[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73BFRZXS78JMK9GFP5XZ2EG":3,"skill-same:01M73BFRZXS78JMK9GFP5XZ2EG":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},"01M73BFRZXS78JMK9GFP5XZ2EG","read-continue-here",null,"Read a CONTINUE_HERE.md continuation file at session start and resume from where the prior session left off. Covers detecting the file, assessing freshness, parsing the structured handoff, confirming the resumption plan with the user, and cleaning up after consumption. Optionally configures a SessionStart hook and CLAUDE.md instruction for automatic pickup. Use at the start of a session when a continuation file exists, when bootstrapping after an interrupted session, or when setting up automatic continuation detection.","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\u002Fread-continue-here\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: read-continue-here\nlocale: caveman-lite\nsource_locale: en\nsource_commit: 82c77053\ntranslator: \"Julius Brussee homage — caveman\"\ntranslation_date: \"2026-04-26\"\ndescription: >\n  Read a CONTINUE_HERE.md continuation file at session start and resume\n  from where the prior session left off. Covers detecting the file, assessing\n  freshness, parsing the structured handoff, confirming the resumption plan\n  with the user, and cleaning up after consumption. Optionally configures a\n  SessionStart hook and CLAUDE.md instruction for automatic pickup. Use at the\n  start of a session when a continuation file exists, when bootstrapping after\n  an interrupted session, or when setting up automatic continuation detection.\nlicense: MIT\nallowed-tools: Read Write Bash Grep Glob\nmetadata:\n  author: Philipp Thoss\n  version: \"1.0\"\n  domain: general\n  complexity: basic\n  language: multi\n  tags: session, continuity, handoff, context, workflow, read\n---\n\n# Read Continue Here\n\nRead a structured continuation file and resume work from where the prior session left off.\n\n## When to Use\n\n- Starting a new session and CONTINUE_HERE.md exists in the project root\n- After a SessionStart hook injects continuation context\n- Bootstrapping identity and detecting prior session artifacts\n- Setting up automatic continuation detection for a project (one-time infrastructure)\n\n## Inputs\n\n- **Required**: A project directory (defaults to current working directory)\n- **Optional**: Whether to configure infrastructure (SessionStart hook + CLAUDE.md instruction)\n- **Optional**: Whether to delete the file after consumption (default: yes)\n\n## Procedure\n\n### Step 1: Detect and Read the Continuation File\n\nCheck for `CONTINUE_HERE.md` in the project root:\n\n```bash\nls -la CONTINUE_HERE.md 2>\u002Fdev\u002Fnull\n```\n\nIf absent, exit gracefully — there is nothing to continue from.\n\nIf present, read the file contents. Parse the 5 sections: Objective, Completed, In Progress, Next Steps, Context. Extract the timestamp and branch from the header line.\n\n**Got:** The file is read and its sections are parsed into a clear mental model of the prior session's state.\n\n**If fail:** If the file exists but is malformed (missing sections, empty), treat it as a partial signal — extract whatever is present and note what is missing to the user.\n\n### Step 2: Assess Freshness\n\nCompare the file's timestamp against the current time:\n\n```bash\n# File modification time\nstat -c '%Y' CONTINUE_HERE.md 2>\u002Fdev\u002Fnull || stat -f '%m' CONTINUE_HERE.md\n# Current time\ndate +%s\n```\n\nClassify freshness:\n- **Fresh** (\u003C 24 hours, same branch): safe to act on directly\n- **Stale** (> 24 hours or different branch): flag to user before proceeding\n- **Superseded** (new commits exist after the handoff timestamp): someone worked on the project since the handoff\n\nCheck branch alignment:\n\n```bash\ngit branch --show-current\ngit log --oneline --since=\"$(stat -c '%Y' CONTINUE_HERE.md | xargs -I{} date -d @{} --iso-8601=seconds)\" 2>\u002Fdev\u002Fnull\n```\n\n**Got:** A freshness assessment with classification (fresh, stale, or superseded) and supporting evidence.\n\n**If fail:** If not in a git repo, skip branch and commit checks. Rely on the timestamp in the file header alone.\n\n### Step 3: Summarize and Confirm Resumption\n\nPresent the continuation state to the user concisely:\n- \"Prior session objective: [Objective]\"\n- \"Completed: [summary]\"\n- \"In progress: [summary]\"\n- \"Proposed next action: [Next Steps item 1]\"\n\nIf freshness is \"stale\" or \"superseded\", present the evidence and ask whether to proceed with the handoff or start fresh.\n\nIf any Next Steps items are tagged `**[USER]**`, surface those explicitly — they require user decisions before work can proceed.\n\n**Got:** The user confirms the resumption plan, possibly with adjustments. The agent has a clear mandate for what to do next.\n\n**If fail:** If the user says \"start fresh\" or \"ignore that file\", acknowledge and proceed without the continuation context. Offer to delete the file to prevent future confusion.\n\n### Step 4: Act on the Handoff\n\nBegin working from Next Steps item 1 (or wherever the user directed):\n- Reference In Progress items to understand partial state\n- Use the Context section to avoid retrying failed approaches\n- Treat Completed items as done — do not re-verify unless the user asks\n\n**Got:** The agent is productively working on the right task, informed by the continuation file.\n\n**If fail:** If the Next Steps are ambiguous or the In Progress state is unclear, ask the user for clarification rather than guessing.\n\n### Step 5: Clean Up\n\nAfter the handoff is consumed and work is underway, delete CONTINUE_HERE.md:\n\n```bash\nrm CONTINUE_HERE.md\n```\n\nStale continuation files cause confusion in future sessions.\n\n**Got:** The file is removed. The project root is clean.\n\n**If fail:** If the user wants to keep the file (e.g., as a reference during the session), leave it but note that it should be deleted before session end to prevent the next session from re-consuming it.\n\n### Step 6: Configure SessionStart Hook (Optional)\n\nIf not already configured, set up automatic reading of CONTINUE_HERE.md on session start.\n\nCreate the hook script:\n\n```bash\nmkdir -p ~\u002F.claude\u002Fhooks\u002Fcontinue-here\n\ncat > ~\u002F.claude\u002Fhooks\u002Fcontinue-here\u002Fread-continuation.sh \u003C\u003C 'SCRIPT'\n#!\u002Fbin\u002Fbash\n# SessionStart hook: inject CONTINUE_HERE.md into session context\n# OS-aware: works on native Linux, WSL, macOS, and Windows (Git Bash\u002FMSYS)\nset -uo pipefail\n\n# --- Platform detection ---\ndetect_platform() {\n  case \"$(uname -s)\" in\n    Darwin) echo \"mac\" ;;\n    Linux)\n      if grep -qi microsoft \u002Fproc\u002Fversion 2>\u002Fdev\u002Fnull; then\n        echo \"wsl\"\n      else\n        echo \"linux\"\n      fi ;;\n    MINGW*|MSYS*|CYGWIN*) echo \"windows\" ;;\n    *) echo \"unknown\" ;;\n  esac\n}\nPLATFORM=${PLATFORM:-$(detect_platform)}\n\nCONTINUE_FILE=\"$PWD\u002FCONTINUE_HERE.md\"\n\nif [ ! -f \"$CONTINUE_FILE\" ]; then\n  exit 0\nfi\n\n# Strip CRLF (files on NTFS often have Windows line endings)\nCONTENT=$(sed 's\u002F\\r$\u002F\u002F' \"$CONTINUE_FILE\")\n\n# JSON-escape: prefer jq, fall back to portable awk\nif command -v jq >\u002Fdev\u002Fnull 2>&1; then\n  ESCAPED=$(printf '%s' \"$CONTENT\" | jq -Rsa .)\nelse\n  ESCAPED=$(printf '%s' \"$CONTENT\" | awk '\n    BEGIN { ORS=\"\"; print \"\\\"\" }\n    {\n      gsub(\u002F\\\\\u002F, \"\\\\\\\\\")\n      gsub(\u002F\"\u002F, \"\\\\\\\"\")\n      gsub(\u002F\\t\u002F, \"\\\\t\")\n      if (NR > 1) print \"\\\\n\"\n      print\n    }\n    END { print \"\\\"\" }\n  ')\nfi\n\ncat \u003C\u003C EOF\n{\"hookSpecificOutput\":{\"sessionStartContext\":{\"additionalContext\":$ESCAPED}}}\nEOF\nSCRIPT\n\nchmod +x ~\u002F.claude\u002Fhooks\u002Fcontinue-here\u002Fread-continuation.sh\n```\n\nAdd to `~\u002F.claude\u002Fsettings.json` in the SessionStart hooks array:\n\n```json\n{\n  \"type\": \"command\",\n  \"command\": \"~\u002F.claude\u002Fhooks\u002Fcontinue-here\u002Fread-continuation.sh\",\n  \"timeout\": 5\n}\n```\n\n**Got:** The hook script exists, is executable, and is registered in settings.json. On next session start, if CONTINUE_HERE.md exists, its content is injected into the session context.\n\n**If fail:** Check that settings.json is valid JSON after editing. Test the hook manually: `cd \u002Fyour\u002Fproject && ~\u002F.claude\u002Fhooks\u002Fcontinue-here\u002Fread-continuation.sh`. The script falls back to `awk` if `jq` is not installed, so `jq` is recommended but not required.\n\n### Step 7: Add CLAUDE.md Instruction (Optional)\n\nAdd a brief instruction to the project's CLAUDE.md so Claude understands the file's purpose:\n\n```markdown\n## Session Continuity\n\nIf `CONTINUE_HERE.md` exists in the project root, read it at session start. It contains a structured handoff from a prior session: objective, completed work, in-progress state, next steps, and context. Act on it — acknowledge the continuation, summarize prior state, and propose resuming from the Next Steps section. If the file is older than 24 hours, flag this to the user before proceeding. After the handoff is consumed, the file can be deleted.\n```\n\n**Got:** CLAUDE.md contains the instruction. Future sessions will read and act on CONTINUE_HERE.md even if the SessionStart hook is not configured.\n\n**If fail:** If CLAUDE.md does not exist, create it with just this section. If the file is too long, add the instruction near the top where it will not be truncated.\n\n## Validation\n\n- [ ] CONTINUE_HERE.md was detected (or absence was handled gracefully)\n- [ ] Freshness was assessed (timestamp, branch, post-handoff commits)\n- [ ] Resumption plan was presented to and confirmed by the user\n- [ ] Work began from the correct Next Steps item\n- [ ] The file was cleaned up after consumption\n- [ ] (Optional) SessionStart hook script exists and is executable\n- [ ] (Optional) CLAUDE.md contains the session continuity instruction\n\n## Pitfalls\n\n- **Acting without confirming**: Always present the resumption plan to the user. They may have changed their mind about what to work on, even if the file is fresh.\n- **Trusting stale files blindly**: A continuation file older than 24 hours or from a different branch is a suggestion, not a mandate. Always check freshness.\n- **Ignoring the Context section**: The most valuable part of the file is often the failed approaches. Skipping this section leads to retrying dead ends.\n- **Forgetting to clean up**: Leaving CONTINUE_HERE.md after consumption causes confusion in the next session, which will try to act on it again.\n- **Treating Completed items as unverified**: Unless the user specifically asks, do not re-do completed work. Trust the prior session's assessment.\n\n## Related Skills\n\n- `write-continue-here` — the complement: writing the continuation file at session end\n- `bootstrap-agent-identity` — full identity reconstruction that includes continuation detection as one heuristic\n- `manage-memory` — durable cross-session knowledge (complements this ephemeral handoff)\n- `write-claude-md` — project instructions where the optional continuity guidance lives\n","# Read Continue Here\n\nRead a structured continuation file and resume work from where the prior session left off.\n\n## When to Use\n\n- Starting a new session and CONTINUE_HERE.md exists in the project root\n- After a SessionStart hook injects continuation context\n- Bootstrapping identity and detecting prior session artifacts\n- Setting up automatic continuation detection for a project (one-time infrastructure)\n\n## Inputs\n\n- **Required**: A project directory (defaults to current working directory)\n- **Optional**: Whether to configure infrastructure (SessionStart hook + CLAUDE.md instruction)\n- **Optional**: Whether to delete the file after consumption (default: yes)\n\n## Procedure\n\n### Step 1: Detect and Read the Continuation File\n\nCheck for `CONTINUE_HERE.md` in the project root:\n\n```bash\nls -la CONTINUE_HERE.md 2>\u002Fdev\u002Fnull\n```\n\nIf absent, exit gracefully — there is nothing to continue from.\n\nIf present, read the file contents. Parse the 5 sections: Objective, Completed, In Progress, Next Steps, Context. Extract the timestamp and branch from the header line.\n\n**Got:** The file is read and its sections are parsed into a clear mental model of the prior session's state.\n\n**If fail:** If the file exists but is malformed (missing sections, empty), treat it as a partial signal — extract whatever is present and note what is missing to the user.\n\n### Step 2: Assess Freshness\n\nCompare the file's timestamp against the current time:\n\n```bash\n# File modification time\nstat -c '%Y' CONTINUE_HERE.md 2>\u002Fdev\u002Fnull || stat -f '%m' CONTINUE_HERE.md\n# Current time\ndate +%s\n```\n\nClassify freshness:\n- **Fresh** (\u003C 24 hours, same branch): safe to act on directly\n- **Stale** (> 24 hours or different branch): flag to user before proceeding\n- **Superseded** (new commits exist after the handoff timestamp): someone worked on the project since the handoff\n\nCheck branch alignment:\n\n```bash\ngit branch --show-current\ngit log --oneline --since=\"$(stat -c '%Y' CONTINUE_HERE.md | xargs -I{} date -d @{} --iso-8601=seconds)\" 2>\u002Fdev\u002Fnull\n```\n\n**Got:** A freshness assessment with classification (fresh, stale, or superseded) and supporting evidence.\n\n**If fail:** If not in a git repo, skip branch and commit checks. Rely on the timestamp in the file header alone.\n\n### Step 3: Summarize and Confirm Resumption\n\nPresent the continuation state to the user concisely:\n- \"Prior session objective: [Objective]\"\n- \"Completed: [summary]\"\n- \"In progress: [summary]\"\n- \"Proposed next action: [Next Steps item 1]\"\n\nIf freshness is \"stale\" or \"superseded\", present the evidence and ask whether to proceed with the handoff or start fresh.\n\nIf any Next Steps items are tagged `**[USER]**`, surface those explicitly — they require user decisions before work can proceed.\n\n**Got:** The user confirms the resumption plan, possibly with adjustments. The agent has a clear mandate for what to do next.\n\n**If fail:** If the user says \"start fresh\" or \"ignore that file\", acknowledge and proceed without the continuation context. Offer to delete the file to prevent future confusion.\n\n### Step 4: Act on the Handoff\n\nBegin working from Next Steps item 1 (or wherever the user directed):\n- Reference In Progress items to understand partial state\n- Use the Context section to avoid retrying failed approaches\n- Treat Completed items as done — do not re-verify unless the user asks\n\n**Got:** The agent is productively working on the right task, informed by the continuation file.\n\n**If fail:** If the Next Steps are ambiguous or the In Progress state is unclear, ask the user for clarification rather than guessing.\n\n### Step 5: Clean Up\n\nAfter the handoff is consumed and work is underway, delete CONTINUE_HERE.md:\n\n```bash\nrm CONTINUE_HERE.md\n```\n\nStale continuation files cause confusion in future sessions.\n\n**Got:** The file is removed. The project root is clean.\n\n**If fail:** If the user wants to keep the file (e.g., as a reference during the session), leave it but note that it should be deleted before session end to prevent the next session from re-consuming it.\n\n### Step 6: Configure SessionStart Hook (Optional)\n\nIf not already configured, set up automatic reading of CONTINUE_HERE.md on session start.\n\nCreate the hook script:\n\n```bash\nmkdir -p ~\u002F.claude\u002Fhooks\u002Fcontinue-here\n\ncat > ~\u002F.claude\u002Fhooks\u002Fcontinue-here\u002Fread-continuation.sh \u003C\u003C 'SCRIPT'\n#!\u002Fbin\u002Fbash\n# SessionStart hook: inject CONTINUE_HERE.md into session context\n# OS-aware: works on native Linux, WSL, macOS, and Windows (Git Bash\u002FMSYS)\nset -uo pipefail\n\n# --- Platform detection ---\ndetect_platform() {\n  case \"$(uname -s)\" in\n    Darwin) echo \"mac\" ;;\n    Linux)\n      if grep -qi microsoft \u002Fproc\u002Fversion 2>\u002Fdev\u002Fnull; then\n        echo \"wsl\"\n      else\n        echo \"linux\"\n      fi ;;\n    MINGW*|MSYS*|CYGWIN*) echo \"windows\" ;;\n    *) echo \"unknown\" ;;\n  esac\n}\nPLATFORM=${PLATFORM:-$(detect_platform)}\n\nCONTINUE_FILE=\"$PWD\u002FCONTINUE_HERE.md\"\n\nif [ ! -f \"$CONTINUE_FILE\" ]; then\n  exit 0\nfi\n\n# Strip CRLF (files on NTFS often have Windows line endings)\nCONTENT=$(sed 's\u002F\\r$\u002F\u002F' \"$CONTINUE_FILE\")\n\n# JSON-escape: prefer jq, fall back to portable awk\nif command -v jq >\u002Fdev\u002Fnull 2>&1; then\n  ESCAPED=$(printf '%s' \"$CONTENT\" | jq -Rsa .)\nelse\n  ESCAPED=$(printf '%s' \"$CONTENT\" | awk '\n    BEGIN { ORS=\"\"; print \"\\\"\" }\n    {\n      gsub(\u002F\\\\\u002F, \"\\\\\\\\\")\n      gsub(\u002F\"\u002F, \"\\\\\\\"\")\n      gsub(\u002F\\t\u002F, \"\\\\t\")\n      if (NR > 1) print \"\\\\n\"\n      print\n    }\n    END { print \"\\\"\" }\n  ')\nfi\n\ncat \u003C\u003C EOF\n{\"hookSpecificOutput\":{\"sessionStartContext\":{\"additionalContext\":$ESCAPED}}}\nEOF\nSCRIPT\n\nchmod +x ~\u002F.claude\u002Fhooks\u002Fcontinue-here\u002Fread-continuation.sh\n```\n\nAdd to `~\u002F.claude\u002Fsettings.json` in the SessionStart hooks array:\n\n```json\n{\n  \"type\": \"command\",\n  \"command\": \"~\u002F.claude\u002Fhooks\u002Fcontinue-here\u002Fread-continuation.sh\",\n  \"timeout\": 5\n}\n```\n\n**Got:** The hook script exists, is executable, and is registered in settings.json. On next session start, if CONTINUE_HERE.md exists, its content is injected into the session context.\n\n**If fail:** Check that settings.json is valid JSON after editing. Test the hook manually: `cd \u002Fyour\u002Fproject && ~\u002F.claude\u002Fhooks\u002Fcontinue-here\u002Fread-continuation.sh`. The script falls back to `awk` if `jq` is not installed, so `jq` is recommended but not required.\n\n### Step 7: Add CLAUDE.md Instruction (Optional)\n\nAdd a brief instruction to the project's CLAUDE.md so Claude understands the file's purpose:\n\n```markdown\n## Session Continuity\n\nIf `CONTINUE_HERE.md` exists in the project root, read it at session start. It contains a structured handoff from a prior session: objective, completed work, in-progress state, next steps, and context. Act on it — acknowledge the continuation, summarize prior state, and propose resuming from the Next Steps section. If the file is older than 24 hours, flag this to the user before proceeding. After the handoff is consumed, the file can be deleted.\n```\n\n**Got:** CLAUDE.md contains the instruction. Future sessions will read and act on CONTINUE_HERE.md even if the SessionStart hook is not configured.\n\n**If fail:** If CLAUDE.md does not exist, create it with just this section. If the file is too long, add the instruction near the top where it will not be truncated.\n\n## Validation\n\n- [ ] CONTINUE_HERE.md was detected (or absence was handled gracefully)\n- [ ] Freshness was assessed (timestamp, branch, post-handoff commits)\n- [ ] Resumption plan was presented to and confirmed by the user\n- [ ] Work began from the correct Next Steps item\n- [ ] The file was cleaned up after consumption\n- [ ] (Optional) SessionStart hook script exists and is executable\n- [ ] (Optional) CLAUDE.md contains the session continuity instruction\n\n## Pitfalls\n\n- **Acting without confirming**: Always present the resumption plan to the user. They may have changed their mind about what to work on, even if the file is fresh.\n- **Trusting stale files blindly**: A continuation file older than 24 hours or from a different branch is a suggestion, not a mandate. Always check freshness.\n- **Ignoring the Context section**: The most valuable part of the file is often the failed approaches. Skipping this section leads to retrying dead ends.\n- **Forgetting to clean up**: Leaving CONTINUE_HERE.md after consumption causes confusion in the next session, which will try to act on it again.\n- **Treating Completed items as unverified**: Unless the user specifically asks, do not re-do completed work. Trust the prior session's assessment.\n\n## Related Skills\n\n- `write-continue-here` — the complement: writing the continuation file at session end\n- `bootstrap-agent-identity` — full identity reconstruction that includes continuation detection as one heuristic\n- `manage-memory` — durable cross-session knowledge (complements this ephemeral handoff)\n- `write-claude-md` — project instructions where the optional continuity guidance lives\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},"session, continuity, handoff, context, workflow, read","Philipp Thoss","general","1.0","multi","basic","Julius Brussee homage — caveman","Read a CONTINUE_HERE.md continuation file at session start and resume from where the prior session left off. Covers detecting the file, assessing freshness, parsing the structured handoff, confirming the resumption plan with the user, and cleaning up after consumption. Optionally configures a SessionStart hook and CLAUDE.md instruction for automatic pickup. Use at the start of a session when a continuation file exists, when bootstrapping after an interrupted session, or when setting up automatic continuation detection.\n","Read Write Bash Grep Glob","82c77053","en","2026-04-26","master","f483e54f3ad5f202a77d45f2e57f8d970b71195f","skills_library\u002Fread-continue-here",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 read-continue-here",{"tool":51,"command":52},"bunx","bunx skills add roohe\u002Fagentic-super-skills --skill read-continue-here",{"tool":54,"command":55},"pnpm","pnpm dlx skills add roohe\u002Fagentic-super-skills --skill read-continue-here","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fread-continue-here\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",[],[]]