@cleocode/cleo 2026.3.4 → 2026.3.6

package/packages/ct-skills/skills.json

@@ -1,5 +1,246 @@
 {
-  "version": "2.0.0",
-  "generated": "2026-02-19T18:35:42Z",
-  "skills": [{"name":"ct-cleo","description":"CLEO task management protocol - core guidance for session, task, and workflow operations. Provides MCP-first workflow, CLI fallback, session protocol, task discovery patterns, RCSD lifecycle overview, and error handling. Load this skill for detailed CLEO protocol guidance.","version":"2.0.0","path":"skills/ct-cleo/SKILL.md","references":["skills/ct-cleo/references/session-protocol.md","skills/ct-cleo/references/rcsd-lifecycle.md","skills/ct-cleo/references/orchestrator-constraints.md","skills/ct-cleo/references/anti-patterns.md"],"core":true,"category":"core","tier":0,"protocol":null,"dependencies":[],"sharedResources":["task-system-integration"],"compatibility":["claude-code","gemini-cli","codex-cli"],"license":"MIT","metadata":{}},{"name":"ct-contribution","description":"Guided workflow for multi-agent consensus contributions. Use when user says \"/contribution\", \"contribution protocol\", \"submit contribution\", \"consensus workflow\", \"multi-agent decision\", \"create contribution\", \"contribution start\", \"contribution submit\", \"detect conflicts\", \"weighted consensus\", \"decision tracking\", \"conflict resolution\".","version":"1.0.0","path":"skills/ct-contribution/SKILL.md","references":[],"core":false,"category":"meta","tier":3,"protocol":"contribution","dependencies":[],"sharedResources":["subagent-protocol-base"],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-dev-workflow","description":"Development workflow orchestration for task-driven development with atomic commits, conventional commit messages, and systematic release processes. Enforces task traceability, branch discipline, smart test scope selection, and GitHub Actions integration. Use when committing code, creating releases, managing branches, or following contribution protocols. Triggers on commit operations, release preparation, or workflow compliance needs.","version":"3.0.0","path":"skills/ct-dev-workflow/SKILL.md","references":[],"core":false,"category":"specialist","tier":2,"protocol":"contribution","dependencies":[],"sharedResources":["subagent-protocol-base","task-system-integration"],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-docs-lookup","description":"This skill should be used when the user asks \"how do I configure [library]\", \"write code using [framework]\", \"what are the [library] methods\", \"show me [framework] examples\", or mentions libraries like React, Vue, Next.js, Prisma, Supabase, Express, Tailwind, Drizzle, Svelte. Triggers for library setup, configuration, API references, framework code examples, or version-specific docs (\"React 19\", \"Next.js 15\").","version":"1.0.0","path":"skills/ct-docs-lookup/SKILL.md","references":[],"core":false,"category":"composition","tier":3,"protocol":null,"dependencies":[],"sharedResources":[],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-docs-review","description":"This skill should be used when the user asks to \"review documentation\", \"check docs style\", \"review this markdown file\", \"check style guide compliance\", \"review PR documentation\", or needs documentation reviewed against the CLEO writing style guide. Supports both local file review and GitHub PR review modes with inline comments.","version":"1.0.0","path":"skills/ct-docs-review/SKILL.md","references":[],"core":false,"category":"composition","tier":3,"protocol":null,"dependencies":[],"sharedResources":[],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-docs-write","description":"This skill should be used when creating, editing, or reviewing documentation files (markdown, MDX, README, guides). Use when the user asks to \"write docs\", \"create documentation\", \"edit the README\", \"improve doc clarity\", \"make docs more readable\", \"follow the style guide\", or \"write user-facing content\". Applies CLEO's conversational, clear, and user-focused writing style.","version":"1.0.0","path":"skills/ct-docs-write/SKILL.md","references":[],"core":false,"category":"composition","tier":3,"protocol":null,"dependencies":[],"sharedResources":[],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-documentor","description":"Documentation creation, editing, and review with CLEO style guide compliance. Coordinates specialized skills for lookup, writing, and review. Use when creating or updating documentation files, consolidating scattered documentation, or validating documentation against style standards. Triggers on documentation tasks, doc update requests, or style guide compliance checks.","version":"3.0.0","path":"skills/ct-documentor/SKILL.md","references":[],"core":false,"category":"specialist","tier":3,"protocol":null,"dependencies":["ct-docs-lookup","ct-docs-write","ct-docs-review"],"sharedResources":["subagent-protocol-base","task-system-integration"],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-epic-architect","description":"Epic planning and task decomposition for breaking down large initiatives into atomic, executable tasks. Provides dependency analysis, wave-based parallel execution planning, hierarchy management, and research linking. Use when creating epics, decomposing initiatives into task trees, planning parallel workflows, or analyzing task dependencies. Triggers on epic creation, task decomposition requests, or planning phase work.","version":"3.0.0","path":"skills/ct-epic-architect/SKILL.md","references":["skills/ct-epic-architect/references/bug-epic-example.md","skills/ct-epic-architect/references/commands.md","skills/ct-epic-architect/references/feature-epic-example.md","skills/ct-epic-architect/references/migration-epic-example.md","skills/ct-epic-architect/references/output-format.md","skills/ct-epic-architect/references/patterns.md","skills/ct-epic-architect/references/refactor-epic-example.md","skills/ct-epic-architect/references/research-epic-example.md","skills/ct-epic-architect/references/shell-escaping.md","skills/ct-epic-architect/references/skill-aware-execution.md"],"core":false,"category":"recommended","tier":1,"protocol":"decomposition","dependencies":[],"sharedResources":["subagent-protocol-base","task-system-integration"],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-gitbook","description":"Comprehensive guide for the modern GitBook platform including Docs Sites publishing, @gitbook/api TypeScript SDK, Git Sync with GitHub App, Change Requests, Site Sections, adaptive content, visitor authentication (Auth0/Okta/Azure AD), LLM-ready docs (llms.txt, MCP server), OpenAPI integration, content blocks, custom domains, SSO/SAML, SEO optimization, and migration from MkDocs/Docusaurus. Use when creating, managing, or automating GitBook documentation sites, configuring Git Sync, working with the GitBook API, setting up authentication, or migrating documentation to GitBook.","version":"1.0.0","path":"skills/ct-gitbook/SKILL.md","references":["skills/ct-gitbook/references/api-sdk.md","skills/ct-gitbook/references/auth-sso.md","skills/ct-gitbook/references/change-requests.md","skills/ct-gitbook/references/content-blocks.md","skills/ct-gitbook/references/docs-sites.md","skills/ct-gitbook/references/git-sync.md","skills/ct-gitbook/references/llm-ready.md","skills/ct-gitbook/references/migration.md"],"core":false,"category":"meta","tier":3,"protocol":null,"dependencies":[],"sharedResources":[],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-library-implementer-bash","description":"Bash library development with focus on creating well-structured lib/*.sh files following shell best practices. Implements reusable functions, utility modules, and shared helpers with proper documentation, error handling, and dependency management. Use when creating new lib/ modules, implementing shared functions, or adding utility libraries. Triggers on library implementation tasks, bash module creation, or utility function needs.","version":"2.0.0","path":"skills/ct-library-implementer-bash/SKILL.md","references":[],"core":false,"category":"specialist","tier":2,"protocol":"implementation","dependencies":[],"sharedResources":["subagent-protocol-base","task-system-integration"],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-orchestrator","description":"This skill should be used when the user asks to \"orchestrate\", \"orchestrator mode\", \"run as orchestrator\", \"delegate to subagents\", \"coordinate agents\", \"spawn subagents\", \"multi-agent workflow\", \"context-protected workflow\", \"agent farm\", \"HITL orchestration\", or needs to manage complex workflows by delegating work to subagents while protecting the main context window. Enforces ORC-001 through ORC-009 constraints.","version":"3.0.0","path":"skills/ct-orchestrator/SKILL.md","references":["skills/ct-orchestrator/references/autonomous-operation.md","skills/ct-orchestrator/references/lifecycle-gates.md","skills/ct-orchestrator/references/orchestrator-compliance.md","skills/ct-orchestrator/references/orchestrator-handoffs.md","skills/ct-orchestrator/references/orchestrator-patterns.md","skills/ct-orchestrator/references/orchestrator-recovery.md","skills/ct-orchestrator/references/orchestrator-spawning.md","skills/ct-orchestrator/references/orchestrator-tokens.md","skills/ct-orchestrator/references/SUBAGENT-PROTOCOL-BLOCK.md"],"core":true,"category":"core","tier":0,"protocol":"agent-protocol","dependencies":[],"sharedResources":["subagent-protocol-base","task-system-integration"],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-research-agent","description":"Multi-source research and investigation combining web search, documentation lookup via Context7, and codebase analysis. Synthesizes findings into actionable recommendations with proper citation and task traceability. Use when conducting research, investigating best practices, gathering technical information, or analyzing existing implementations. Triggers on research tasks, investigation needs, or information discovery requests.","version":"2.0.0","path":"skills/ct-research-agent/SKILL.md","references":[],"core":false,"category":"recommended","tier":2,"protocol":"research","dependencies":[],"sharedResources":["subagent-protocol-base","task-system-integration"],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-skill-creator","description":"Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.","version":"1.0.0","path":"skills/ct-skill-creator/SKILL.md","references":["skills/ct-skill-creator/references/output-patterns.md","skills/ct-skill-creator/references/workflows.md"],"core":false,"category":"meta","tier":3,"protocol":null,"dependencies":[],"sharedResources":[],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-skill-lookup","description":"This skill should be used when the user asks to \"find me a skill\", \"search for skills\", \"what skills are available\", \"get skill XYZ\", \"install a skill\", \"extend Claude's capabilities with skills\", or mentions Agent Skills, prompts.chat, SkillsMP, marketplace, external skills, or reusable AI agent components.","version":"1.1.0","path":"skills/ct-skill-lookup/SKILL.md","references":[],"core":false,"category":"meta","tier":3,"protocol":null,"dependencies":[],"sharedResources":[],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-spec-writer","description":"Technical specification writing using RFC 2119 language for clear, unambiguous requirements. Creates protocol specifications, technical requirements, API specifications, and architecture documents with testable requirements and compliance criteria. Use when writing specifications, defining protocols, documenting requirements, or creating API contracts. Triggers on specification tasks, protocol definition needs, or requirement documentation.","version":"2.0.0","path":"skills/ct-spec-writer/SKILL.md","references":[],"core":false,"category":"recommended","tier":2,"protocol":"specification","dependencies":[],"sharedResources":["subagent-protocol-base","task-system-integration"],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-task-executor","description":"General implementation task execution for completing assigned CLEO tasks by following instructions and producing concrete deliverables. Handles coding, configuration, documentation work with quality verification against acceptance criteria and progress reporting. Use when executing implementation tasks, completing assigned work, or producing task deliverables. Triggers on implementation tasks, general execution needs, or task completion work.","version":"2.0.0","path":"skills/ct-task-executor/SKILL.md","references":[],"core":true,"category":"core","tier":2,"protocol":"implementation","dependencies":[],"sharedResources":["subagent-protocol-base","task-system-integration"],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-test-writer-bats","description":"BATS (Bash Automated Testing System) test creation for comprehensive integration and unit testing. Creates idempotent tests with happy path, error handling, and edge case coverage. Includes fixture creation and JSON output validation. Use when writing tests, creating test suites, adding test coverage, or validating bash implementations. Triggers on test writing tasks, test coverage needs, or BATS test creation.","version":"2.0.0","path":"skills/ct-test-writer-bats/SKILL.md","references":[],"core":false,"category":"specialist","tier":2,"protocol":"testing","dependencies":[],"sharedResources":["subagent-protocol-base","task-system-integration"],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"ct-validator","description":"Compliance validation for verifying systems, documents, or code against requirements, schemas, or standards. Performs schema validation, code compliance checks, document validation, and protocol compliance verification with detailed pass/fail reporting. Use when validating compliance, checking schemas, verifying code standards, or auditing protocol implementations. Triggers on validation tasks, compliance checks, or quality verification needs.","version":"2.0.0","path":"skills/ct-validator/SKILL.md","references":[],"core":false,"category":"recommended","tier":2,"protocol":"validation","dependencies":[],"sharedResources":["subagent-protocol-base","task-system-integration"],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}},{"name":"railway-platform","description":"Deploy and manage applications on Railway platform. Use for creating projects, deploying services (Node.js, Python, Go, Docker, static sites), managing databases (Postgres, Redis, MySQL, MongoDB), configuring domains, environment variables, volumes, cron jobs, and networking. Integrates with GitHub for auto-deploys. Supports monorepos, private networking, and Railway Metal infrastructure.","version":"1.0.0","path":"skills/railway-platform/SKILL.md","references":["skills/railway-platform/references/01-getting-started.md","skills/railway-platform/references/02-projects.md","skills/railway-platform/references/03-services.md","skills/railway-platform/references/04-deployments.md","skills/railway-platform/references/05-databases.md","skills/railway-platform/references/06-environments.md","skills/railway-platform/references/07-domains.md","skills/railway-platform/references/08-volumes.md","skills/railway-platform/references/09-networking.md","skills/railway-platform/references/10-cron.md","skills/railway-platform/references/11-functions.md","skills/railway-platform/references/12-monorepo.md","skills/railway-platform/references/13-troubleshooting.md","skills/railway-platform/references/14-railway-metal.md"],"core":false,"category":"specialist","tier":3,"protocol":null,"dependencies":[],"sharedResources":[],"compatibility":["claude-code","cursor","windsurf","gemini-cli"],"license":"MIT","metadata":{}}]
+  "version": "2.1.0",
+  "generated": "2026-03-02T05:45:00Z",
+  "skills": [
+    {
+      "name": "ct-cleo",
+      "description": "CLEO task management protocol - core guidance for session, task, and workflow operations. Provides MCP-first workflow, CLI fallback, session protocol, task discovery patterns, RCSD lifecycle overview, and error handling. Load this skill for detailed CLEO protocol guidance.",
+      "version": "2.0.0",
+      "path": "skills/ct-cleo/SKILL.md",
+      "references": ["skills/ct-cleo/references/session-protocol.md", "skills/ct-cleo/references/rcsd-lifecycle.md", "skills/ct-cleo/references/anti-patterns.md"],
+      "core": true,
+      "category": "core",
+      "tier": 0,
+      "protocol": null,
+      "dependencies": [],
+      "sharedResources": ["task-system-integration"],
+      "compatibility": ["claude-code", "gemini-cli", "codex-cli"],
+      "license": "MIT",
+      "metadata": {}
+    },
+    {
+      "name": "ct-orchestrator",
+      "description": "Pipeline-aware orchestration for multi-agent workflows. Manages RCASD-IVTR+C pipeline progression for epics, delegates all work to subagents via provider-neutral spawning, enforces lifecycle gates before spawning, and reads only manifests. Use when orchestrating complex workflows, delegating to subagents, or managing epic pipeline progression.",
+      "version": "4.0.0",
+      "path": "skills/ct-orchestrator/SKILL.md",
+      "references": ["skills/ct-orchestrator/references/autonomous-operation.md", "skills/ct-orchestrator/references/lifecycle-gates.md", "skills/ct-orchestrator/references/orchestrator-compliance.md", "skills/ct-orchestrator/references/orchestrator-handoffs.md", "skills/ct-orchestrator/references/orchestrator-patterns.md", "skills/ct-orchestrator/references/orchestrator-recovery.md", "skills/ct-orchestrator/references/orchestrator-spawning.md", "skills/ct-orchestrator/references/orchestrator-tokens.md", "skills/ct-orchestrator/references/SUBAGENT-PROTOCOL-BLOCK.md"],
+      "core": true,
+      "category": "core",
+      "tier": 0,
+      "protocol": "agent-protocol",
+      "dependencies": [],
+      "sharedResources": ["subagent-protocol-base", "task-system-integration"],
+      "compatibility": ["claude-code", "cursor", "windsurf", "gemini-cli"],
+      "license": "MIT",
+      "metadata": {}
+    },
+    {
+      "name": "ct-task-executor",
+      "description": "General implementation task execution for completing assigned CLEO tasks by following instructions and producing concrete deliverables. Handles coding, configuration, documentation work with quality verification against acceptance criteria and progress reporting.",
+      "version": "2.0.0",
+      "path": "skills/ct-task-executor/SKILL.md",
+      "references": [],
+      "core": true,
+      "category": "core",
+      "tier": 0,
+      "protocol": "implementation",
+      "dependencies": [],
+      "sharedResources": ["subagent-protocol-base", "task-system-integration"],
+      "compatibility": ["claude-code", "cursor", "windsurf", "gemini-cli"],
+      "license": "MIT",
+      "metadata": {}
+    },
+    {
+      "name": "ct-epic-architect",
+      "description": "Epic planning and task decomposition for breaking down large initiatives into atomic, executable tasks. Provides dependency analysis, wave-based parallel execution planning, hierarchy management, and research linking.",
+      "version": "3.0.0",
+      "path": "skills/ct-epic-architect/SKILL.md",
+      "references": ["skills/ct-epic-architect/references/bug-epic-example.md", "skills/ct-epic-architect/references/commands.md", "skills/ct-epic-architect/references/feature-epic-example.md", "skills/ct-epic-architect/references/migration-epic-example.md", "skills/ct-epic-architect/references/output-format.md", "skills/ct-epic-architect/references/patterns.md", "skills/ct-epic-architect/references/refactor-epic-example.md", "skills/ct-epic-architect/references/research-epic-example.md", "skills/ct-epic-architect/references/shell-escaping.md", "skills/ct-epic-architect/references/skill-aware-execution.md"],
+      "core": false,
+      "category": "recommended",
+      "tier": 1,
+      "protocol": "decomposition",
+      "dependencies": [],
+      "sharedResources": ["subagent-protocol-base", "task-system-integration"],
+      "compatibility": ["claude-code", "cursor", "windsurf", "gemini-cli"],
+      "license": "MIT",
+      "metadata": {}
+    },
+    {
+      "name": "ct-research-agent",
+      "description": "Multi-source research and investigation combining web search, documentation lookup via Context7, and codebase analysis. Synthesizes findings into actionable recommendations with proper citation and task traceability.",
+      "version": "2.0.0",
+      "path": "skills/ct-research-agent/SKILL.md",
+      "references": [],
+      "core": false,
+      "category": "recommended",
+      "tier": 1,
+      "protocol": "research",
+      "dependencies": [],
+      "sharedResources": ["subagent-protocol-base", "task-system-integration"],
+      "compatibility": ["claude-code", "cursor", "windsurf", "gemini-cli"],
+      "license": "MIT",
+      "metadata": {}
+    },
+    {
+      "name": "ct-spec-writer",
+      "description": "Technical specification writing using RFC 2119 language for clear, unambiguous requirements. Creates protocol specifications, technical requirements, API specifications, and architecture documents with testable requirements and compliance criteria.",
+      "version": "2.0.0",
+      "path": "skills/ct-spec-writer/SKILL.md",
+      "references": [],
+      "core": false,
+      "category": "recommended",
+      "tier": 1,
+      "protocol": "specification",
+      "dependencies": [],
+      "sharedResources": ["subagent-protocol-base", "task-system-integration"],
+      "compatibility": ["claude-code", "cursor", "windsurf", "gemini-cli"],
+      "license": "MIT",
+      "metadata": {}
+    },
+    {
+      "name": "ct-validator",
+      "description": "Compliance validation for verifying systems, documents, or code against requirements, schemas, or standards. Performs schema validation, code compliance checks, document validation, and protocol compliance verification with detailed pass/fail reporting.",
+      "version": "2.0.0",
+      "path": "skills/ct-validator/SKILL.md",
+      "references": [],
+      "core": false,
+      "category": "recommended",
+      "tier": 1,
+      "protocol": "validation",
+      "dependencies": [],
+      "sharedResources": ["subagent-protocol-base", "task-system-integration"],
+      "compatibility": ["claude-code", "cursor", "windsurf", "gemini-cli"],
+      "license": "MIT",
+      "metadata": {}
+    },
+    {
+      "name": "ct-dev-workflow",
+      "description": "Development workflow orchestration for task-driven development with atomic commits, conventional commit messages, and systematic release processes. Enforces task traceability, branch discipline, smart test scope selection, and GitHub Actions integration.",
+      "version": "3.0.0",
+      "path": "skills/ct-dev-workflow/SKILL.md",
+      "references": [],
+      "core": false,
+      "category": "specialist",
+      "tier": 2,
+      "protocol": "contribution",
+      "dependencies": [],
+      "sharedResources": ["subagent-protocol-base", "task-system-integration"],
+      "compatibility": ["claude-code", "cursor", "windsurf", "gemini-cli"],
+      "license": "MIT",
+      "metadata": {}
+    },
+    {
+      "name": "ct-documentor",
+      "description": "Documentation creation, editing, and review with CLEO style guide compliance. Coordinates specialized skills for lookup, writing, and review.",
+      "version": "3.0.0",
+      "path": "skills/ct-documentor/SKILL.md",
+      "references": [],
+      "core": false,
+      "category": "specialist",
+      "tier": 2,
+      "protocol": null,
+      "dependencies": ["ct-docs-lookup", "ct-docs-write", "ct-docs-review"],
+      "sharedResources": ["subagent-protocol-base", "task-system-integration"],
+      "compatibility": ["claude-code", "cursor", "windsurf", "gemini-cli"],
+      "license": "MIT",
+      "metadata": {}
+    },
+    {
+      "name": "ct-docs-lookup",
+      "description": "Context7 library documentation lookup. Use when configuring libraries, writing framework code, or looking up API references and version-specific docs.",
+      "version": "1.0.0",
+      "path": "skills/ct-docs-lookup/SKILL.md",
+      "references": [],
+      "core": false,
+      "category": "composition",
+      "tier": 2,
+      "protocol": null,
+      "dependencies": [],
+      "sharedResources": [],
+      "compatibility": ["claude-code", "cursor", "windsurf", "gemini-cli"],
+      "license": "MIT",
+      "metadata": {}
+    },
+    {
+      "name": "ct-docs-write",
+      "description": "Documentation writing with CLEO's conversational, clear, user-focused style. Use when creating, editing, or improving documentation files.",
+      "version": "1.0.0",
+      "path": "skills/ct-docs-write/SKILL.md",
+      "references": [],
+      "core": false,
+      "category": "composition",
+      "tier": 2,
+      "protocol": null,
+      "dependencies": [],
+      "sharedResources": [],
+      "compatibility": ["claude-code", "cursor", "windsurf", "gemini-cli"],
+      "license": "MIT",
+      "metadata": {}
+    },
+    {
+      "name": "ct-docs-review",
+      "description": "Documentation review against CLEO writing style guide. Supports local file review and GitHub PR review modes.",
+      "version": "1.0.0",
+      "path": "skills/ct-docs-review/SKILL.md",
+      "references": [],
+      "core": false,
+      "category": "composition",
+      "tier": 2,
+      "protocol": null,
+      "dependencies": [],
+      "sharedResources": [],
+      "compatibility": ["claude-code", "cursor", "windsurf", "gemini-cli"],
+      "license": "MIT",
+      "metadata": {}
+    },
+    {
+      "name": "ct-contribution",
+      "description": "Guided workflow for multi-agent consensus contributions including conflict detection, weighted consensus, and decision tracking.",
+      "version": "1.0.0",
+      "path": "skills/ct-contribution/SKILL.md",
+      "references": [],
+      "core": false,
+      "category": "specialist",
+      "tier": 2,
+      "protocol": "contribution",
+      "dependencies": [],
+      "sharedResources": ["subagent-protocol-base"],
+      "compatibility": ["claude-code", "cursor", "windsurf", "gemini-cli"],
+      "license": "MIT",
+      "metadata": {}
+    },
+    {
+      "name": "ct-grade",
+      "description": "Session grading for agent behavioral analysis. Evaluates session quality against CLEO protocol using a 5-dimension rubric to produce scores and diagnostic flags.",
+      "version": "1.0.0",
+      "path": "skills/ct-grade/SKILL.md",
+      "references": [],
+      "core": false,
+      "category": "specialist",
+      "tier": 2,
+      "protocol": null,
+      "dependencies": [],
+      "sharedResources": [],
+      "compatibility": ["claude-code", "cursor", "windsurf", "gemini-cli"],
+      "license": "MIT",
+      "metadata": {}
+    },
+    {
+      "name": "ct-skill-creator",
+      "description": "Guide for creating effective skills. Use when creating a new skill or updating an existing skill that extends agent capabilities.",
+      "version": "1.0.0",
+      "path": "skills/ct-skill-creator/SKILL.md",
+      "references": ["skills/ct-skill-creator/references/output-patterns.md", "skills/ct-skill-creator/references/workflows.md"],
+      "core": false,
+      "category": "meta",
+      "tier": 3,
+      "protocol": null,
+      "dependencies": [],
+      "sharedResources": [],
+      "compatibility": ["claude-code", "cursor", "windsurf", "gemini-cli"],
+      "license": "MIT",
+      "metadata": {}
+    }
+  ]
 }

package/templates/CLEO-INJECTION.md

@@ -72,6 +72,30 @@ For advanced session ops (find, suspend, resume, debrief, decisions): see `.cleo
 
 **Budget note**: `session list` defaults to 10 results (~500-2000 tokens). Prefer `session find` for discovery (~200-400 tokens).
 
+## Memory Protocol
+
+CLEO includes a native BRAIN memory system. Use the 3-layer retrieval pattern for token-efficient access:
+
+| Step | Operation | Gateway | ~Tokens | Purpose |
+|------|-----------|---------|---------|---------|
+| 1 | `memory brain.search` | query | 50/hit | Search index (IDs + titles) |
+| 2 | `memory brain.timeline` | query | 200-500 | Context around an anchor ID |
+| 3 | `memory brain.fetch` | query | 500/entry | Full details for filtered IDs |
+| Save | `memory brain.observe` | mutate | — | Save observation to brain.db |
+
+**Workflow**: Search first (cheap) → filter interesting IDs → fetch only what you need.
+
+**Example**:
+```
+cleo_query memory brain.search {query: "authentication"}
+cleo_query memory brain.fetch {ids: ["O-abc123"]}
+cleo_mutate memory brain.observe {text: "Found auth uses JWT", title: "Auth discovery"}
+```
+
+**Anti-patterns:**
+- Fetching all entries without searching first (expensive)
+- Skipping brain.search and going straight to brain.fetch
+
 ## Escalation
 
 For deeper guidance beyond this minimal protocol:

package/packages/ct-skills/protocols/agent-protocol.md

@@ -1,260 +0,0 @@
-# CLEO Agent Protocol
-
-**Version**: 1.0.0
-**Type**: Agent Reference
-**Audience**: LLM agents operating CLEO CLI
-
----
-
-## Commands
-
-| Command | Purpose | Output Key |
-|---------|---------|------------|
-| ct find "query" | Search tasks | .tasks[].id |
-| ct find --id 142 | ID search | .tasks[].id |
-| ct show T### | Task details | .task |
-| ct add "Title" | Create task | .task.id |
-| ct add "Title" --parent T### | Create subtask | .task.id |
-| ct done T### | Complete task | .completedAt |
-| ct update T### --status active | Update status | .task |
-| ct start T### | Start working on task | .task |
-| ct current | Current task | .task |
-| ct next | Suggest task | .recommendation.taskId |
-| ct session list | List sessions | .sessions[] |
-| ct session start --scope epic:T### --auto-start --name "..." | Start session | .session.id |
-| ct session end --note "..." | End session | .session |
-| ct session resume ID | Resume session | .session |
-| ct session status | Current session | .session |
-| ct dash | Project overview | .summary |
-| ct context | Context usage | .context |
-| ct archive | Archive done tasks | .archived[] |
-| ct exists T### | Check existence | .exists |
-| ct list --parent T### | Children only | .tasks[] |
-
-## Session Sequence
-
-1. `ct session list` - Check existing sessions
-2. `ct session start --scope epic:T### --auto-start --name "Name"` OR `ct session resume ID`
-3. `ct start T###` - Start working on task
-4. Execute work on current task
-5. `ct complete T###` - Mark done
-6. `ct start T###` - Next task (or `ct next`)
-7. `ct archive` - Clean up done tasks
-8. `ct session end --note "Progress summary"` - ALWAYS end
-
-**CRITICAL**: Session start requires BOTH `--scope` AND `--auto-start` (or `--start T###`)
-
-## Exit Codes
-
-### General (0-8)
-
-| Code | Constant | Recoverable | Recovery |
-|------|----------|:-----------:|----------|
-| 0 | SUCCESS | - | - |
-| 1 | GENERAL_ERROR | Yes | Check error.message |
-| 2 | INVALID_INPUT | Yes | Fix arguments |
-| 3 | FILE_ERROR | No | Check permissions |
-| 4 | NOT_FOUND | Yes | `ct find` to locate ID |
-| 5 | DEPENDENCY_ERROR | No | Install missing tool |
-| 6 | VALIDATION_ERROR | Yes | Check field lengths, escape \$ |
-| 7 | LOCK_TIMEOUT | Yes | Retry after delay |
-| 8 | CONFIG_ERROR | Yes | `ct doctor` to diagnose |
-
-### Hierarchy (10-19)
-
-| Code | Constant | Recoverable | Recovery |
-|------|----------|:-----------:|----------|
-| 10 | PARENT_NOT_FOUND | Yes | `ct exists <parentId>` first |
-| 11 | DEPTH_EXCEEDED | Yes | Max 3 levels (epic->task->subtask) |
-| 12 | SIBLING_LIMIT | Yes | Check parent children count |
-| 13 | INVALID_PARENT_TYPE | Yes | Subtasks cannot have children |
-| 14 | CIRCULAR_REFERENCE | No | Check dependency graph |
-| 15 | ORPHAN_DETECTED | Yes | Verify parent exists |
-| 16 | HAS_CHILDREN | Yes | Delete children first or use --cascade |
-| 17 | TASK_COMPLETED | Yes | Use `ct archive` instead |
-| 18 | CASCADE_FAILED | No | Manual intervention required |
-| 19 | HAS_DEPENDENTS | Yes | Use --orphan flag |
-
-### Concurrency (20-22)
-
-| Code | Constant | Recoverable | Recovery |
-|------|----------|:-----------:|----------|
-| 20 | CHECKSUM_MISMATCH | Yes | Retry (file changed externally) |
-| 21 | CONCURRENT_MODIFICATION | Yes | Retry after delay |
-| 22 | ID_COLLISION | Yes | Retry (regenerates ID) |
-
-### Session (30-39)
-
-| Code | Constant | Recoverable | Recovery |
-|------|----------|:-----------:|----------|
-| 30 | SESSION_EXISTS | Yes | `ct session list`, resume existing |
-| 31 | SESSION_NOT_FOUND | Yes | `ct session list` for valid IDs |
-| 32 | SCOPE_CONFLICT | Yes | End conflicting session first |
-| 33 | SCOPE_INVALID | Yes | Verify epic exists |
-| 34 | TASK_NOT_IN_SCOPE | Yes | End session, restart with correct scope |
-| 35 | TASK_CLAIMED | Yes | `ct next` for unclaimed task |
-| 36 | SESSION_REQUIRED | Yes | `ct session start` first |
-| 37 | SESSION_CLOSE_BLOCKED | No | Complete pending tasks first |
-| 38 | START_REQUIRED | Yes | `ct start T###` |
-| 39 | NOTES_REQUIRED | Yes | Add `--note "..."` |
-
-### Verification (40-47)
-
-| Code | Constant | Recoverable | Recovery |
-|------|----------|:-----------:|----------|
-| 40 | VERIFICATION_INIT_FAILED | Yes | Check task state |
-| 41 | GATE_UPDATE_FAILED | Yes | Retry |
-| 42 | INVALID_GATE | Yes | Check valid gate names |
-| 43 | INVALID_AGENT | Yes | Check valid agent names |
-| 44 | MAX_ROUNDS_EXCEEDED | Yes | Review implementation |
-| 45 | GATE_DEPENDENCY | Yes | Complete prerequisite gate |
-| 46 | VERIFICATION_LOCKED | No | Requires manual unlock |
-| 47 | ROUND_MISMATCH | Yes | Sync round number |
-
-### Context Safeguard (50-54)
-
-| Code | Constant | Action |
-|------|----------|--------|
-| 50 | CONTEXT_WARNING | Continue, reduce output |
-| 51 | CONTEXT_CAUTION | Prioritize completion |
-| 52 | CONTEXT_CRITICAL | Run `ct safestop` |
-| 53 | CONTEXT_EMERGENCY | Immediate `ct safestop` |
-| 54 | CONTEXT_STALE | Re-check context state |
-
-### Protocol/Orchestrator (60-67)
-
-| Code | Constant | Recoverable | Recovery |
-|------|----------|:-----------:|----------|
-| 60 | PROTOCOL_MISSING | Yes | Add protocol injection block |
-| 61 | INVALID_RETURN_MESSAGE | Yes | Fix return format |
-| 62 | MANIFEST_ENTRY_MISSING | Yes | Append MANIFEST.jsonl entry |
-| 63 | SPAWN_VALIDATION_FAILED | Yes | Fix spawn parameters |
-| 64 | AUTONOMOUS_BOUNDARY | No | Requires HITL decision |
-| 65 | HANDOFF_REQUIRED | No | Generate handoff document |
-| 66 | RESUME_FAILED | Yes | Check session/handoff validity |
-| 67 | CONCURRENT_SESSION | Yes | End other session first |
-
-**NOTE**: Codes 60-67 have a known collision between protocol validation (RCSD) and orchestrator functions. They are isolated by usage context.
-
-### Nexus (70-79)
-
-| Code | Constant | Recoverable | Recovery |
-|------|----------|:-----------:|----------|
-| 70 | NEXUS_NOT_INITIALIZED | Yes | Run nexus init |
-| 71 | NEXUS_PROJECT_NOT_FOUND | Yes | Register project first |
-| 72 | NEXUS_PERMISSION_DENIED | No | Check permissions |
-| 73 | NEXUS_INVALID_SYNTAX | Yes | Fix query syntax |
-| 74 | NEXUS_SYNC_FAILED | Yes | Retry sync |
-| 75 | NEXUS_REGISTRY_CORRUPT | No | Manual repair needed |
-| 76 | NEXUS_PROJECT_EXISTS | Yes | Already registered |
-| 77 | NEXUS_QUERY_FAILED | Yes | Retry or refine query |
-| 78 | NEXUS_GRAPH_ERROR | Yes | Retry |
-| 79 | NEXUS_RESERVED | - | Reserved |
-
-### Lifecycle (80-84)
-
-| Code | Constant | Recoverable | Recovery |
-|------|----------|:-----------:|----------|
-| 80 | LIFECYCLE_GATE_FAILED | Yes | Complete prerequisite RCSD stages |
-| 81 | AUDIT_MISSING | Yes | Add required audit fields |
-| 82 | CIRCULAR_VALIDATION | No | Assign different validator |
-| 83 | LIFECYCLE_TRANSITION_INVALID | No | Follow RCSD->IVTR sequence |
-| 84 | PROVENANCE_REQUIRED | Yes | Add provenance fields |
-
-### Special (100+) - NOT errors
-
-| Code | Constant | Meaning | Agent Action |
-|------|----------|---------|-------------|
-| 100 | NO_DATA | Query returned empty | Do NOT retry. No matching data. |
-| 101 | ALREADY_EXISTS | Resource exists | Treat as success. |
-| 102 | NO_CHANGE | No-op (idempotent) | Treat as success. Do NOT retry. |
-
-## Error Recovery Decision Trees
-
-### Exit 34 (TASK_NOT_IN_SCOPE)
-```
-1. ct session status           -> get current scope
-2. ct show T###                -> get task's parent epic
-3. ct session end --note "Scope mismatch"
-4. ct session start --scope epic:<parentId> --auto-start --name "Name"
-5. RETRY original command
-```
-
-### Exit 35 (TASK_CLAIMED)
-```
-1. ct next                     -> get unclaimed task suggestion
-2. ct start <suggested>        -> switch to unclaimed task
-```
-
-### Exit 38 (START_REQUIRED)
-```
-1. ct start T###               -> start working on target task
-2. RETRY original command
-```
-
-### Exit 100 (NO_DATA) with session start
-```
-1. ct session list             -> check existing sessions
-2. IF sessions exist: ct session resume <id>
-3. ELSE: ct session start --scope epic:T### --auto-start --name "Name"
-```
-
-## State Transitions
-
-| From | To | Via Command |
-|------|----|-------------|
-| pending | active | `ct start T###` |
-| pending | blocked | `ct update T### --status blocked` |
-| pending | done | `ct complete T###` |
-| active | pending | `ct start <other>` (stops current) |
-| active | blocked | `ct update T### --status blocked` |
-| active | done | `ct complete T###` |
-| blocked | pending | `ct update T### --status pending` |
-| blocked | active | `ct start T###` |
-| done | active | `ct reopen T###` |
-
-Valid statuses: `pending` | `active` | `blocked` | `done`
-
-## JSON Output Format
-
-All commands return:
-```json
-{"_meta":{"command":"...","timestamp":"...","version":"..."},"success":true,...}
-```
-
-Errors return:
-```json
-{"_meta":{...},"success":false,"error":{"code":"E_...","exitCode":N,"message":"...","fix":"ct ...","alternatives":[{"action":"...","command":"ct ..."}]}}
-```
-
-**Parsing patterns**:
-- Success check: `jq '.success'`
-- Error code: `jq '.error.code'`
-- Fix command: `jq -r '.error.fix'`
-- Results field: `jq -r '._meta.resultsField'` -> tells which key has primary data
-
-## Constraints
-
-| Rule | Value |
-|------|-------|
-| Hierarchy depth | Max 3 (epic -> task -> subtask) |
-| Siblings per parent | Max configurable (default varies) |
-| Valid statuses | pending, active, blocked, done |
-| ID format | T### (sequential, immutable) |
-| Shell escaping | Escape `$` as `\$` in arguments |
-| Context efficiency | Use `find` (not `list`) for discovery |
-| Discovery pattern | `find` -> `show` for details |
-
-## Subagent Protocol
-
-1. `ct start T###` - Start task before work
-2. Execute implementation work
-3. Write output file to designated path
-4. Append ONE line to `MANIFEST.jsonl` (compact JSON, no pretty-print)
-5. `ct complete T###` - Mark task done
-6. Return summary message ONLY (no file content)
-
-**Manifest entry format**:
-```json
-{"id":"T###-slug","file":"path","title":"...","date":"YYYY-MM-DD","status":"complete","agent_type":"...","topics":[],"key_findings":[],"actionable":true,"needs_followup":[],"linked_tasks":["T###"]}
-```