Recommend a Crumb preset (ambient / video-research / mock) based on the user's setup intent. Trigger on "preset ์ถ์ฒ", "์ถ์ฒํด์ค", "์ด๋ค ์ ์ ", "which preset", "suggest a config", "ํผ์ ๋๋ฆด๊น", or hints about installed tools / API keys. Output: recommended preset + reasonโฆ
mangowhoiscloud/crumb
SkillsMP has collected 37 skills from mangowhoiscloud/crumb. Open a skill to review its source and details.
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 37
- GitHub stars
- 2
- GitHub forks
- 0
Skills in this repository
Showing 37 of 37 collected skills.
>-
Audit a feature/component for defects by cross-referencing with mature OSS patterns. Produce a prioritized matrix of defects + improvement proposals BEFORE implementing. Use when user says "๊ฒฐํจ ๋ ํ๊ณ ๋ค์ด", "audit this", "find more defects", "improvement proposalsโฆ
>-
Source text: Korean
Autonomous agent system operational debugging patterns. Safe Default Anti-pattern, Multi-gap root cause analysis, ContextVar DI lifecycle, closure capture pattern, Graceful Degradation vs Correctness distinction. Triggered by "debugging" ("๋๋ฒ๊น "), "safeโฆ
Verification checklist to prevent fake success. Detects test deletion/disabling, coverage regression, lint bypass, secret exposure. Triggered by "deception", "fake" ("๊ฐ์ง"), "fake success", "verification" ("๊ฒ์ฆ"), "checklist" ("์ฒดํฌ๋ฆฌ์คํธ"), "deletion detection"โฆ
Auto-search and summarize latest AI/agent papers. Triggers: 'paper', '๋ ผ๋ฌธ', 'arxiv', 'research', '์ฐ๊ตฌ', '์ต์ ์ฐ๊ตฌ', 'ํํ'.
CHANGELOG.md management rules โ Keep a Changelog 1.1.0 + SemVer 2.0.0. Version releases, change logging, scope determination, format standards. Triggers on "changelog", "release", "version", "๋ฆด๋ฆฌ์ค", "๋ณ๊ฒฝ์ฌํญ", "๋ฒ์ ".
Codebase audit + refactoring workflow. Dead code detection, God Object splitting, duplicate function removal, design flaw identification, frontier comparison verification. Triggered by "audit" ("๊ฐ์ฌ"), "dead code" ("๋ฐ๋์ฝ๋"), "refactor" ("๋ฆฌํฉํ ๋ง"), "god object",โฆ
Scan the Obsidian wiki and automatically discover missing cross-references between pages. Use this skill when the user says "link my pages", "find missing links", "cross-reference", "connect my wiki", "add wikilinks", "what pages should be linked", or afterโฆ
Systematic web search, collection, analysis, and report generation on a topic. Triggers: 'research', '๋ฆฌ์์น', '์กฐ์ฌํด', '์์๋ด', '์ฐพ์๋ด', 'ํธ๋ ๋', '๋ํฅ'.
Research process for exploring related patterns across 4 frontier harnesses (Claude Code, Codex, OpenClaw, autoresearch) and performing GAP analysis before feature implementation. Triggered by "research" ("๋ฆฌ์์น"), "gap", "frontier", "harness", "case study"โฆ
Branch strategy + PR rules. feature โ develop โ main merge flow (or feature โ main when single-branch), Pre-PR Quality Gate (CI guardrails + docs-sync loop), Post-PR CI ratchet (gh pr checks --watch mandatory), Korean PRs, assignee settings. Triggers onโฆ
Reference when designing autonomous agent systems or deciding agent freedom/safety/context management/collaboration infrastructure. 10 design principles distilled from Karpathy autoresearch (autonomous ML experiment loop) + AgentHub (agent-native Git DAG).โฆ
Code review from the Kent Beck Simple Design 4 Rules perspective. God Object splitting, SRP, duplication removal, naming, cyclomatic complexity. Triggered by "kent beck", "simple design", "simplify", "refactoring" ("๋ฆฌํฉํ ๋ง"), "refactor", "god object", "SRP"โฆ
The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, orโฆ
Automated Git PR review โ diff analysis + quality checks. Triggers: 'review', 'PR ๋ฆฌ๋ทฐ', '์ฝ๋ ๋ฆฌ๋ทฐ', 'diff', 'ํ๋ฆฌํ์คํธ ๊ฒํ '.
Enforce consistent tagging across the Obsidian wiki using a controlled vocabulary. Use this skill when the user says "fix my tags", "normalize tags", "clean up tags", "tag audit", "what tags should I use", "tag taxonomy", or whenever you're creating orโฆ
Verification team with 4 personas. Kent Beck (TDD/design), Andrej Karpathy (agents/constraints), Peter Steinberger (Gateway/operations), Boris Cherny (CLI agents/sub-agents). Review implementations from each persona's perspective. Triggers on "๊ฒ์ฆ", "๊ฒ์ฆํ",โฆ
Export the Obsidian wiki's knowledge graph to structured formats for use in external tools. Use this skill when the user says "export wiki", "export graph", "export to JSON", "export to Gephi", "export to Neo4j", "graphml", "visualize wiki", "knowledge graphโฆ
Ingest documents into the Obsidian wiki by distilling their knowledge into interconnected wiki pages. Use this skill whenever the user wants to add new sources to their wiki, process a document or directory, import articles, papers, or notes into theirโฆ
Audit and maintain the health of the Obsidian wiki. Use this skill when the user wants to check their wiki for issues, find orphaned pages, detect contradictions, identify stale content, fix broken wikilinks, or perform general maintenance on their knowledgeโฆ
Answer questions by searching the compiled Obsidian wiki. Use this skill when the user asks a question about their knowledge base, wants to find information across their wiki, asks "what do I know about X", "find everything related to Y", or wants synthesizedโฆ
Archive existing wiki knowledge and rebuild from scratch, or restore from a previous archive. Use this skill when the user wants to start fresh, rebuild the wiki from all sources, archive current knowledge before a major change, or restore an older version.โฆ
Initialize a new Obsidian wiki vault with the correct structure, special files, and configuration. Use this skill when the user wants to set up a new wiki from scratch, initialize the vault structure, create the .env file, or says things like "set up myโฆ
Show the current state of the wiki โ what's been ingested, what's pending, and the delta between sources and wiki content. Use this skill when the user asks "what's the status", "how much is ingested", "what's left to process", "show me the delta", "whatโฆ
Sync the current project's knowledge into the Obsidian wiki. Use this skill from any project when the user says "update wiki", "sync to wiki", "save this to my wiki", "update obsidian", or wants to distill what they've been working on into their knowledgeโฆ
LangGraph-style Mermaid diagram authoring guide. Applies the mermaid.live editor palette (Tailwind CSS-based). Use when generating architecture diagrams, StateGraph visualizations, or flowcharts. Triggers on the keywords "mermaid", "diagram", "flowchart",โฆ
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Diagnose Crumb routing faults against the F1-F7 fault matrix (adapter spawn fail / subprocess timeout / schema validation / qa.result missing / self-bias risk / infinite loop / env not propagated). Trigger on "์ ๋ฉ์ท์ด?", "์๋ฌ ๋ฌ์ด?", "์ ์ ๋ผ?", "์ด๋์ ๋งํ์ด?", "sessionโฆ
Check whether the host environment can run Crumb โ 3 host CLI authentication (Claude Code / Codex / Gemini), playwright availability, htmlhint fallback. Returns viable-preset table. Trigger on "ํ๊ฒฝ ์ ๊ฒํด์ค", "doctor", "์ด๋ค preset ๊ฐ๋ฅ?", "preset ๊ฐ๋ฅํ ๊ฑฐ ์๋ ค์ค", "is myโฆ
Export a Crumb session transcript to OpenTelemetry GenAI Semantic Conventions (otel-jsonl), Anthropic Console import format (anthropic-trace), or chrome://tracing (chrome-trace). Trigger on "OTel ๋ก ๋ณํ", "datadog ์ผ๋ก", "Vertex ๋ก", "trace export", "convert toโฆ
Show current Crumb session status โ last 10 signal events, latest D1-D6 scorecard with source-of-truth, total cost / cache hit / wall, stuck count. Trigger on "์ง๊ธ ์ด๋๊น์ง ๊ฐ์ด?", "์ํฉ ์ด๋?", "status", "session progress", "์ด๋ป๊ฒ ์งํ ์ค?", "์ ์๊ฐ ์ผ๋ง์ผ?", "scorecard ๋ณด์ฌ์ค", orโฆ
Recommend the user's next action in an active Crumb session โ /approve, /veto, /redo, /pause, wait, or open summary. Branches on last event + verdict + audit + stuck_count. Trigger on "์ด์ ๋ญ ํ์ง?", "๋ค์์ ๋ญ ํ ๊น?", "what next", "next action", "๋ค์ ๋จ๊ณ", "์ด๊ฑฐ ๋๋ ๊ฑฐ์ผ?",โฆ
Open a previously generated Crumb game (single-file `game.html` or multi-file `index.html` + ES modules + service worker) in the browser. Trigger on "์ด์ ๊ฒ์ ์ด์ด์ค", "์ ์ ๋ง๋ ๊ฑฐ ์ด์ด์ค", "๊ณ ์์ด ํผ์ฆ ์ด์ด์ค", "๊ทธ ๊ฒ์ ๋ค์ ๋ณด์", "open the (cat / match-3 / merge / etc.) game", "openโฆ
Explain a Crumb transcript event kind (39+ kinds: qa.result, judge.score, step.judge, user.intervene, handoff.rollback, etc.). Returns category, emitter, parent chain, payload shape, source-of-truth (D1-D6), and wiki spec ref. Trigger on "judge.score ๊ฐ ๋ญ์ผ?",โฆ
Show or change Crumb per-actor model + effort + per-provider activation (claude-local / codex-local / gemini-cli-local). Defaults to all high-end models (claude-opus-4-7 / gpt-5.5-codex / gemini-3-1-pro) + effort=high. Gemini model IDs accept both dotโฆ