[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79FXK7DXJ2NF2G17NDPJM4V":3,"skill-same:01M79FXK7DXJ2NF2G17NDPJM4V":58},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":14,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M79FXK7DXJ2NF2G17NDPJM4V","skill-installer",null,"Discover, fetch, validate, and install Grok skills from local directories, GitHub repository URLs (or tree paths), or known curated collections. Creates the proper directory structure under the chosen scope (~\u002F.grok\u002Fskills\u002F, \u003Crepo>\u002F.grok\u002Fskills\u002F, or .\u002F .grok\u002Fskills\u002F), validates the SKILL.md frontmatter, optionally runs a post- install check, and reports exactly what was installed. Use when the user says \"install the X skill\", \"$skill-installer ...\", \"add this skill from github\", \"skill-installer\", or wants to bring in a ported-from-codex or community skill.","zfifteen\u002Fskills-catalog","zfifteen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F221906715?v=4","01M79CQFXDZM5J5CJTCECPFA66","Dionisio Alberto Lopez III","01M79CQFY4C62PN8A2T5KDAHGA",1,"MIT","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fskill-installer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skill-installer\ndescription: >\n  Discover, fetch, validate, and install Grok skills from local directories, GitHub\n  repository URLs (or tree paths), or known curated collections. Creates the proper\n  directory structure under the chosen scope (~\u002F.grok\u002Fskills\u002F, \u003Crepo>\u002F.grok\u002Fskills\u002F,\n  or .\u002F .grok\u002Fskills\u002F), validates the SKILL.md frontmatter, optionally runs a post-\n  install check, and reports exactly what was installed. Use when the user says\n  \"install the X skill\", \"$skill-installer ...\", \"add this skill from github\",\n  \"skill-installer\", or wants to bring in a ported-from-codex or community skill.\nwhen-to-use: Use when the user wants to install a new or updated skill (local path, GitHub URL, or named curated skill) into one of the Grok skill search locations.\nargument-hint: \"\u003Cskill-name-or-path-or-github-url> [to \u003Cscope: user|project|local>]\"\nmetadata:\n  short-description: \"Install skills from local, GitHub, or curated sources into Grok\"\n  source: \"ported-from-codex\u002Fskill-installer (inferred from Codex $skill-installer behavior + vendor_imports)\"\n  original_codex: \"skill-installer (built-in Codex command \u002F $skill-installer)\"\n---\n\n# Skill Installer\n\nInstall or update Grok skills safely and repeatably.\n\n## Scopes (in priority order for the running Grok)\n- Local (CWD): `.\u002F.grok\u002Fskills\u002F\u003Cname>\u002F`\n- Project (repo root): `\u003Crepo-root>\u002F.grok\u002Fskills\u002F\u003Cname>\u002F`\n- User: `~\u002F.grok\u002Fskills\u002F\u003Cname>\u002F`\n\nThe skill will ask or infer the best scope (default Project if inside a git repo, else User).\n\n## Step 1: Parse the Request\nAccept inputs like:\n- `my-skill` (name only — will search known locations or prompt for source)\n- `.\u002Fpath\u002Fto\u002Flocal\u002Fskill-dir`\n- `https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\u002Ftree\u002Fmain\u002Fskills\u002Fmy-skill`\n- `install the create-plan skill from .experimental`\n- Named curated skills (the skill can maintain a small built-in catalog or fetch a manifest)\n\nResolve the source to a concrete location (local dir or clonable GitHub URL).\n\n## Step 2: Fetch \u002F Copy the Skill\n- **Local path**: Validate it exists and contains SKILL.md. Copy (or symlink in dev mode) the entire directory.\n- **GitHub URL**: Use `grok_com_github` MCP tools (get_file_contents on SKILL.md + supporting files, or fall back to `run_terminal_cmd git clone --depth 1 --filter=blob:none` + sparse checkout of the skill subtree). Or use `open_page` \u002F `web_fetch` + manual reconstruction for simple cases.\n- Create the target directory under the chosen scope using `run_terminal_cmd mkdir -p` or by writing files via the `write` \u002F `search_replace` tools.\n\n## Step 3: Validate the Skill (Use the Helper Script)\nAlways run the bundled validator:\n\n```bash\npython3 \"\u003Cskill-dir>\u002Fscripts\u002Finstall_skill.py\" validate \"\u003Cpath-to-candidate-skill-dir>\"\n```\n\nThe script checks:\n- Presence and parseability of SKILL.md\n- Valid YAML frontmatter with required `name` and `description`\n- `name` matches the directory name (or warns)\n- No obvious dangerous content (e.g. exec in frontmatter)\n- Presence of referenced scripts\u002F (they must exist if declared)\n- Basic size \u002F structure sanity\n\nOnly proceed on clean validation (or explicit user override after showing warnings).\n\n## Step 4: Install \u002F Write the Files\n- For each file in the source skill (SKILL.md, scripts\u002F*, references\u002F*, templates\u002F*, etc.):\n  - Read source content (via `read_file` for local, MCP get_file_contents or web for remote).\n  - Write to the target location using the agent's `write` tool (or `search_replace` with empty old_string for new files).\n- Preserve executable bits on scripts where possible (the helper can emit `chmod +x` commands for the agent to run).\n- Record an install receipt: `installed-from.json` inside the target skill dir with source, commit-ish (if git), timestamp, and validation result.\n\n## Step 5: Post-Install\n- Tell the user the exact final path.\n- Instruct: \"Run `grok inspect --json` or `\u002Fskills` to verify. The skill should appear within seconds (auto-reload on disk change).\"\n- Offer to immediately test it: \"Would you like me to inject `\u002F\u003Cname>` now and run a quick smoke test?\"\n- If the skill declares a `post_install` hook or test command in metadata, surface it.\n\n## Step 6: Update \u002F Re-install\nIf the target already exists:\n- Show a diff summary (or full `git diff` style if the target is tracked).\n- Ask for confirmation before overwriting.\n- Support `--force` \u002F \"update in place\".\n\n## The Helper Script\n`scripts\u002Finstall_skill.py` (real Python, invoked via `run_terminal_cmd`):\n- Subcommands: `validate`, `install`, `diff`, `receipt`\n- Understands both local filesystem paths and can be extended for GitHub tree URLs.\n- Is the single source of truth for \"is this a valid Grok skill?\"\n- Designed to be run from the workspace root; resolves the target skill dir relative to SKILL.md location of *this* installer skill when needed.\n\nSee the script source for exact CLI and behavior.\n\n## Success Criteria\n- The installed skill is immediately discoverable by Grok (appears in `\u002Fskills` and `grok inspect`).\n- All files from the source are present and bit-for-bit identical (modulo line endings on Windows).\n- Validation passed or user explicitly accepted the warnings.\n- The user knows exactly where it landed and how to invoke it.\n- No silent overwrites of user-modified skills.\n\n## Safety & Ethics\n- Never install skills from untrusted sources without explicit user confirmation.\n- Show the full source URL \u002F path and a summary of what will be written before writing anything.\n- If the skill contains references\u002F or large assets, warn about disk usage.\n- Support \"dry-run\" mode that only prints the plan.\n\n## For This Repo (Prime Gap Structure)\nWhen installing skills here, prefer the project scope (`\u003Crepo>\u002F.grok\u002Fskills\u002F`) so the whole team benefits. After install, review the new skill against AGENTS.md before using it on PGS work.\n\n## Related Skills\n- `create-skill` (the bundled interactive creator) — use this installer to bring in ports or community skills; use create-skill for brand-new ones authored in-session.\n","# Skill Installer\n\nInstall or update Grok skills safely and repeatably.\n\n## Scopes (in priority order for the running Grok)\n- Local (CWD): `.\u002F.grok\u002Fskills\u002F\u003Cname>\u002F`\n- Project (repo root): `\u003Crepo-root>\u002F.grok\u002Fskills\u002F\u003Cname>\u002F`\n- User: `~\u002F.grok\u002Fskills\u002F\u003Cname>\u002F`\n\nThe skill will ask or infer the best scope (default Project if inside a git repo, else User).\n\n## Step 1: Parse the Request\nAccept inputs like:\n- `my-skill` (name only — will search known locations or prompt for source)\n- `.\u002Fpath\u002Fto\u002Flocal\u002Fskill-dir`\n- `https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\u002Ftree\u002Fmain\u002Fskills\u002Fmy-skill`\n- `install the create-plan skill from .experimental`\n- Named curated skills (the skill can maintain a small built-in catalog or fetch a manifest)\n\nResolve the source to a concrete location (local dir or clonable GitHub URL).\n\n## Step 2: Fetch \u002F Copy the Skill\n- **Local path**: Validate it exists and contains SKILL.md. Copy (or symlink in dev mode) the entire directory.\n- **GitHub URL**: Use `grok_com_github` MCP tools (get_file_contents on SKILL.md + supporting files, or fall back to `run_terminal_cmd git clone --depth 1 --filter=blob:none` + sparse checkout of the skill subtree). Or use `open_page` \u002F `web_fetch` + manual reconstruction for simple cases.\n- Create the target directory under the chosen scope using `run_terminal_cmd mkdir -p` or by writing files via the `write` \u002F `search_replace` tools.\n\n## Step 3: Validate the Skill (Use the Helper Script)\nAlways run the bundled validator:\n\n```bash\npython3 \"\u003Cskill-dir>\u002Fscripts\u002Finstall_skill.py\" validate \"\u003Cpath-to-candidate-skill-dir>\"\n```\n\nThe script checks:\n- Presence and parseability of SKILL.md\n- Valid YAML frontmatter with required `name` and `description`\n- `name` matches the directory name (or warns)\n- No obvious dangerous content (e.g. exec in frontmatter)\n- Presence of referenced scripts\u002F (they must exist if declared)\n- Basic size \u002F structure sanity\n\nOnly proceed on clean validation (or explicit user override after showing warnings).\n\n## Step 4: Install \u002F Write the Files\n- For each file in the source skill (SKILL.md, scripts\u002F*, references\u002F*, templates\u002F*, etc.):\n  - Read source content (via `read_file` for local, MCP get_file_contents or web for remote).\n  - Write to the target location using the agent's `write` tool (or `search_replace` with empty old_string for new files).\n- Preserve executable bits on scripts where possible (the helper can emit `chmod +x` commands for the agent to run).\n- Record an install receipt: `installed-from.json` inside the target skill dir with source, commit-ish (if git), timestamp, and validation result.\n\n## Step 5: Post-Install\n- Tell the user the exact final path.\n- Instruct: \"Run `grok inspect --json` or `\u002Fskills` to verify. The skill should appear within seconds (auto-reload on disk change).\"\n- Offer to immediately test it: \"Would you like me to inject `\u002F\u003Cname>` now and run a quick smoke test?\"\n- If the skill declares a `post_install` hook or test command in metadata, surface it.\n\n## Step 6: Update \u002F Re-install\nIf the target already exists:\n- Show a diff summary (or full `git diff` style if the target is tracked).\n- Ask for confirmation before overwriting.\n- Support `--force` \u002F \"update in place\".\n\n## The Helper Script\n`scripts\u002Finstall_skill.py` (real Python, invoked via `run_terminal_cmd`):\n- Subcommands: `validate`, `install`, `diff`, `receipt`\n- Understands both local filesystem paths and can be extended for GitHub tree URLs.\n- Is the single source of truth for \"is this a valid Grok skill?\"\n- Designed to be run from the workspace root; resolves the target skill dir relative to SKILL.md location of *this* installer skill when needed.\n\nSee the script source for exact CLI and behavior.\n\n## Success Criteria\n- The installed skill is immediately discoverable by Grok (appears in `\u002Fskills` and `grok inspect`).\n- All files from the source are present and bit-for-bit identical (modulo line endings on Windows).\n- Validation passed or user explicitly accepted the warnings.\n- The user knows exactly where it landed and how to invoke it.\n- No silent overwrites of user-modified skills.\n\n## Safety & Ethics\n- Never install skills from untrusted sources without explicit user confirmation.\n- Show the full source URL \u002F path and a summary of what will be written before writing anything.\n- If the skill contains references\u002F or large assets, warn about disk usage.\n- Support \"dry-run\" mode that only prints the plan.\n\n## For This Repo (Prime Gap Structure)\nWhen installing skills here, prefer the project scope (`\u003Crepo>\u002F.grok\u002Fskills\u002F`) so the whole team benefits. After install, review the new skill against AGENTS.md before using it on PGS work.\n\n## Related Skills\n- `create-skill` (the bundled interactive creator) — use this installer to bring in ports or community skills; use create-skill for brand-new ones authored in-session.\n",{"name":5,"metadata":24,"description":28,"when-to-use":29,"argument-hint":30},{"source":25,"original_codex":26,"short-description":27},"ported-from-codex\u002Fskill-installer (inferred from Codex $skill-installer behavior + vendor_imports)","skill-installer (built-in Codex command \u002F $skill-installer)","Install skills from local, GitHub, or curated sources into Grok","Discover, fetch, validate, and install Grok skills from local directories, GitHub repository URLs (or tree paths), or known curated collections. Creates the proper directory structure under the chosen scope (~\u002F.grok\u002Fskills\u002F, \u003Crepo>\u002F.grok\u002Fskills\u002F, or .\u002F .grok\u002Fskills\u002F), validates the SKILL.md frontmatter, optionally runs a post- install check, and reports exactly what was installed. Use when the user says \"install the X skill\", \"$skill-installer ...\", \"add this skill from github\", \"skill-installer\", or wants to bring in a ported-from-codex or community skill.\n","Use when the user wants to install a new or updated skill (local path, GitHub URL, or named curated skill) into one of the Grok skill search locations.","\u003Cskill-name-or-path-or-github-url> [to \u003Cscope: user|project|local>]","main","d9535210da9af28aa76bca80de80355197e1b6d6","skills\u002Fskill-installer","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog","https:\u002F\u002Fgithub.com\u002Fzfifteen","I like to measure things.","2026-07-19 23:41:54",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add zfifteen\u002Fskills-catalog --skill skill-installer",{"tool":44,"command":45},"bunx","bunx skills add zfifteen\u002Fskills-catalog --skill skill-installer",{"tool":47,"command":48},"pnpm","pnpm dlx skills add zfifteen\u002Fskills-catalog --skill skill-installer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fskill-installer\u002FSKILL.md",true,[52],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"scripts\u002Finstall_skill.py","SCRIPT","脚本",7037,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fskill-installer\u002Fscripts\u002Finstall_skill.py",[59,66,73,80,89,96],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M79GXQ2PWPT2E4CJYHXVJ0YE","Zotero","Use Zotero Desktop from Codex to enable\u002Fprobe the local API, search a local Zotero library, list items\u002Fcollections\u002Ftags, export BibTeX, insert citation keys into LaTeX or Markdown drafts, read indexed full text when requested, and import BibTeX\u002FRIS records into Zotero through the connector server. Use when the user mentions Zotero, citations, references.bib, BibTeX export, local Zotero API, localhost:23119, or adding citations from a Zotero library.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fzotero\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M79GXN85NETKBE06865CWK6Z","zoom-apps-sdk","Use when using Apps SDK.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M79GXCYD7FGYS932J9N9RFFY","youtube","Obtain accurate, timestamped YouTube video transcripts (preferring manual captions over auto-generated) as the primary deliverable, then derive summaries, key claims, or notes from that transcript.  Use when the user provides a YouTube URL (or video ID) and wants the transcript, a faithful summary, key claims with attribution, timestamped notes, or \"what does this video actually say\".  The skill is transcript-first: never substitute metadata, title, description, or search snippets for the spoken content.  Triggers: \"youtube transcript\", \"get the transcript of this video\", \"summarize this youtube video\", \"what did they say in https:\u002F\u002Fyoutube.com\u002F...\", \"key claims from this talk\".","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M79GX8EXHHYM566BKR7MS778","yeet","Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M79GX2HFJPX84NMRE5VBTYX9","x-post-creator","Create X-ready post threads and co-located story packages from the active conversation or referenced project material. Use when the user says turn this into an X-post, \u002Fx-post, make this into an X thread, or wants plain-language social posts with supporting images saved to docs\u002Fx-posts\u002F[story-name]\u002F.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fx-post-creator\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M79GWXQT4HBT6QME6QSBZJFA","x-api","Search, read, and write X posts through the local X API MCP server (the same backend used by the Codex x-api skill). Use for searching X\u002Fx.com, reading threads and replies, creating lists, staging\u002Fpublishing posts for @alltheputs, finding high-visibility reply targets for research outreach, ingesting public context, or any request that mentions \u002Fx-api or \"search X\".","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fx-api\u002FSKILL.md",[],[]]