[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73C1Z3ZKMP66YA7VC0DF9F7":3,"skill-same:01M73C1Z3ZKMP66YA7VC0DF9F7":59},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"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":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":44,"updatedAt":45,"install":46,"resources":58},"01M73C1Z3ZKMP66YA7VC0DF9F7","gateguard",null,"Pre-edit fact-forcing quality gate. Ensures agents investigate a file's importers, schemas, and scope constraints before making changes. Part of the 3-layer enforcement model (Hook → Prompt → Skill).","5throck\u002Fai-workspace-standards","5throck","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10958964?v=4","01M73BFEH0V0VS483TW4JD49JW","01M73BFEJ5VQZJHJSFTVPAZGDM",25,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002F.gemini\u002Fskills\u002Fgateguard\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: gateguard\ndescription: >\n  Pre-edit fact-forcing quality gate. Ensures agents investigate a file's\n  importers, schemas, and scope constraints before making changes.\n  Part of the 3-layer enforcement model (Hook → Prompt → Skill).\nversion: 1.0.2\nlast_reviewed: 2026-11-08\nstatus: active\nscope: common\nl2_propagate: true\nowner: pm\nprerequisites: Bun runtime\nmetadata:\n  type: process\n  triggers:\n    - gateguard\n    - \u002Fgateguard\n    - investigate file\n    - check before edit\n    - pre-edit check\n---\n\n# Skill: gateguard\n\n## Context\n\nGateGuard is a pre-edit quality gate that forces agents to investigate a file before making changes. It ensures agents understand:\n- Which files import or depend on the target file\n- What data schemas, interfaces, and type definitions the file exports\n- Whether the user's instructions impose scope constraints\n\nThis is the **manual\u002Fskill layer** of the 3-layer enforcement model. The hook layer (PreToolUse\u002FBeforeTool) provides automatic enforcement on Claude CLI and Gemini CLI. This skill covers manual invocation and Antigravity (where hooks don't fire).\n\n## Enforcement Coverage\n\n| Platform | Hook | Prompt | Skill |\n|----------|:----:|:------:|:-----:|\n| Claude Code CLI | ✅ PreToolUse | ✅ | ✅ |\n| Claude Desktop App | ✅* (bundled CLI) | ✅ | ✅ |\n| Gemini CLI | ✅ BeforeTool | ✅ | ✅ |\n| Antigravity | ❌ | ✅ | ✅ |\n\n\\* Claude Desktop App: documented by Anthropic but workspace testing (2026-05) observed intermittent behavior.\n\n## When to Use\n\n- Before editing any TypeScript, JSON, or configuration file that may be imported by other files\n- When a user request involves modifying shared utilities, type definitions, or script infrastructure\n- When the agent is unsure whether a change is safe to make without investigating dependencies\n- As a pre-check before any architectural modification to workspace scripts, helpers, or registries\n\n## Output Format\n\n```\n[GATEGUARD] Pre-edit investigation complete\n  Target: \u003Cfile-path>\n  Importers: \u003Clist of importing files, or \"none\">\n  Exported schemas: \u003Clist of interfaces\u002Ftypes\u002Fclasses, or \"none\">\n  Scope constraints: \u003Cuser-imposed constraints, or \"none\">\n  Risk level: low | medium | high\n  Recommendation: proceed | proceed with caution | escalate to architect\n```\n\n## Execution Steps\n\nWhen invoked (via `\u002Fgateguard \u003Cfile-path>` or trigger match):\n\n1. **Receive target file path** from arguments or user input\n2. **Search for importers**: Run `grep` for import patterns referencing the target file's basename\n   ```bash\n   grep -r \"from ['\\\"].*\u003Cbasename>['\\\"]\" --include=\"*.ts\" --include=\"*.js\" --include=\"*.json\" --include=\"*.md\" . | grep -v node_modules | grep -v \".git\"\n   ```\n3. **Extract schemas**: Scan the target file for `interface`, `type`, `enum`, `class` exports\n4. **Summarize findings** (1-3 sentences):\n   - List importers (if any) and their relationship to the target\n   - Note any exported schemas that downstream consumers depend on\n   - Flag any scope constraints from user instructions\n5. **Present to agent**: Output summary as `[GATEGUARD] Pre-edit investigation complete` with findings\n\n## Agent Behavior After Investigation\n\nAfter completing the GateGuard investigation, the agent may proceed with the edit. If importers were found, the agent should verify that changes won't break downstream consumers.\n\n## Related Skills\n\n- CONSTITUTION.md §11.2 — GateGuard specification\n- `scripts\u002Fhooks\u002Fgateguard-fact-force.ts` — Hook layer implementation\n- ADR-0021 — Platform Settings Parity Policy\n","# Skill: gateguard\n\n## Context\n\nGateGuard is a pre-edit quality gate that forces agents to investigate a file before making changes. It ensures agents understand:\n- Which files import or depend on the target file\n- What data schemas, interfaces, and type definitions the file exports\n- Whether the user's instructions impose scope constraints\n\nThis is the **manual\u002Fskill layer** of the 3-layer enforcement model. The hook layer (PreToolUse\u002FBeforeTool) provides automatic enforcement on Claude CLI and Gemini CLI. This skill covers manual invocation and Antigravity (where hooks don't fire).\n\n## Enforcement Coverage\n\n| Platform | Hook | Prompt | Skill |\n|----------|:----:|:------:|:-----:|\n| Claude Code CLI | ✅ PreToolUse | ✅ | ✅ |\n| Claude Desktop App | ✅* (bundled CLI) | ✅ | ✅ |\n| Gemini CLI | ✅ BeforeTool | ✅ | ✅ |\n| Antigravity | ❌ | ✅ | ✅ |\n\n\\* Claude Desktop App: documented by Anthropic but workspace testing (2026-05) observed intermittent behavior.\n\n## When to Use\n\n- Before editing any TypeScript, JSON, or configuration file that may be imported by other files\n- When a user request involves modifying shared utilities, type definitions, or script infrastructure\n- When the agent is unsure whether a change is safe to make without investigating dependencies\n- As a pre-check before any architectural modification to workspace scripts, helpers, or registries\n\n## Output Format\n\n```\n[GATEGUARD] Pre-edit investigation complete\n  Target: \u003Cfile-path>\n  Importers: \u003Clist of importing files, or \"none\">\n  Exported schemas: \u003Clist of interfaces\u002Ftypes\u002Fclasses, or \"none\">\n  Scope constraints: \u003Cuser-imposed constraints, or \"none\">\n  Risk level: low | medium | high\n  Recommendation: proceed | proceed with caution | escalate to architect\n```\n\n## Execution Steps\n\nWhen invoked (via `\u002Fgateguard \u003Cfile-path>` or trigger match):\n\n1. **Receive target file path** from arguments or user input\n2. **Search for importers**: Run `grep` for import patterns referencing the target file's basename\n   ```bash\n   grep -r \"from ['\\\"].*\u003Cbasename>['\\\"]\" --include=\"*.ts\" --include=\"*.js\" --include=\"*.json\" --include=\"*.md\" . | grep -v node_modules | grep -v \".git\"\n   ```\n3. **Extract schemas**: Scan the target file for `interface`, `type`, `enum`, `class` exports\n4. **Summarize findings** (1-3 sentences):\n   - List importers (if any) and their relationship to the target\n   - Note any exported schemas that downstream consumers depend on\n   - Flag any scope constraints from user instructions\n5. **Present to agent**: Output summary as `[GATEGUARD] Pre-edit investigation complete` with findings\n\n## Agent Behavior After Investigation\n\nAfter completing the GateGuard investigation, the agent may proceed with the edit. If importers were found, the agent should verify that changes won't break downstream consumers.\n\n## Related Skills\n\n- CONSTITUTION.md §11.2 — GateGuard specification\n- `scripts\u002Fhooks\u002Fgateguard-fact-force.ts` — Hook layer implementation\n- ADR-0021 — Platform Settings Parity Policy\n",{"name":5,"owner":23,"scope":24,"status":25,"version":26,"metadata":27,"description":34,"l2_propagate":35,"last_reviewed":36,"prerequisites":37},"pm","common","active","1.0.2",{"type":28,"triggers":29},"process",[5,30,31,32,33],"\u002Fgateguard","investigate file","check before edit","pre-edit check","Pre-edit fact-forcing quality gate. Ensures agents investigate a file's importers, schemas, and scope constraints before making changes. Part of the 3-layer enforcement model (Hook → Prompt → Skill).\n",true,1794096000000,"Bun runtime","main","1162ccc568cf90c01b3886d6143cbfd851a37883",".gemini\u002Fskills\u002Fgateguard",9,"https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards","https:\u002F\u002Fgithub.com\u002F5throck","Experienced in digital transformation, enterprise IT, startup acceleration, and business strategy. Focused on building practical systems that connect technolo","2026-11-14 21:22:34",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":35},[48,51,54],{"tool":49,"command":50},"npx","npx skills add 5throck\u002Fai-workspace-standards --skill gateguard",{"tool":52,"command":53},"bunx","bunx skills add 5throck\u002Fai-workspace-standards --skill gateguard",{"tool":55,"command":56},"pnpm","pnpm dlx skills add 5throck\u002Fai-workspace-standards --skill gateguard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002F.gemini\u002Fskills\u002Fgateguard\u002FSKILL.md",[],[60,68,73,78,83,88],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":67},"01M7BBJDYHJMGTJYSC37JVWY8S","i18n-layout","Text layout and encoding guidance: character encoding (UTF-8, legacy Korean code pages, BOM hazards), line endings, RTL\u002Fbidi handling, and script-specific font selection (Hangul focus). Use when: encoding is corrupted or mojibake appears, an RTL locale must render correctly, fonts must be chosen for a script, or CRLF\u002FBOM issues surface.","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":69,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":67},"01M7BBJ9XHAAS1AVGKZZ841VBZ","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.hermes\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":74,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":67},"01M7BBJ5C3X8TKFKG5R9P9P49W","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.gemini\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":79,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":67},"01M7BBJ1B52X0QMJ2QVBMPJB37","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.codex\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":84,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":67},"01M7BBHX91BW2Q2R276MRX5AW3","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.claude\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":89,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":67},"01M7BBHQWGXPSFRWN1PRC2NMMV","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.agents\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[]]