القائمة
Domain-agnostic knowledge acquisition — from zero to structured expertise through conversational learning
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Run the 7-step Artificial Critical Thinking pass — Materiality → Hypothesise → Alternatives → Disconfirmers → Audit priors → Severity → Commit-with-marker
Challenge what you think is right — alternative hypotheses, missing data, evidence quality, bias detection, falsifiability, and adversarial review
Step-back protocol — restate, generalise, specialise, invert, ask why, pre-mortem, check stakeholders, and audit framings before solving
Build knowledge bases that build software — research before code, teach before execute
Two-phase brain upgrade — mechanical install via shared core, then LLM-led semantic reconciliation
Clear documentation through visual excellence
| name | bootstrap-learning |
| description | Domain-agnostic knowledge acquisition — from zero to structured expertise through conversational learning |
| tier | standard |
| applyTo | **/*learn*,**/*bootstrap*,**/*knowledge*,**/*domain* |
| currency | "2026-04-22T00:00:00.000Z" |
Turn any unfamiliar domain into structured, connected knowledge through progressive conversation.
Learning a new domain is hard because you don't know what you don't know. This skill provides a systematic approach to go from zero knowledge to a well-structured skill file.
Goal: Understand the domain's shape before diving in.
| Technique | Example Question | What You Learn |
|---|---|---|
| Boundary mapping | "What does X include and exclude?" | Scope |
| Vocabulary scan | "What are the 5 key terms?" | Entry points |
| Expert identification | "Who are the authorities?" | Trust sources |
| Adjacent domains | "What's related but different?" | Context |
Exit criteria: Can describe the domain in one sentence. Can list 5-10 key terms.
Goal: Understand the 3-5 ideas everything else builds on.
Exit criteria: Can explain core concepts without jargon. Can answer "why does this exist?"
Goal: Move from "I understand the concept" to "I can apply it."
| Elaboration Type | Purpose | Example |
|---|---|---|
| Happy path | How it works normally | "Walk me through a typical OAuth flow" |
| Edge cases | Where it breaks | "What happens when the token expires mid-request?" |
| Anti-patterns | Common mistakes | "What do beginners always get wrong?" |
| Trade-offs | Decision framework | "When would you NOT use event sourcing?" |
Exit criteria: Can identify when to use and when NOT to use the thing.
Goal: Integrate new knowledge with what you already know.
Exit criteria: At least 2 connections to existing skills identified.
Goal: Store the learning in the right format and location.
| What You Learned | Store As | Location |
|---|---|---|
| Domain reference knowledge | SKILL.md | skills/[domain]/ |
| Step-by-step procedure | .instructions.md | instructions/ |
| Interactive workflow | .prompt.md | prompts/ |
| Cross-project pattern | GK-* | Global knowledge |
| One-off insight | GI-* | Global insights |
Exit criteria: At least one memory file created. Connections linked.
| Signal | Type of Gap | Action |
|---|---|---|
| "I don't know the right question to ask" | Vocabulary gap | Return to Phase 1 |
| "I understand the words but not the concept" | Foundation gap | Return to Phase 2 |
| "I understand it but can't apply it" | Elaboration gap | Return to Phase 3 |
| "I know this but it feels isolated" | Connection gap | Phase 4 |
| "I keep re-learning this" | Consolidation gap | Phase 5 |
If you can't explain it simply, you don't understand it well enough.
After learning a concept, try to explain it in one paragraph using no jargon. If you can't, identify which part is unclear and loop back.
A good bootstrap learning output (SKILL.md) should:
