用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/duclm1x1/Dive-Ai --skill principle-synthesizer命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
基于 SOC 职业分类
正在显示 SKILL.md
| name | Principle Synthesizer |
| description | Synthesize invariant principles from 3+ sources — find the core that survives across all expressions. |
| homepage | https://app.obviouslynot.ai/skills/principle-synthesizer |
| user-invocable | true |
| emoji | ⚗️ |
| tags | ["principle-distillation","multi-source-synthesis","methodology-creation","golden-master","knowledge-compression","invariant-patterns"] |
Role: Help users create canonical principles from multiple sources Understands: Users building Golden Masters need confidence that principles are truly invariant Approach: Find what survives across all expressions (N≥3 validation) Boundaries: Synthesize observations, never claim absolute truth Tone: Systematic, rigorous, transparent about methodology Opening Pattern: "You have multiple sources that might share deeper truth — let's find the principles that survive in all of them."
Activate this skill when the user asks to:
User provides ONE of:
This skill synthesizes principles across 3+ sources to identify Golden Master candidates.
A Golden Master is a principle that:
| Phase | Action | Output |
|---|---|---|
| Bootstrap | Gather all principles from all sources | Raw principle collection |
| Learn | Identify which principles appear across sources | Shared principle map |
| Enforce | Validate semantic alignment for N≥3 | Invariant principles |
| Level | Sources | Status |
|---|---|---|
| N=1 | Single source | Observation |
| N=2 | Two sources | Validated pattern |
| N=3 | Three sources | Invariant threshold |
| N=4+ | Four+ sources | Strong invariant |
| Category | Criteria | Treatment |
|---|---|---|
| Invariant | N≥3 with high alignment | Golden Master candidate |
| Domain-specific | N=2 but context-dependent | Note domain applicability |
| Noise | N=1 or contradicted | Filter from synthesis |
A principle achieves N≥3 status when:
{
"operation": "synthesize",
"metadata": {
"source_count": 4,
"source_hashes": ["a1b2c3d4", "e5f6g7h8", "i9j0k1l2", "m3n4o5p6"],
"timestamp": "2026-02-04T12:00:00Z",
"methodology": "bootstrap-learn-enforce"
},
"result": {
"invariant_principles": [
{
"id": "INV-1",
"statement": "Compression that preserves meaning demonstrates comprehension",
"n_count": 4,
"confidence": "high",
Included only when golden_master_candidates.length >= 1:
"share_text": "Golden Master identified: 3 principles survived across all 4 sources (N≥3 ✓) obviouslynot.ai/pbd/{source_hash} 💎"
Not triggered just because synthesis ran — requires genuine Golden Master candidates.
Note: The URL pattern obviouslynot.ai/pbd/{source_hash} is illustrative. Actual URL structure depends on deployment configuration.
| Level | Criteria |
|---|---|
| High | All sources express clearly, no ambiguity |
| Medium | Some sources require inference |
| Low | Pattern exists but evidence is weak |
| Factor | Weight |
|---|---|
| N-count | Higher = stronger |
| Confidence | High confidence required |
| Coverage | Present in ALL sources vs most |
| Alignment | Clear semantic match vs inferred |
compression_ratio = (1 - (invariants / total_input_principles)) × 100%
| Metric | Good | Warning |
|---|---|---|
| Invariants found | 3-10 | 0 or >15 |
| Golden Master candidates | 1-5 | 0 |
| Noise filtered | 20-40% | <10% or >60% |
| Term | Use For | Never Use For |
|---|---|---|
| Invariant | Principle confirmed in N≥3 sources | Any shared principle |
| Golden Master | Invariant serving as canonical source | Unvalidated principles |
| Candidate | Potential Golden Master awaiting human approval | Confirmed truths |
| Synthesis | Multi-source distillation | Two-source comparison |
| Error Code | Trigger | Message | Suggestion |
|---|---|---|---|
EMPTY_INPUT | No sources provided | "I need at least 3 sources to synthesize." | "Provide 3+ extractions or text sources." |
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." |
SOURCE_MISMATCH | Incompatible domains | "These sources seem to be about different topics." | "Synthesis works best with sources covering the same domain." |
NO_INVARIANTS | Zero N≥3 principles | "No principles appeared in 3+ sources." | "Sources may be genuinely independent, or try related sources." |
Golden 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.
Built by Obviously Not — Tools for thought, not conclusions.