SKILL-caamp
Central AI Agent Managed Packages - unified provider registry and package manager for AI coding agents Use when: (1) running caamp CLI commands, (2) calling its 276 API functions, (3) configuring @cleocode/caamp, (4) understanding its 180 type definitions, (5) working with its 8 classes, (6) user mentions "ai", "agent", "skills", "cli", "claude", (7) user mentions "@cleocode/caamp" or asks about its API.
Best use case
SKILL-caamp is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Central AI Agent Managed Packages - unified provider registry and package manager for AI coding agents Use when: (1) running caamp CLI commands, (2) calling its 276 API functions, (3) configuring @cleocode/caamp, (4) understanding its 180 type definitions, (5) working with its 8 classes, (6) user mentions "ai", "agent", "skills", "cli", "claude", (7) user mentions "@cleocode/caamp" or asks about its API.
Teams using SKILL-caamp should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/SKILL-caamp/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How SKILL-caamp Compares
| Feature / Agent | SKILL-caamp | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Central AI Agent Managed Packages - unified provider registry and package manager for AI coding agents Use when: (1) running caamp CLI commands, (2) calling its 276 API functions, (3) configuring @cleocode/caamp, (4) understanding its 180 type definitions, (5) working with its 8 classes, (6) user mentions "ai", "agent", "skills", "cli", "claude", (7) user mentions "@cleocode/caamp" or asks about its API.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# @cleocode/caamp
Central AI Agent Managed Packages - unified provider registry and package manager for AI coding agents
## Quick Start
```bash
npm install -D @cleocode/caamp
```
```bash
npx caamp --help
```
## API
| Function | Description |
|----------|-------------|
| `getPlatformPaths()` | Get OS-appropriate paths for CAAMP's global directories. |
| `getSystemInfo()` | Get a cached system information snapshot. |
| `_resetPlatformPathsCache()` | Invalidate the path and system info caches. Use in tests after mutating AGENTS_HOME env var. |
| `getPlatformLocations()` | Resolves platform-specific directory locations for the current OS. |
| `getAgentsHome()` | Returns the global agents home directory path. |
| `getProjectAgentsDir()` | Returns the project-local `.agents` directory path. |
| `resolveProjectPath()` | Resolves a relative path against a project directory. |
| `getCanonicalSkillsDir()` | Returns the canonical skills storage directory path. |
| `getLockFilePath()` | Returns the path to the CAAMP lock file. |
| `getAgentsMcpDir()` | Gets the MCP directory within the `.agents/` standard structure. |
| `getAgentsMcpServersPath()` | Gets the MCP servers.json path within the `.agents/` standard structure. |
| `getAgentsInstructFile()` | Gets the primary AGENTS.md instruction file path within `.agents/`. |
| `getAgentsConfigPath()` | Gets the config.toml path within the `.agents/` standard structure. |
| `getAgentsWikiDir()` | Gets the wiki directory within the `.agents/` standard structure. |
| `getAgentsSpecDir()` | Gets the spec directory within the `.agents/` standard structure. |
| ... | 261 more — see API reference |
## Configuration
```typescript
import type { DetectionConfig } from "@cleocode/caamp";
const config: Partial<DetectionConfig> = {
// Detection methods to try, in order.
methods: [],
// Binary name to look up on PATH (for `"binary"` method).
binary: "...",
// Directories to check for existence (for `"directory"` method).
directories: "...",
// macOS .app bundle name (for `"appBundle"` method).
appBundle: "...",
// Flatpak application ID (for `"flatpak"` method).
flatpakId: "...",
};
```
See [references/CONFIGURATION.md](references/CONFIGURATION.md) for full details.
## Gotchas
- `HookEvent` is deprecated: Use `CanonicalHookEvent` from `../hooks/types.js` for the normalized CAAMP taxonomy. This type remains for backward compatibility with registry.json's `capabilities.hooks.supported` string arrays.
- `CtSkillEntry` is deprecated: Use `SkillLibraryEntry` instead.
- `CtValidationResult` is deprecated: Use `SkillLibraryValidationResult` instead.
- `CtValidationIssue` is deprecated: Use `SkillLibraryValidationIssue` instead.
- `CtProfileDefinition` is deprecated: Use `SkillLibraryProfile` instead.
- `CtDispatchMatrix` is deprecated: Use `SkillLibraryDispatchMatrix` instead.
- `CtManifest` is deprecated: Use `SkillLibraryManifest` instead.
- `CtManifestSkill` is deprecated: Use `SkillLibraryManifestSkill` instead.
- `resolveProvidersRegistryPath()` throws: Error if `providers/registry.json` cannot be found within 8 parent levels
- `ensureProviderInstructionFile()` throws: Error if the provider ID is not found in the registry
- `ensureAllProviderInstructionFiles()` throws: Error if any provider ID is not found in the registry
- `resolveTierDir()` throws: `Error` when `tier='project'` and no `projectDir` is supplied
- `resolveDefaultTargetProviders()` throws: `PiRequiredError` when mode is `'force-pi'` and Pi is not installed.
- `resolveFormat()` throws: Error if format flags conflict
- `readConfig()` throws: If the file cannot be read or the format is unsupported
- `writeConfig()` throws: If the format is unsupported
- `removeConfig()` throws: If the format is unsupported
- `installMcpServer()` throws: `Error` when the provider has no MCP capability or no project-scoped config path is available.
- `requireMcpProvider()` throws: `LAFSCommandError` when the provider is unknown or has no MCP capability.
- `parseScope()` throws: `LAFSCommandError` when `raw` is set to an invalid value.
- `parseEnvAssignment()` throws: `LAFSCommandError` when the token is malformed.
- `fetchWithTimeout()` throws: `NetworkError` on timeout or network failure
- `ensureOkResponse()` throws: `NetworkError` when `response.ok` is `false`
- `requirePiHarness()` throws: `LAFSCommandError` when Pi is not installed.
- `parseScope()` throws: `LAFSCommandError` when `raw` is set to an invalid value.
- `recommendSkills()` throws: Error with `code` and `issues` properties when criteria are invalid
- `loadLibraryFromModule()` throws: If the module cannot be loaded or does not implement SkillLibrary
- `buildLibraryFromFiles()` throws: If skills.json is not found at the root
- `registerSkillLibraryFromPath()` throws: Error if the library cannot be loaded from the given path
## Key Types
- **`SkillLibraryEntry`** — A single skill entry in a library catalog.
- **`SkillLibraryValidationResult`** — Validation result from skill frontmatter validation.
- **`SkillLibraryValidationIssue`** — A single validation issue.
- **`SkillLibraryProfile`** — Profile definition for grouped skill installation.
- **`SkillLibraryDispatchMatrix`** — Dispatch matrix for task routing to skills.
- **`SkillLibraryManifestSkill`** — Skill entry within the library manifest.
- **`SkillLibraryManifest`** — Full manifest structure for a skill library.
- **`SkillLibrary`** — Standard interface for a skill library. Any directory or module providing skills must implement this contract. CAAMP uses it to discover, resolve, and install skills from any source.
- **`RegistryDetection`** — Raw detection configuration as stored in registry.json.
- **`ProviderPriority`** — Priority tier identifier stored in registry.json.
## References
- [references/CONFIGURATION.md](references/CONFIGURATION.md) — Full config options
- [references/API-REFERENCE.md](references/API-REFERENCE.md) — Signatures, parameters, examplesRelated Skills
signaldock-connect
Connect any AI agent to SignalDock for agent-to-agent messaging. Use when an agent needs to: (1) register on api.signaldock.io, (2) install the signaldock runtime CLI, (3) send/receive messages to other agents, (4) set up SSE real-time streaming, (5) poll for messages, (6) check inbox, or (7) connect to the SignalDock platform. Triggers on: "connect to signaldock", "register agent", "send message to agent", "agent messaging", "signaldock setup", "install signaldock", "agent-to-agent".
ct-validator
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.
ct-task-executor
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.
ct-stickynote
Quick ephemeral sticky notes for project-wide capture before formal classification
ct-spec-writer
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.
ct-skill-validator
Validates an existing skill folder against the full CLEO standard and ecosystem. Use when auditing skills for structural compliance, verifying a skill fits into the CLEO ecosystem and constitution, running quality A/B evals, or preparing a skill for distribution. Runs a 3-phase validation loop — structural, ecosystem fit, and quality eval — then presents all findings as an HTML report opened in the user's browser. Iterates until all required phases pass.
ct-skill-creator
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.
ct-research-agent
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.
ct-release-orchestrator
Orchestrates the full release pipeline: version bump, then changelog, then commit, then tag, then conditionally forks to artifact-publish and provenance based on release config. Parent protocol that composes ct-artifact-publisher and ct-provenance-keeper as sub-protocols: not every release publishes artifacts (source-only releases skip it), and artifact publishers delegate signing and attestation to provenance. Use when shipping a new version, running cleo release ship, or promoting a completed epic to released status.
ct-provenance-keeper
Generates in-toto v1 attestations, SLSA-level provenance records, SBOMs (CycloneDX or SPDX), and sigstore/cosign signatures for published artifacts. Invoked by ct-artifact-publisher as a delegation for signing and attestation. Records the full commit, then build, then artifact, then attestation, then registry chain in .cleo/releases.json and rejects publishes whose digest does not match the attestation. Triggers when artifact-publish reaches the provenance step or when a release needs SLSA L2+ attestation.
ct-orchestrator
Pipeline-aware orchestration skill for managing complex workflows through subagent delegation. Use 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", "pipeline management", or needs to manage complex workflows by delegating work to subagents while protecting the main context window. Enforces ORC-001 through ORC-009 constraints. Provider-neutral — works with any AI agent runtime.
ct-memory
Brain memory protocol with progressive disclosure for anti-hallucination and context recall