[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77YM4V3PFE731QZGCW40GS2":3,"skill-same:01M77YM4V3PFE731QZGCW40GS2":47},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M77YM4V3PFE731QZGCW40GS2","workspace-governance",null,"A methodology-first workspace governance skill for AI agents. Focuses on principles, decision framework, and safe execution patterns instead of fixed directory templates. Triggers on \"organize\", \"cleanup\", \"archive\", \"workspace check\", \"整理工作区\", \"清理文件\", \"归档项目\", \"太乱了\".","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fw\u002Fworkspace-governance\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: workspace-governance\ndescription: >\n  A methodology-first workspace governance skill for AI agents.\n  Focuses on principles, decision framework, and safe execution patterns\n  instead of fixed directory templates. Triggers on \"organize\", \"cleanup\",\n  \"archive\", \"workspace check\", \"整理工作区\", \"清理文件\", \"归档项目\", \"太乱了\".\n---\n\n# Workspace Governance\n\nMethodology-first workspace governance for AI agents.\n\n## Chinese Guide\n\nFor Chinese readers:\n\n- Quick entry: `README.zh-CN.md`\n- Detailed manual: `references\u002F治理手册.zh-CN.md`\n\n## Purpose\n\nThis skill teaches an agent how to design a workspace management strategy that fits its own runtime, platform, and user preferences.\n\nThis is not a single directory template and not a rigid SOP.  \nThe agent should adapt based on context, then execute safely.\n\n## Core Principles\n\n1. Boundary before structure: define what can be touched first.\n2. Plan before action: generate a governance plan before file operations.\n3. Reversible before optimized: preserve rollback paths and avoid irreversible changes.\n4. Fit current system first: reuse existing conventions when they are workable.\n5. User control at key points: destructive operations require explicit confirmation.\n6. Evidence-driven decisions: only propose actions based on real scan results.\n\n## When to Use\n\n- Workspace is messy and needs cleanup or reorganization.\n- User asks to archive\u002Fclose finished work.\n- User asks to create a new project with clear boundaries.\n- User asks for workspace audit\u002Fhealth check.\n- Agent needs to establish sustainable file governance rules.\n\n## Required Capabilities and Preconditions\n\nBefore execution, the agent should verify runtime capabilities:\n\n1. File\u002Fdir inspection and manipulation (`ls`, move, rename, archive, delete).\n2. Logging output capability (file or structured output sink).\n3. User confirmation capability for ambiguous\u002Fdestructive actions.\n\nPreconditions:\n\n- `workspace_root` must be defined (user-provided or default current directory).\n- If `workspace_root` is broad\u002Fhigh-risk, require explicit confirmation before scanning.\n- If confirmation capability is unavailable, `ask-user` items are blocking items.\n\n## Scope and Boundaries\n\nThe agent must define these before execution:\n\n- `workspace_root`: the manageable boundary for this task.\n- `immutable_dirs`: directories that must never be moved\u002Fdeleted\u002Frenamed.\n- `protected_files`: sensitive files (keys, env, certs, VCS metadata).\n- `risk_level`: low\u002Fmedium\u002Fhigh based on destructive potential.\n\nIf `workspace_root` is too broad (for example home root), require explicit confirmation before scanning.\n\n## Adaptation Model (Platform-Agnostic)\n\nThe agent should adapt strategy using this order:\n\n1. User explicit constraints and preferences.\n2. Current repository\u002Fproject conventions.\n3. Platform\u002Fruntime restrictions.\n4. Conservative fallback defaults.\n\nDo not force a fixed folder structure unless the user requests standardization.\n\n### Optional Adapt Block\n\n```yaml\nSKILL_ADAPT:\n  workspace_root: \u003Cpath>\n  immutable_dirs: [dir1, dir2]\n  protected_files: [pattern1, pattern2]\n  cache_policy: separate # separate | consolidate\n  naming_policy: inherit # inherit | enforce\n```\n\n### Adapt Loading Rules (Mandatory)\n\nIf `SKILL_ADAPT.yaml` exists, the agent must read it before planning and execution.\nIf platform profiles exist (for example `tools\u002Fadapt-profiles\u002Fopenclaw.yaml`), the agent should load the matching profile as an overlay.\n\nConfiguration precedence:\n\n1. User explicit instruction in current session.\n2. `SKILL_ADAPT` config.\n3. Repository conventions detected from files.\n4. Conservative defaults from this skill.\n\nIf `SKILL_ADAPT` parsing fails:\n\n- Do not silently ignore.\n- Fall back to conservative defaults.\n- Record a warning in governance logs.\n\nProfile merge semantics:\n\n- `immutable_dirs`: union (security items only increase)\n- `protected_files`: union (protection only increases)\n- `destructive_guard`: override allowed only when strictness is not reduced\n\n## Decision Framework\n\nBefore any move\u002Fdelete action, produce a governance plan with:\n\n1. **Current State Summary**\n   - What is cluttered\n   - What is ambiguous\n   - What is sensitive\n2. **Target Strategy**\n   - Keep, move, rename, archive, delete policy\n   - Naming and lifecycle policy\n   - Cache\u002Ftemp policy\n3. **Risk and Rollback**\n   - Risks per action class\n   - Rollback method and checkpoints\n4. **User Confirmation Items**\n   - Items that need user decision\n   - Items excluded from automation\n\n### Plan Output Template\n\n| Item | Current | Proposed Action | Target | Risk | Reason |\n|------|---------|-----------------|--------|------|--------|\n| example.tmp | root | delete | — | medium | temporary artifact |\n| report-final.docx | root | ask user | docs or archive | low | destination ambiguous |\n\n## Execution Pattern (Generic)\n\nUse this pattern regardless of platform:\n\n1. Detect context and runtime capabilities.\n2. Load `SKILL_ADAPT` (if present) and resolve effective policy by precedence.\n3. Detect boundaries (`workspace_root`, immutable\u002Fprotected scope).\n4. Scan inside `workspace_root` only.\n5. Classify findings: keep\u002Fmove\u002Frename\u002Farchive\u002Fdelete\u002Fask-user.\n6. Generate plan table with reasons, risks, and rollback checkpoints.\n7. Get confirmation for destructive or ambiguous actions.\n8. Execute in small batches with checkpoint logs.\n9. Report results and failures.\n10. Record governance log for traceability.\n\nIf multiple user intents exist, process sequentially and reconfirm between destructive batches.\n\n## Non-Interactive Safety Policy (Mandatory)\n\nFor non-interactive runtimes (cron, background subagent, execute-only environments):\n\n- If any item is classified as `ask-user`, the agent must stop with status `blocked`.\n- The agent must output a `pending_decisions` list and required user input.\n- The agent must not silently skip, auto-approve, or auto-delete ambiguous items.\n- Destructive actions without confirmation capability must be refused (`fail-fast`).\n\nRecommended blocked output:\n\n| Item | Proposed Action | Block Reason | Needed Input |\n|------|-----------------|-------------|--------------|\n| report-final.docx | ask-user | no confirmation channel | choose destination |\n\n## Classification Heuristics (Flexible)\n\nUse heuristics, not hard-coded folders:\n\n- **Project artifacts**: source code, configs, tests, docs tied to one project.\n- **Reusable assets**: media or references used across projects.\n- **Ephemeral data**: cache\u002Ftmp\u002Fbuild artifacts\u002Flog leftovers.\n- **Agent\u002Fruntime state**: tool configs, sessions, internal runtime files.\n- **Ambiguous items**: unclear ownership or destination.\n\nRules:\n- Ambiguous items must be escalated to user decisions.\n- Never silently rename if semantic meaning may change.\n- Never overwrite existing files on move.\n\n## Safety Baseline (Mandatory)\n\n### Never Touch Without Explicit User Approval\n\n- Version control metadata (`.git\u002F`, `.svn\u002F`, `.hg\u002F`)\n- Secret material (`*.key`, `*.pem`, `*.p12`, private credentials)\n- Environment files (`.env` and equivalents)\n- Agent\u002Fruntime configuration directories\n\n### Destructive Action Guardrails\n\n- Always show dry-run plan first.\n- Require explicit confirmation for delete and bulk move.\n- Use collision-safe naming on move.\n- Keep operation logs and failure reasons.\n- Stop and ask user if unexpected high-risk patterns are detected.\n\n## Standard Operation Modes\n\n### 1) Organize\n\nGoal: improve discoverability and reduce clutter with minimal disturbance.\n\n### 2) Create Project\n\nGoal: initialize a new work area aligned with existing conventions.\n\n### 3) Archive Project\n\nGoal: transition inactive work into retrievable cold storage with metadata.\n\n### 4) Hygiene Check\n\nGoal: audit quality signals and output fix recommendations.\n\nNote: The agent should choose implementation details based on local system constraints, not this document's examples.\n\n## Skill Interoperability (Optional)\n\n`workspace-governance` can run standalone, but some scenarios may benefit from companion skills\u002Ftools:\n\n- Git or GitHub-related archive verification: use Git\u002FGitHub skill\u002Ftooling.\n- Cloud\u002Fobject storage archive lifecycle: use cloud storage skills\u002Ftools.\n- Team approval workflow before destructive batches: use workflow\u002Fapproval skills\u002Ftools.\n\nInteroperability rule:\n\n- Never assume companion skills are present.\n- If a companion capability is required by user intent but unavailable, report `blocked` with required dependency.\n\n## Quality Signals for Audit\n\nRecommended checks:\n\n- Boundary clarity (what is managed vs protected)\n- Root clutter level\n- Naming consistency\n- Build\u002Fcache residue\n- Archive lifecycle completeness\n- Recoverability (rollback\u002Freadability of logs)\n\nOutput style:\n- Pass items with clear evidence.\n- Violations with fix suggestion and risk level.\n- Summary with actionable next steps.\n\n## Logging and Traceability\n\nThe agent should keep a lightweight operation record, including:\n\n- Date (`YYYY-MM-DD`)\n- Intent type (organize\u002Fcreate\u002Farchive\u002Faudit)\n- Planned changes vs executed changes\n- Success\u002Ffailure counts\n- Unresolved decisions pending user input\n\n### Rollback and Checkpoint Schema (Minimum)\n\nEach execution should create:\n\n1. A pre-execution checkpoint (`checkpoint_before`).\n2. A checkpoint per batch (`checkpoint_batch_\u003Cn>`).\n3. A final checkpoint (`checkpoint_after`).\n\nMinimum log fields:\n\n- `timestamp` (`YYYY-MM-DD HH:mm:ss`)\n- `intent` (organize\u002Fcreate\u002Farchive\u002Faudit)\n- `batch_id`\n- `action` (move\u002Frename\u002Farchive\u002Fdelete)\n- `source_path`\n- `target_path`\n- `result` (success\u002Ffailure\u002Fblocked)\n- `reversible` (yes\u002Fno)\n- `rollback_ref` (checkpoint id or recovery note)\n\n## Anti-Patterns to Avoid\n\n- Forcing a universal directory layout on every system\n- Performing bulk cleanup without a dry-run plan\n- Treating unknown files as disposable\n- Optimizing structure while ignoring user workflow habits\n- Mixing agent state and user business content without explicit mapping\n\n## Minimal Example (Reference Only)\n\nExample principles in action:\n\n1. Detect workspace boundary and immutable dirs.\n2. Scan only within boundary.\n3. Mark ambiguous files as `ask-user`.\n4. Confirm plan before delete\u002Fmove.\n5. Execute and log.\n\nThis example is illustrative, not normative.\n\n## Author\n\n- 作者: Mars2003 （GitHub）\n- 日期: 2026-04-28\n","# Workspace Governance\n\nMethodology-first workspace governance for AI agents.\n\n## Chinese Guide\n\nFor Chinese readers:\n\n- Quick entry: `README.zh-CN.md`\n- Detailed manual: `references\u002F治理手册.zh-CN.md`\n\n## Purpose\n\nThis skill teaches an agent how to design a workspace management strategy that fits its own runtime, platform, and user preferences.\n\nThis is not a single directory template and not a rigid SOP.  \nThe agent should adapt based on context, then execute safely.\n\n## Core Principles\n\n1. Boundary before structure: define what can be touched first.\n2. Plan before action: generate a governance plan before file operations.\n3. Reversible before optimized: preserve rollback paths and avoid irreversible changes.\n4. Fit current system first: reuse existing conventions when they are workable.\n5. User control at key points: destructive operations require explicit confirmation.\n6. Evidence-driven decisions: only propose actions based on real scan results.\n\n## When to Use\n\n- Workspace is messy and needs cleanup or reorganization.\n- User asks to archive\u002Fclose finished work.\n- User asks to create a new project with clear boundaries.\n- User asks for workspace audit\u002Fhealth check.\n- Agent needs to establish sustainable file governance rules.\n\n## Required Capabilities and Preconditions\n\nBefore execution, the agent should verify runtime capabilities:\n\n1. File\u002Fdir inspection and manipulation (`ls`, move, rename, archive, delete).\n2. Logging output capability (file or structured output sink).\n3. User confirmation capability for ambiguous\u002Fdestructive actions.\n\nPreconditions:\n\n- `workspace_root` must be defined (user-provided or default current directory).\n- If `workspace_root` is broad\u002Fhigh-risk, require explicit confirmation before scanning.\n- If confirmation capability is unavailable, `ask-user` items are blocking items.\n\n## Scope and Boundaries\n\nThe agent must define these before execution:\n\n- `workspace_root`: the manageable boundary for this task.\n- `immutable_dirs`: directories that must never be moved\u002Fdeleted\u002Frenamed.\n- `protected_files`: sensitive files (keys, env, certs, VCS metadata).\n- `risk_level`: low\u002Fmedium\u002Fhigh based on destructive potential.\n\nIf `workspace_root` is too broad (for example home root), require explicit confirmation before scanning.\n\n## Adaptation Model (Platform-Agnostic)\n\nThe agent should adapt strategy using this order:\n\n1. User explicit constraints and preferences.\n2. Current repository\u002Fproject conventions.\n3. Platform\u002Fruntime restrictions.\n4. Conservative fallback defaults.\n\nDo not force a fixed folder structure unless the user requests standardization.\n\n### Optional Adapt Block\n\n```yaml\nSKILL_ADAPT:\n  workspace_root: \u003Cpath>\n  immutable_dirs: [dir1, dir2]\n  protected_files: [pattern1, pattern2]\n  cache_policy: separate # separate | consolidate\n  naming_policy: inherit # inherit | enforce\n```\n\n### Adapt Loading Rules (Mandatory)\n\nIf `SKILL_ADAPT.yaml` exists, the agent must read it before planning and execution.\nIf platform profiles exist (for example `tools\u002Fadapt-profiles\u002Fopenclaw.yaml`), the agent should load the matching profile as an overlay.\n\nConfiguration precedence:\n\n1. User explicit instruction in current session.\n2. `SKILL_ADAPT` config.\n3. Repository conventions detected from files.\n4. Conservative defaults from this skill.\n\nIf `SKILL_ADAPT` parsing fails:\n\n- Do not silently ignore.\n- Fall back to conservative defaults.\n- Record a warning in governance logs.\n\nProfile merge semantics:\n\n- `immutable_dirs`: union (security items only increase)\n- `protected_files`: union (protection only increases)\n- `destructive_guard`: override allowed only when strictness is not reduced\n\n## Decision Framework\n\nBefore any move\u002Fdelete action, produce a governance plan with:\n\n1. **Current State Summary**\n   - What is cluttered\n   - What is ambiguous\n   - What is sensitive\n2. **Target Strategy**\n   - Keep, move, rename, archive, delete policy\n   - Naming and lifecycle policy\n   - Cache\u002Ftemp policy\n3. **Risk and Rollback**\n   - Risks per action class\n   - Rollback method and checkpoints\n4. **User Confirmation Items**\n   - Items that need user decision\n   - Items excluded from automation\n\n### Plan Output Template\n\n| Item | Current | Proposed Action | Target | Risk | Reason |\n|------|---------|-----------------|--------|------|--------|\n| example.tmp | root | delete | — | medium | temporary artifact |\n| report-final.docx | root | ask user | docs or archive | low | destination ambiguous |\n\n## Execution Pattern (Generic)\n\nUse this pattern regardless of platform:\n\n1. Detect context and runtime capabilities.\n2. Load `SKILL_ADAPT` (if present) and resolve effective policy by precedence.\n3. Detect boundaries (`workspace_root`, immutable\u002Fprotected scope).\n4. Scan inside `workspace_root` only.\n5. Classify findings: keep\u002Fmove\u002Frename\u002Farchive\u002Fdelete\u002Fask-user.\n6. Generate plan table with reasons, risks, and rollback checkpoints.\n7. Get confirmation for destructive or ambiguous actions.\n8. Execute in small batches with checkpoint logs.\n9. Report results and failures.\n10. Record governance log for traceability.\n\nIf multiple user intents exist, process sequentially and reconfirm between destructive batches.\n\n## Non-Interactive Safety Policy (Mandatory)\n\nFor non-interactive runtimes (cron, background subagent, execute-only environments):\n\n- If any item is classified as `ask-user`, the agent must stop with status `blocked`.\n- The agent must output a `pending_decisions` list and required user input.\n- The agent must not silently skip, auto-approve, or auto-delete ambiguous items.\n- Destructive actions without confirmation capability must be refused (`fail-fast`).\n\nRecommended blocked output:\n\n| Item | Proposed Action | Block Reason | Needed Input |\n|------|-----------------|-------------|--------------|\n| report-final.docx | ask-user | no confirmation channel | choose destination |\n\n## Classification Heuristics (Flexible)\n\nUse heuristics, not hard-coded folders:\n\n- **Project artifacts**: source code, configs, tests, docs tied to one project.\n- **Reusable assets**: media or references used across projects.\n- **Ephemeral data**: cache\u002Ftmp\u002Fbuild artifacts\u002Flog leftovers.\n- **Agent\u002Fruntime state**: tool configs, sessions, internal runtime files.\n- **Ambiguous items**: unclear ownership or destination.\n\nRules:\n- Ambiguous items must be escalated to user decisions.\n- Never silently rename if semantic meaning may change.\n- Never overwrite existing files on move.\n\n## Safety Baseline (Mandatory)\n\n### Never Touch Without Explicit User Approval\n\n- Version control metadata (`.git\u002F`, `.svn\u002F`, `.hg\u002F`)\n- Secret material (`*.key`, `*.pem`, `*.p12`, private credentials)\n- Environment files (`.env` and equivalents)\n- Agent\u002Fruntime configuration directories\n\n### Destructive Action Guardrails\n\n- Always show dry-run plan first.\n- Require explicit confirmation for delete and bulk move.\n- Use collision-safe naming on move.\n- Keep operation logs and failure reasons.\n- Stop and ask user if unexpected high-risk patterns are detected.\n\n## Standard Operation Modes\n\n### 1) Organize\n\nGoal: improve discoverability and reduce clutter with minimal disturbance.\n\n### 2) Create Project\n\nGoal: initialize a new work area aligned with existing conventions.\n\n### 3) Archive Project\n\nGoal: transition inactive work into retrievable cold storage with metadata.\n\n### 4) Hygiene Check\n\nGoal: audit quality signals and output fix recommendations.\n\nNote: The agent should choose implementation details based on local system constraints, not this document's examples.\n\n## Skill Interoperability (Optional)\n\n`workspace-governance` can run standalone, but some scenarios may benefit from companion skills\u002Ftools:\n\n- Git or GitHub-related archive verification: use Git\u002FGitHub skill\u002Ftooling.\n- Cloud\u002Fobject storage archive lifecycle: use cloud storage skills\u002Ftools.\n- Team approval workflow before destructive batches: use workflow\u002Fapproval skills\u002Ftools.\n\nInteroperability rule:\n\n- Never assume companion skills are present.\n- If a companion capability is required by user intent but unavailable, report `blocked` with required dependency.\n\n## Quality Signals for Audit\n\nRecommended checks:\n\n- Boundary clarity (what is managed vs protected)\n- Root clutter level\n- Naming consistency\n- Build\u002Fcache residue\n- Archive lifecycle completeness\n- Recoverability (rollback\u002Freadability of logs)\n\nOutput style:\n- Pass items with clear evidence.\n- Violations with fix suggestion and risk level.\n- Summary with actionable next steps.\n\n## Logging and Traceability\n\nThe agent should keep a lightweight operation record, including:\n\n- Date (`YYYY-MM-DD`)\n- Intent type (organize\u002Fcreate\u002Farchive\u002Faudit)\n- Planned changes vs executed changes\n- Success\u002Ffailure counts\n- Unresolved decisions pending user input\n\n### Rollback and Checkpoint Schema (Minimum)\n\nEach execution should create:\n\n1. A pre-execution checkpoint (`checkpoint_before`).\n2. A checkpoint per batch (`checkpoint_batch_\u003Cn>`).\n3. A final checkpoint (`checkpoint_after`).\n\nMinimum log fields:\n\n- `timestamp` (`YYYY-MM-DD HH:mm:ss`)\n- `intent` (organize\u002Fcreate\u002Farchive\u002Faudit)\n- `batch_id`\n- `action` (move\u002Frename\u002Farchive\u002Fdelete)\n- `source_path`\n- `target_path`\n- `result` (success\u002Ffailure\u002Fblocked)\n- `reversible` (yes\u002Fno)\n- `rollback_ref` (checkpoint id or recovery note)\n\n## Anti-Patterns to Avoid\n\n- Forcing a universal directory layout on every system\n- Performing bulk cleanup without a dry-run plan\n- Treating unknown files as disposable\n- Optimizing structure while ignoring user workflow habits\n- Mixing agent state and user business content without explicit mapping\n\n## Minimal Example (Reference Only)\n\nExample principles in action:\n\n1. Detect workspace boundary and immutable dirs.\n2. Scan only within boundary.\n3. Mark ambiguous files as `ask-user`.\n4. Confirm plan before delete\u002Fmove.\n5. Execute and log.\n\nThis example is illustrative, not normative.\n\n## Author\n\n- 作者: Mars2003 （GitHub）\n- 日期: 2026-04-28\n",{"name":5,"description":7},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fw\u002Fworkspace-governance",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill workspace-governance",{"tool":39,"command":40},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill workspace-governance",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill workspace-governance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fw\u002Fworkspace-governance\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]