[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73A8YAGJKZAMK2M2TKT2M0D":3,"skill-same:01M73A8YAGJKZAMK2M2TKT2M0D":59},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":6,"updatedAt":44,"install":45,"resources":58},"01M73A8YAGJKZAMK2M2TKT2M0D","manage-memory",null,"Organize, extract, prune, and verify Claude Code persistent memory files. Covers MEMORY.md as a concise index, topic extraction to dedicated files, staleness detection, accuracy verification against project state, and the 200-line truncation constraint. Use when MEMORY.md is approaching the 200-line limit, after a session produces durable insights worth preserving, when a topic section has grown beyond 10-15 lines and should be extracted, or when project state has changed and memory entries may be stale.","roohe\u002Fagentic-super-skills","roohe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99054084?v=4","01M734WCDFP6RZVT5CNM00QR26","01M734WCE4BD0T4NZS5PCV9V5F",10,"MIT","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fmanage-memory\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: manage-memory\nlocale: caveman-lite\nsource_locale: en\nsource_commit: 82c77053\ntranslator: \"Julius Brussee homage — caveman\"\ntranslation_date: \"2026-04-24\"\ndescription: >\n  Organize, extract, prune, and verify Claude Code persistent memory files.\n  Covers MEMORY.md as a concise index, topic extraction to dedicated files,\n  staleness detection, accuracy verification against project state, and\n  the 200-line truncation constraint. Use when MEMORY.md is approaching the\n  200-line limit, after a session produces durable insights worth preserving,\n  when a topic section has grown beyond 10-15 lines and should be extracted,\n  or when project state has changed and memory entries may be stale.\nlicense: MIT\nallowed-tools: Read Write Edit Bash Grep Glob\nmetadata:\n  author: Philipp Thoss\n  version: \"1.0\"\n  domain: general\n  complexity: intermediate\n  language: multi\n  tags: memory, claude-code, organization, maintenance, auto-memory\n---\n\n# Manage Memory\n\nMaintain Claude Code's persistent memory directory so it stays accurate, concise, and useful across sessions. MEMORY.md is loaded into the system prompt on every conversation — lines after 200 are truncated, so this file must be a lean index pointing to topic files for detail.\n\n## When to Use\n\n- MEMORY.md is approaching the 200-line truncation threshold\n- A session produced durable insights worth preserving (new patterns, architecture decisions, debugging solutions)\n- A topic section in MEMORY.md has grown beyond 10-15 lines and should be extracted\n- Project state has changed (renamed files, new domains, updated counts) and memory entries may be stale\n- Starting a new area of work and checking whether relevant memory already exists\n- Periodic maintenance between sessions to keep the memory directory healthy\n\n## Inputs\n\n- **Required**: Access to the memory directory (typically `~\u002F.claude\u002Fprojects\u002F\u003Cproject-path>\u002Fmemory\u002F`)\n- **Optional**: Specific trigger (e.g., \"MEMORY.md is too long,\" \"just finished a major refactor\")\n- **Optional**: Topic to add, update, or extract\n\n## Procedure\n\n### Step 1: Assess Current State\n\nRead MEMORY.md and list all files in the memory directory:\n\n```bash\nwc -l \u003Cmemory-dir>\u002FMEMORY.md\nls -la \u003Cmemory-dir>\u002F\n```\n\nCheck the line count against the 200-line limit. Inventory existing topic files.\n\n**Got:** Clear picture of total lines, number of topic files, and which sections exist in MEMORY.md.\n\n**If fail:** If the memory directory doesn't exist, create it. If MEMORY.md doesn't exist, create a minimal one with a `# Project Memory` header and a `## Topic Files` section.\n\n### Step 2: Identify Stale Entries\n\nCompare memory claims against current project state. Common staleness patterns:\n\n1. **Count drift**: File counts, skill counts, domain counts that changed after additions\u002Fremovals\n2. **Renamed paths**: Files or directories that were moved or renamed\n3. **Superseded patterns**: Workarounds that are no longer needed after fixes\n4. **Contradictions**: Two entries that say different things about the same topic\n\nUse Grep to spot-check key claims:\n\n```bash\n# Example: verify a skill count claim\ngrep -c \"^      - id:\" skills\u002F_registry.yml\n# Example: verify a file still exists\nls path\u002Fclaimed\u002Fin\u002Fmemory.md\n```\n\n**Got:** A list of entries that are stale, with the correct current values.\n\n**If fail:** If you can't verify a claim (e.g., it references external state you can't check), leave it but add a `(unverified)` note rather than silently preserving potentially wrong information.\n\n### Step 3: Decide What to Add\n\nFor new entries, apply these filters before writing:\n\n1. **Durability**: Will this be true next session? Avoid session-specific context (current task, in-progress work, temporary state).\n2. **Non-duplication**: Does CLAUDE.md or project documentation already cover this? Don't duplicate — memory is for things NOT captured elsewhere.\n3. **Verified**: Has this been confirmed across multiple interactions, or is it a single observation? For single observations, verify against project docs before writing.\n4. **Actionable**: Does knowing this change behavior? \"The sky is blue\" isn't useful. \"Exit code 5 means quoting error — use temp files\" changes how you work.\n\nException: If the user explicitly asks to remember something, save it immediately — no need to wait for multiple confirmations.\n\n**Got:** A filtered list of entries worth adding, each meeting durability + non-duplication + verification + actionability criteria.\n\n**If fail:** If unsure whether an entry is worth keeping, err toward keeping it briefly in MEMORY.md — it's easier to prune later than to rediscover.\n\n### Step 4: Extract Oversize Topics\n\nWhen a section in MEMORY.md exceeds ~10-15 lines, extract it to a dedicated topic file:\n\n1. Create `\u003Cmemory-dir>\u002F\u003Ctopic-name>.md` with a descriptive header\n2. Move the detailed content from MEMORY.md to the topic file\n3. Replace the section in MEMORY.md with a 1-2 line summary and a link:\n\n```markdown\n## Topic Files\n- [topic-name.md](topic-name.md) — Brief description of contents\n```\n\nNaming conventions for topic files:\n- Use lowercase kebab-case: `viz-architecture.md`, not `VizArchitecture.md`\n- Name by topic, not chronology: `patterns.md`, not `session-2024-12.md`\n- Group related items: combine \"R debugging\" and \"WSL quirks\" into `patterns.md` rather than creating one file per fact\n\n**Got:** MEMORY.md stays under 200 lines. Each topic file is self-contained and readable without MEMORY.md context.\n\n**If fail:** If a topic file would be fewer than 5 lines, it's probably not worth extracting — leave it inline in MEMORY.md.\n\n### Step 5: Update MEMORY.md\n\nApply all changes: remove stale entries, add new entries, update counts, and ensure the Topic Files section lists all dedicated files.\n\nMEMORY.md structure should follow this pattern:\n\n```markdown\n# Project Memory\n\n## Section 1 — High-level context\n- Bullet points, concise\n\n## Section 2 — Another topic\n- Key facts only\n\n## Topic Files\n- [file.md](file.md) — What it covers\n```\n\nGuidelines:\n- Keep each bullet to 1-2 lines maximum\n- Use inline formatting (`code`, **bold**) for scanability\n- Put the most frequently needed context first\n- The Topic Files section should always be last\n\n**Got:** MEMORY.md is under 200 lines, accurate, and has working links to all topic files.\n\n**If fail:** If you can't get under 200 lines after extraction, identify the least-frequently-used section and extract it. Every section is a candidate — even the project structure overview can go to a topic file if needed, leaving a 1-line summary.\n\n### Step 6: Verify Integrity\n\nRun a final check:\n\n1. **Line count**: Confirm MEMORY.md is under 200 lines\n2. **Links**: Verify every topic file referenced in MEMORY.md exists\n3. **Orphans**: Check for topic files not referenced in MEMORY.md\n4. **Accuracy**: Spot-check 2-3 factual claims against project state\n\n```bash\nwc -l \u003Cmemory-dir>\u002FMEMORY.md\n# Check for broken links\nfor f in $(grep -oP '\\[.*?\\]\\(\\K[^)]+' \u003Cmemory-dir>\u002FMEMORY.md); do\n  ls \u003Cmemory-dir>\u002F$f 2>\u002Fdev\u002Fnull || echo \"BROKEN: $f\"\ndone\n# Check for orphan files\nls \u003Cmemory-dir>\u002F*.md | grep -v MEMORY.md\n```\n\n**Got:** Line count under 200, no broken links, no orphan files, spot-checked claims are accurate.\n\n**If fail:** Fix broken links (update or remove). For orphan files, either add a reference in MEMORY.md or delete them if they're no longer relevant.\n\n## Validation\n\n- [ ] MEMORY.md is under 200 lines\n- [ ] All topic files referenced in MEMORY.md exist on disk\n- [ ] No orphan `.md` files in memory directory (every file is linked from MEMORY.md)\n- [ ] No stale counts or renamed paths in any memory file\n- [ ] New entries meet the durability\u002Fnon-duplication\u002Fverified\u002Factionable criteria\n- [ ] Topic files have descriptive headers and are self-contained\n- [ ] MEMORY.md reads as a useful quick-reference, not a changelog\n\n## Pitfalls\n\n- **Memory file pollution**: Writing every session observation to memory. Most findings are session-specific and don't need persisting. Apply the four filters (Step 3) before writing.\n- **Stale counts**: Updating code but not memory. Counts (skills, agents, domains, files) drift silently. Always verify counts against the source of truth before trusting memory.\n- **Chronological organization**: Organizing by \"when I learned it\" instead of \"what it's about.\" Topic-based organization (`patterns.md`, `viz-architecture.md`) is far more useful for retrieval than date-based files.\n- **Duplicating CLAUDE.md**: CLAUDE.md is the authoritative project instruction file. Memory should capture things NOT in CLAUDE.md — debugging insights, architecture decisions, workflow preferences, cross-project patterns.\n- **Over-extraction**: Creating a topic file for every 3-line section. Only extract when a section exceeds ~10-15 lines. Small sections work fine inline.\n- **Forgetting the 200-line limit**: MEMORY.md is loaded into every system prompt. Lines after 200 are silently truncated. If the file grows past this, the bottom content is effectively invisible.\n\n## Related Skills\n\n- `write-claude-md` — CLAUDE.md captures project instructions; memory captures cross-session learning\n- `prune-agent-memory` — the inverse of manage-memory: auditing, classifying, and selectively forgetting stored memories\n- `write-continue-here` — write a structured continuation file for session handoff; complements memory as a short-term context bridge\n- `read-continue-here` — read and act on a continuation file at session start; the consumption side of the handoff\n- `create-skill` — new skills may produce memory-worthy patterns\n- `heal` — self-healing may update memory as part of integration step\n- `meditate` — meditation sessions may surface insights worth persisting\n","# Manage Memory\n\nMaintain Claude Code's persistent memory directory so it stays accurate, concise, and useful across sessions. MEMORY.md is loaded into the system prompt on every conversation — lines after 200 are truncated, so this file must be a lean index pointing to topic files for detail.\n\n## When to Use\n\n- MEMORY.md is approaching the 200-line truncation threshold\n- A session produced durable insights worth preserving (new patterns, architecture decisions, debugging solutions)\n- A topic section in MEMORY.md has grown beyond 10-15 lines and should be extracted\n- Project state has changed (renamed files, new domains, updated counts) and memory entries may be stale\n- Starting a new area of work and checking whether relevant memory already exists\n- Periodic maintenance between sessions to keep the memory directory healthy\n\n## Inputs\n\n- **Required**: Access to the memory directory (typically `~\u002F.claude\u002Fprojects\u002F\u003Cproject-path>\u002Fmemory\u002F`)\n- **Optional**: Specific trigger (e.g., \"MEMORY.md is too long,\" \"just finished a major refactor\")\n- **Optional**: Topic to add, update, or extract\n\n## Procedure\n\n### Step 1: Assess Current State\n\nRead MEMORY.md and list all files in the memory directory:\n\n```bash\nwc -l \u003Cmemory-dir>\u002FMEMORY.md\nls -la \u003Cmemory-dir>\u002F\n```\n\nCheck the line count against the 200-line limit. Inventory existing topic files.\n\n**Got:** Clear picture of total lines, number of topic files, and which sections exist in MEMORY.md.\n\n**If fail:** If the memory directory doesn't exist, create it. If MEMORY.md doesn't exist, create a minimal one with a `# Project Memory` header and a `## Topic Files` section.\n\n### Step 2: Identify Stale Entries\n\nCompare memory claims against current project state. Common staleness patterns:\n\n1. **Count drift**: File counts, skill counts, domain counts that changed after additions\u002Fremovals\n2. **Renamed paths**: Files or directories that were moved or renamed\n3. **Superseded patterns**: Workarounds that are no longer needed after fixes\n4. **Contradictions**: Two entries that say different things about the same topic\n\nUse Grep to spot-check key claims:\n\n```bash\n# Example: verify a skill count claim\ngrep -c \"^      - id:\" skills\u002F_registry.yml\n# Example: verify a file still exists\nls path\u002Fclaimed\u002Fin\u002Fmemory.md\n```\n\n**Got:** A list of entries that are stale, with the correct current values.\n\n**If fail:** If you can't verify a claim (e.g., it references external state you can't check), leave it but add a `(unverified)` note rather than silently preserving potentially wrong information.\n\n### Step 3: Decide What to Add\n\nFor new entries, apply these filters before writing:\n\n1. **Durability**: Will this be true next session? Avoid session-specific context (current task, in-progress work, temporary state).\n2. **Non-duplication**: Does CLAUDE.md or project documentation already cover this? Don't duplicate — memory is for things NOT captured elsewhere.\n3. **Verified**: Has this been confirmed across multiple interactions, or is it a single observation? For single observations, verify against project docs before writing.\n4. **Actionable**: Does knowing this change behavior? \"The sky is blue\" isn't useful. \"Exit code 5 means quoting error — use temp files\" changes how you work.\n\nException: If the user explicitly asks to remember something, save it immediately — no need to wait for multiple confirmations.\n\n**Got:** A filtered list of entries worth adding, each meeting durability + non-duplication + verification + actionability criteria.\n\n**If fail:** If unsure whether an entry is worth keeping, err toward keeping it briefly in MEMORY.md — it's easier to prune later than to rediscover.\n\n### Step 4: Extract Oversize Topics\n\nWhen a section in MEMORY.md exceeds ~10-15 lines, extract it to a dedicated topic file:\n\n1. Create `\u003Cmemory-dir>\u002F\u003Ctopic-name>.md` with a descriptive header\n2. Move the detailed content from MEMORY.md to the topic file\n3. Replace the section in MEMORY.md with a 1-2 line summary and a link:\n\n```markdown\n## Topic Files\n- [topic-name.md](topic-name.md) — Brief description of contents\n```\n\nNaming conventions for topic files:\n- Use lowercase kebab-case: `viz-architecture.md`, not `VizArchitecture.md`\n- Name by topic, not chronology: `patterns.md`, not `session-2024-12.md`\n- Group related items: combine \"R debugging\" and \"WSL quirks\" into `patterns.md` rather than creating one file per fact\n\n**Got:** MEMORY.md stays under 200 lines. Each topic file is self-contained and readable without MEMORY.md context.\n\n**If fail:** If a topic file would be fewer than 5 lines, it's probably not worth extracting — leave it inline in MEMORY.md.\n\n### Step 5: Update MEMORY.md\n\nApply all changes: remove stale entries, add new entries, update counts, and ensure the Topic Files section lists all dedicated files.\n\nMEMORY.md structure should follow this pattern:\n\n```markdown\n# Project Memory\n\n## Section 1 — High-level context\n- Bullet points, concise\n\n## Section 2 — Another topic\n- Key facts only\n\n## Topic Files\n- [file.md](file.md) — What it covers\n```\n\nGuidelines:\n- Keep each bullet to 1-2 lines maximum\n- Use inline formatting (`code`, **bold**) for scanability\n- Put the most frequently needed context first\n- The Topic Files section should always be last\n\n**Got:** MEMORY.md is under 200 lines, accurate, and has working links to all topic files.\n\n**If fail:** If you can't get under 200 lines after extraction, identify the least-frequently-used section and extract it. Every section is a candidate — even the project structure overview can go to a topic file if needed, leaving a 1-line summary.\n\n### Step 6: Verify Integrity\n\nRun a final check:\n\n1. **Line count**: Confirm MEMORY.md is under 200 lines\n2. **Links**: Verify every topic file referenced in MEMORY.md exists\n3. **Orphans**: Check for topic files not referenced in MEMORY.md\n4. **Accuracy**: Spot-check 2-3 factual claims against project state\n\n```bash\nwc -l \u003Cmemory-dir>\u002FMEMORY.md\n# Check for broken links\nfor f in $(grep -oP '\\[.*?\\]\\(\\K[^)]+' \u003Cmemory-dir>\u002FMEMORY.md); do\n  ls \u003Cmemory-dir>\u002F$f 2>\u002Fdev\u002Fnull || echo \"BROKEN: $f\"\ndone\n# Check for orphan files\nls \u003Cmemory-dir>\u002F*.md | grep -v MEMORY.md\n```\n\n**Got:** Line count under 200, no broken links, no orphan files, spot-checked claims are accurate.\n\n**If fail:** Fix broken links (update or remove). For orphan files, either add a reference in MEMORY.md or delete them if they're no longer relevant.\n\n## Validation\n\n- [ ] MEMORY.md is under 200 lines\n- [ ] All topic files referenced in MEMORY.md exist on disk\n- [ ] No orphan `.md` files in memory directory (every file is linked from MEMORY.md)\n- [ ] No stale counts or renamed paths in any memory file\n- [ ] New entries meet the durability\u002Fnon-duplication\u002Fverified\u002Factionable criteria\n- [ ] Topic files have descriptive headers and are self-contained\n- [ ] MEMORY.md reads as a useful quick-reference, not a changelog\n\n## Pitfalls\n\n- **Memory file pollution**: Writing every session observation to memory. Most findings are session-specific and don't need persisting. Apply the four filters (Step 3) before writing.\n- **Stale counts**: Updating code but not memory. Counts (skills, agents, domains, files) drift silently. Always verify counts against the source of truth before trusting memory.\n- **Chronological organization**: Organizing by \"when I learned it\" instead of \"what it's about.\" Topic-based organization (`patterns.md`, `viz-architecture.md`) is far more useful for retrieval than date-based files.\n- **Duplicating CLAUDE.md**: CLAUDE.md is the authoritative project instruction file. Memory should capture things NOT in CLAUDE.md — debugging insights, architecture decisions, workflow preferences, cross-project patterns.\n- **Over-extraction**: Creating a topic file for every 3-line section. Only extract when a section exceeds ~10-15 lines. Small sections work fine inline.\n- **Forgetting the 200-line limit**: MEMORY.md is loaded into every system prompt. Lines after 200 are silently truncated. If the file grows past this, the bottom content is effectively invisible.\n\n## Related Skills\n\n- `write-claude-md` — CLAUDE.md captures project instructions; memory captures cross-session learning\n- `prune-agent-memory` — the inverse of manage-memory: auditing, classifying, and selectively forgetting stored memories\n- `write-continue-here` — write a structured continuation file for session handoff; complements memory as a short-term context bridge\n- `read-continue-here` — read and act on a continuation file at session start; the consumption side of the handoff\n- `create-skill` — new skills may produce memory-worthy patterns\n- `heal` — self-healing may update memory as part of integration step\n- `meditate` — meditation sessions may surface insights worth persisting\n",{"name":5,"locale":23,"license":14,"metadata":24,"translator":31,"description":32,"allowed-tools":33,"source_commit":34,"source_locale":35,"translation_date":36},"caveman-lite",{"tags":25,"author":26,"domain":27,"version":28,"language":29,"complexity":30},"memory, claude-code, organization, maintenance, auto-memory","Philipp Thoss","general","1.0","multi","intermediate","Julius Brussee homage — caveman","Organize, extract, prune, and verify Claude Code persistent memory files. Covers MEMORY.md as a concise index, topic extraction to dedicated files, staleness detection, accuracy verification against project state, and the 200-line truncation constraint. Use when MEMORY.md is approaching the 200-line limit, after a session produces durable insights worth preserving, when a topic section has grown beyond 10-15 lines and should be extracted, or when project state has changed and memory entries may be stale.\n","Read Write Edit Bash Grep Glob","82c77053","en","2026-04-24","master","f483e54f3ad5f202a77d45f2e57f8d970b71195f","skills_library\u002Fmanage-memory",2,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills","https:\u002F\u002Fgithub.com\u002Froohe","yoou.link","2026-05-19 15:56:07",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add roohe\u002Fagentic-super-skills --skill manage-memory",{"tool":51,"command":52},"bunx","bunx skills add roohe\u002Fagentic-super-skills --skill manage-memory",{"tool":54,"command":55},"pnpm","pnpm dlx skills add roohe\u002Fagentic-super-skills --skill manage-memory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fmanage-memory\u002FSKILL.md",true,[],[60,67,74,81,88,95],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M73D865CZME2FCMKA4PQM348","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M73D7Z64J4ABWZJD7P44XBBF","youtube-downloader","Download and process YouTube content for research. Use when: downloading competitor videos for analysis; extracting audio for podcasts; getting transcripts for content repurposing; archiving webinars; research content curation","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyoutube-downloader\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M73D7K8778TGZV3GJFR3703D","yc-pitch-deck","Create a compelling startup pitch deck that follows the structure proven to raise billions from top investors. Master the YC and Sequoia formats that get founders funded. Use when: **Fundraising** to create investor pitch decks; **YC application** to structure your narrative; **Demo Day prep** to craft your 2-minute pitch; **Angel investors** to communicate your opportunity; **Partnership pitches** to structure compelling asks","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyc-pitch-deck\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M73D70KJSE0E8Z28YMNNRT04","x-twitter-scraper","Use when the user needs X (Twitter) data or confirmation-gated X actions through Xquik: tweet search, user lookup, follower extraction, media download, monitoring, webhooks, MCP, SDKs, posting, likes, DMs, and profile updates. Requires a Xquik API key. Never ask for X login material.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fx-twitter-scraper\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M73D6ED01GV077R7K4NZNFZJ","write-vignette","Create R package vignettes using R Markdown or Quarto. Covers vignette setup, YAML configuration, code chunk options, building and testing, and CRAN requirements for vignettes. Use when adding a Getting Started tutorial, documenting complex workflows spanning multiple functions, creating domain-specific guides, or when CRAN submission requires user-facing documentation beyond function help pages.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-vignette\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":18},"01M73D69YJR0BK3NFHE0CYG3EF","write-validation-documentation","Write IQ\u002FOQ\u002FPQ validation documentation for computerized systems in regulated environments. Covers protocols, reports, test scripts, deviation handling, and approval workflows. Use when validating R or other software for regulated use, preparing for a regulatory audit, documenting qualification of computing environments, or creating and updating validation protocols and reports for new or re-qualified systems.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-validation-documentation\u002FSKILL.md",[],[]]