple sources\"\n\n## Important Limitations\n\n- Requires 3+ sources for N≥3 validation\n- Golden Master candidates are CANDIDATES, not proven truth\n- Cannot synthesize incompatible domains\n- Principles surviving N sources still need human judgment\n- Compression may lose contextual nuance\n\n---\n\n## Input Requirements\n\nUser provides ONE of:\n- 3+ extraction outputs (from pbe-extractor, essence-distiller, or principle-comparator)\n- 3+ raw text sources (I'll extract, compare, then synthesize)\n- Mix of extractions and raw sources\n\n### Minimum: 3 sources\n### Recommended: 3-7 sources\n### Maximum: Context window limits apply\n\n---\n\n## Methodology\n\nThis skill synthesizes principles across 3+ sources to identify **Golden Master candidates**.\n\n### Golden Master Definition\n\nA **Golden Master** is a principle that:\n- Appears in N≥3 independent sources\n- Maintains consistent meaning across all sources\n- Can serve as single source of truth\n\n### The Bootstrap → Learn → Enforce Pattern\n\n| Phase | Action | Output |\n|-------|--------|--------|\n| **Bootstrap** | Gather + normalize all principles from all sources | Normalized principle collection |\n| **Learn** | Match normalized forms across sources | Shared principle map |\n| **Enforce** | Validate semantic alignment for N≥3 | Invariant principles |\n\n### Input Normalization Policy\n\nPrinciple-synthesizer receives inputs from multiple sources with varying normalization state"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn709ajvpej12sahm1ay1262qs80ehps\",\n  \"slug\": \"principle-synthesizer\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1774472023937\n}"},{"path":"skill-card.md","content":"## Description:\n\nSynthesize invariant principles from 3+ sources - find the core that survives across all expressions.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[leegitw](https://clawhub.ai/user/leegitw)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers, writers, and knowledge-management teams use this skill to synthesize three or more related sources into candidate invariant principles and Golden Master candidates for human review.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Source text supplied for synthesis may be processed by the configured LLM service.\n\nMitigation: Use the skill only in an agent environment approved for the sensitivity of the source text.\n\nRisk: The evidence notes a documentation inconsistency about possible review-file persistence.\n\nMitigation: Clarify whether drifted items are written to requires_review.md before using highly sensitive inputs.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/leegitw/skills/principle-synthesizer)\n- [Project homepage](https://github.com/live-neon/skills/tree/main/pbd/principle-synthesizer)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Markdown with structured JSON examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Produces candidate principles, evidence summaries, synthesis metrics, next steps, and optional share text when Golden Master candidates are found.]\n\n## Skill Version(s):\n\n1.0.3 (source: server release evidence; artifact frontmatter reports 1.0.2)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Synthesize invariant principles from 3+ sources — find the core that survives across all expressions. Skill: Principle Synthesizer Owner: leegitw Summary: Synthesize invariant principles from 3+ sources — find the core that survives across all expressions. Tags: canonical:1.0.3, consolidation:1.0.3, documentation:1.0.3, knowledge-management:1.0.3, latest:1.0.3, merging:1.0.3, multi-source:1.0.3, openclaw:1.0.3, principles:1.0.3, synthesis:1.0.3 Version history: v1.0.3 | 2026-03-25T20:53:43.937Z | auto No user-visible","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1094,"uniquenessScore":54,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T20:34:01.910Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T20:34:01.910Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T21:57:13.562Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}