[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72BSYGNH81XEQ8ZGSXNQG3D":3,"skill-same:01M72BSYGNH81XEQ8ZGSXNQG3D":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":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M72BSYGNH81XEQ8ZGSXNQG3D","gcc",null,"Git Context Controller (GCC) - Manages agent memory as a versioned file system under .GCC\u002F. This skill should be used when working on multi-step projects that benefit from structured memory persistence, milestone tracking, branching for alternative approaches, and cross-session context recovery. Triggers on \u002Fgcc commands or natural language like 'commit this progress', 'branch to try an alternative', 'merge results', 'recover context'.","Sansar35\u002Fclaude-agent","Sansar35","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F145020281?v=4","01M724CQ2SCC86MGNSD87D0D4K","01M724CQ3965G9WJ3QXE3AJ5YY",1,"MIT","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fgcc\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: gcc\ndescription: \"Git Context Controller (GCC) - Manages agent memory as a versioned file system under .GCC\u002F. This skill should be used when working on multi-step projects that benefit from structured memory persistence, milestone tracking, branching for alternative approaches, and cross-session context recovery. Triggers on \u002Fgcc commands or natural language like 'commit this progress', 'branch to try an alternative', 'merge results', 'recover context'.\"\n---\n\n# Git Context Controller (GCC)\n\n## Overview\n\nGCC transforms agent memory from a passive token stream into a structured, versioned file system under `.GCC\u002F`. Inspired by Git, it provides four operations — COMMIT, BRANCH, MERGE, CONTEXT — to persist milestones, explore alternatives in isolation, synthesize results, and recover historical context efficiently.\n\n## Initialization\n\nOn first use, check if `.GCC\u002F` exists in the project root. If not, run `scripts\u002Fgcc_init.sh` to create the directory structure:\n\n```\n.GCC\u002F\n├── main.md          # Global roadmap and objectives\n├── metadata.yaml    # Infrastructure state (branches, file tree, config)\n├── commit.md        # Commit history for main branch\n├── log.md           # OTA execution log for main branch\n└── branches\u002F        # Isolated workspaces for experiments\n    └── \u003Cbranch-name>\u002F\n        ├── commit.md\n        ├── log.md\n        └── summary.md\n```\n\nFor detailed file format specifications, read `references\u002Ffile_formats.md`.\n\n## Configuration\n\nGCC behavior is controlled via `metadata.yaml`:\n\n- `proactive_commits: true` — Automatically suggest commits after completing coherent sub-tasks\n- `proactive_commits: false` — Only commit when explicitly requested\n\nToggle with: \"enable\u002Fdisable proactive commits\" or by editing `metadata.yaml`.\n\n## Commands\n\n### COMMIT\n\nPersist a milestone on the current branch.\n\n**Triggers**: `\u002Fgcc commit \u003Csummary>`, \"commit this progress\", \"save this milestone\", \"checkpoint\"\n\n**Procedure**:\n1. Read the current branch's `commit.md` to determine the next commit number\n2. Append a new entry to `commit.md` with:\n   - Sequential ID (e.g., `[C004]`)\n   - Date (UTC ISO 8601)\n   - Current branch name\n   - Branch purpose (from `summary.md` if on a branch, or from `main.md`)\n   - Previous progress summary (1-2 sentences from last commit)\n   - This commit's contribution (detailed technical description with files touched)\n3. Append an OTA entry to `log.md` recording the commit action\n4. Update `metadata.yaml` file tree if files were created\u002Fmodified\n5. If on main branch, update milestones section in `main.md`\n\n**Proactive behavior**: When `proactive_commits: true`, suggest a commit after:\n- Completing a function, module, or coherent unit of work\n- Fixing a bug and verifying the fix\n- Finishing a research\u002Fexploration phase with conclusions\n- Any point where losing context would mean re-doing significant work\n\n### BRANCH\n\nCreate an isolated workspace for exploring an alternative approach.\n\n**Triggers**: `\u002Fgcc branch \u003Cname>`, \"branch to try...\", \"explore alternative...\", \"experiment with...\"\n\n**Procedure**:\n1. Create `.GCC\u002Fbranches\u002F\u003Cbranch-name>\u002F` directory\n2. Create `summary.md` with: purpose, parent branch, creation date, key hypotheses\n3. Create empty `commit.md` and `log.md` for the branch\n4. Update `metadata.yaml` to register the new branch\n5. Update `main.md` Active Branches section\n6. Log the branch creation in the parent branch's `log.md`\n\nFrom this point, all COMMITs and OTA logs go to the branch-specific files until a MERGE or explicit branch switch.\n\n### MERGE\n\nIntegrate a completed branch back into the main flow.\n\n**Triggers**: `\u002Fgcc merge \u003Cbranch>`, \"merge results from...\", \"integrate the experiment\", \"branch X is done\"\n\n**Procedure**:\n1. Read the branch's `summary.md` and `commit.md` to understand outcomes\n2. Append a synthesis commit to main's `commit.md` summarizing:\n   - What was tried\n   - What was learned\n   - What is being integrated (or why the branch is being abandoned)\n3. Update `main.md`:\n   - Add milestone entry with branch results\n   - Remove from Active Branches\n   - Update objectives if applicable\n4. Update `metadata.yaml`: set branch status to `merged` or `abandoned`\n5. Log the merge in main's `log.md`\n\n### CONTEXT\n\nRetrieve historical memory at different resolution levels.\n\n**Triggers**: `\u002Fgcc context \u003Cflag>`, \"what did we do on...\", \"recover context\", \"show me the history\", \"where were we\"\n\n**Flags**:\n\n- `--branch [name]` — Read `summary.md` and latest commits for a specific branch (or current branch if no name). Provides high-level understanding of what happened and why.\n\n- `--log [n]` — Read last N entries (default 20) from the current branch's `log.md`. Provides fine-grained OTA traces for debugging or resuming interrupted work.\n\n- `--metadata` — Read `metadata.yaml` to recover project structure: file tree, dependencies, active branches, configuration.\n\n- `--full` — Read `main.md` for the complete project roadmap, all milestones, and active branches. Use for cross-session recovery or handoff to another agent.\n\nWhen no flag is specified, default to `--branch` for the current active branch.\n\n## OTA Logging\n\nThroughout all work (not just during explicit commands), maintain the OTA execution log:\n\n1. **Observation**: What was noticed or discovered\n2. **Thought**: Reasoning about what to do next\n3. **Action**: What action was taken\n\nAppend entries to the active branch's `log.md`. Keep a maximum of 50 entries; when exceeding, remove the oldest entries. Each entry includes a sequential ID, timestamp, and branch name.\n\nLog OTA entries at meaningful decision points — not every single action, but significant observations, strategy changes, and outcomes.\n\n## Cross-Session Recovery\n\nWhen starting a new session on an existing project with `.GCC\u002F`:\n\n1. Read `metadata.yaml` to understand project state and active branches\n2. Read `main.md` for the global roadmap and objectives\n3. Read the active branch's latest commits and log entries\n4. Resume work with full context of what was accomplished and what remains\n\n## Natural Language Mapping\n\n| User says | Command |\n|---|---|\n| \"save\u002Fcheckpoint\u002Fpersist this\" | COMMIT |\n| \"try a different approach\" | BRANCH |\n| \"that experiment worked, integrate it\" | MERGE |\n| \"where were we?\" \u002F \"what's the status?\" | CONTEXT --full |\n| \"what happened on branch X?\" | CONTEXT --branch X |\n| \"show recent activity\" | CONTEXT --log |\n| \"what files do we have?\" | CONTEXT --metadata |\n| \"enable\u002Fdisable auto-commits\" | Toggle `proactive_commits` in metadata.yaml |\n","# Git Context Controller (GCC)\n\n## Overview\n\nGCC transforms agent memory from a passive token stream into a structured, versioned file system under `.GCC\u002F`. Inspired by Git, it provides four operations — COMMIT, BRANCH, MERGE, CONTEXT — to persist milestones, explore alternatives in isolation, synthesize results, and recover historical context efficiently.\n\n## Initialization\n\nOn first use, check if `.GCC\u002F` exists in the project root. If not, run `scripts\u002Fgcc_init.sh` to create the directory structure:\n\n```\n.GCC\u002F\n├── main.md          # Global roadmap and objectives\n├── metadata.yaml    # Infrastructure state (branches, file tree, config)\n├── commit.md        # Commit history for main branch\n├── log.md           # OTA execution log for main branch\n└── branches\u002F        # Isolated workspaces for experiments\n    └── \u003Cbranch-name>\u002F\n        ├── commit.md\n        ├── log.md\n        └── summary.md\n```\n\nFor detailed file format specifications, read `references\u002Ffile_formats.md`.\n\n## Configuration\n\nGCC behavior is controlled via `metadata.yaml`:\n\n- `proactive_commits: true` — Automatically suggest commits after completing coherent sub-tasks\n- `proactive_commits: false` — Only commit when explicitly requested\n\nToggle with: \"enable\u002Fdisable proactive commits\" or by editing `metadata.yaml`.\n\n## Commands\n\n### COMMIT\n\nPersist a milestone on the current branch.\n\n**Triggers**: `\u002Fgcc commit \u003Csummary>`, \"commit this progress\", \"save this milestone\", \"checkpoint\"\n\n**Procedure**:\n1. Read the current branch's `commit.md` to determine the next commit number\n2. Append a new entry to `commit.md` with:\n   - Sequential ID (e.g., `[C004]`)\n   - Date (UTC ISO 8601)\n   - Current branch name\n   - Branch purpose (from `summary.md` if on a branch, or from `main.md`)\n   - Previous progress summary (1-2 sentences from last commit)\n   - This commit's contribution (detailed technical description with files touched)\n3. Append an OTA entry to `log.md` recording the commit action\n4. Update `metadata.yaml` file tree if files were created\u002Fmodified\n5. If on main branch, update milestones section in `main.md`\n\n**Proactive behavior**: When `proactive_commits: true`, suggest a commit after:\n- Completing a function, module, or coherent unit of work\n- Fixing a bug and verifying the fix\n- Finishing a research\u002Fexploration phase with conclusions\n- Any point where losing context would mean re-doing significant work\n\n### BRANCH\n\nCreate an isolated workspace for exploring an alternative approach.\n\n**Triggers**: `\u002Fgcc branch \u003Cname>`, \"branch to try...\", \"explore alternative...\", \"experiment with...\"\n\n**Procedure**:\n1. Create `.GCC\u002Fbranches\u002F\u003Cbranch-name>\u002F` directory\n2. Create `summary.md` with: purpose, parent branch, creation date, key hypotheses\n3. Create empty `commit.md` and `log.md` for the branch\n4. Update `metadata.yaml` to register the new branch\n5. Update `main.md` Active Branches section\n6. Log the branch creation in the parent branch's `log.md`\n\nFrom this point, all COMMITs and OTA logs go to the branch-specific files until a MERGE or explicit branch switch.\n\n### MERGE\n\nIntegrate a completed branch back into the main flow.\n\n**Triggers**: `\u002Fgcc merge \u003Cbranch>`, \"merge results from...\", \"integrate the experiment\", \"branch X is done\"\n\n**Procedure**:\n1. Read the branch's `summary.md` and `commit.md` to understand outcomes\n2. Append a synthesis commit to main's `commit.md` summarizing:\n   - What was tried\n   - What was learned\n   - What is being integrated (or why the branch is being abandoned)\n3. Update `main.md`:\n   - Add milestone entry with branch results\n   - Remove from Active Branches\n   - Update objectives if applicable\n4. Update `metadata.yaml`: set branch status to `merged` or `abandoned`\n5. Log the merge in main's `log.md`\n\n### CONTEXT\n\nRetrieve historical memory at different resolution levels.\n\n**Triggers**: `\u002Fgcc context \u003Cflag>`, \"what did we do on...\", \"recover context\", \"show me the history\", \"where were we\"\n\n**Flags**:\n\n- `--branch [name]` — Read `summary.md` and latest commits for a specific branch (or current branch if no name). Provides high-level understanding of what happened and why.\n\n- `--log [n]` — Read last N entries (default 20) from the current branch's `log.md`. Provides fine-grained OTA traces for debugging or resuming interrupted work.\n\n- `--metadata` — Read `metadata.yaml` to recover project structure: file tree, dependencies, active branches, configuration.\n\n- `--full` — Read `main.md` for the complete project roadmap, all milestones, and active branches. Use for cross-session recovery or handoff to another agent.\n\nWhen no flag is specified, default to `--branch` for the current active branch.\n\n## OTA Logging\n\nThroughout all work (not just during explicit commands), maintain the OTA execution log:\n\n1. **Observation**: What was noticed or discovered\n2. **Thought**: Reasoning about what to do next\n3. **Action**: What action was taken\n\nAppend entries to the active branch's `log.md`. Keep a maximum of 50 entries; when exceeding, remove the oldest entries. Each entry includes a sequential ID, timestamp, and branch name.\n\nLog OTA entries at meaningful decision points — not every single action, but significant observations, strategy changes, and outcomes.\n\n## Cross-Session Recovery\n\nWhen starting a new session on an existing project with `.GCC\u002F`:\n\n1. Read `metadata.yaml` to understand project state and active branches\n2. Read `main.md` for the global roadmap and objectives\n3. Read the active branch's latest commits and log entries\n4. Resume work with full context of what was accomplished and what remains\n\n## Natural Language Mapping\n\n| User says | Command |\n|---|---|\n| \"save\u002Fcheckpoint\u002Fpersist this\" | COMMIT |\n| \"try a different approach\" | BRANCH |\n| \"that experiment worked, integrate it\" | MERGE |\n| \"where were we?\" \u002F \"what's the status?\" | CONTEXT --full |\n| \"what happened on branch X?\" | CONTEXT --branch X |\n| \"show recent activity\" | CONTEXT --log |\n| \"what files do we have?\" | CONTEXT --metadata |\n| \"enable\u002Fdisable auto-commits\" | Toggle `proactive_commits` in metadata.yaml |\n",{"name":5,"description":7},"main","d046d088ce5a79a083f0abc0fe1b7ded73bc5b1f","claude-config\u002Fskills\u002Fgcc","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent","https:\u002F\u002Fgithub.com\u002FSansar35","2026-05-10 16:04:53",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add Sansar35\u002Fclaude-agent --skill gcc",{"tool":35,"command":36},"bunx","bunx skills add Sansar35\u002Fclaude-agent --skill gcc",{"tool":38,"command":39},"pnpm","pnpm dlx skills add Sansar35\u002Fclaude-agent --skill gcc","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fgcc\u002FSKILL.md",true,[43,49,53],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},".skill-source.json","REFERENCE","参考文档",705,"https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fgcc\u002F.skill-source.json",{"path":50,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Ffile_formats.md",3212,"https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fgcc\u002Freferences\u002Ffile_formats.md",{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"scripts\u002Fgcc_init.sh","SCRIPT","脚本",1524,"https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fgcc\u002Fscripts\u002Fgcc_init.sh",[60,67,74,81,88,96],{"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},"01M72DVAN1JYEA302MT0C5MGD6","zustand-store-ts","Create Zustand stores following established patterns with proper TypeScript types and middleware.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzustand-store-ts\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},"01M72DV8J5NBRRM4RPDFRV95N7","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzod-validation-expert\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},"01M72DV5EMHW0BHP9BZ167MDCB","zinc-database","Access ZINC (230M+ purchasable compounds). Search by ZINC ID\u002FSMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzinc-database\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},"01M72DV216QY0E693ZPEVQ0DBS","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\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzarr-python\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":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M72DTXQREMCRKA8NHCVKHN4W","zapier-workflows","Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to \"run\" any process. Also handles Perplexity-based research and Google Sheets data tracking.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-workflows\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-workflows\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M72DTT17TBSJ0Y8J2XZ4C9TZ","zapier-make-patterns","No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points.  This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-make-patterns\u002FSKILL.md",[],[]]