Skip to content

gotalab/cc-sdd / .agents/skills/cc-sdd-new-agent

cc-sdd-new-agent

Verified

Add or extend coding-agent support in cc-sdd by executing the SOP in docs/cc-sdd/sop-new-agent.md end-to-end. Use when introducing a new agent, adding a subagent-capable variant, or evaluating migration of an existing supported agent to skills-based templates.

FileKindSize
SKILL.mdskill md4.5 KB
agents/openai.yamlconfig351 B
references/plan-output-checklist.mdmarkdown1.2 KB
references/skills-migration.mdmarkdown2.3 KB

references/skills-migration.md

View on GitHub
# Skills Migration Guide for Existing Agents

Use this guide when the target agent is already supported in `cc-sdd` and now offers a native Skills mechanism.

## Decision Rule

Default to additive migration:
- Keep existing command/agent integration
- Add a new `{agent-id}-skills` variant
- Add dedicated alias flags (for example `--foo-skills`)

Use in-place migration only when the user explicitly asks for a breaking change.

## Migration Checklist

1. Confirm official Skills format
- Verify skill directory path
- Verify skill file format (`SKILL.md` schema and optional metadata files)
- Verify invocation style differences from command mode

2. Compare current implementation
- Check `tools/cc-sdd/src/agents/registry.ts` for current `agent-id`
- Check current manifest in `tools/cc-sdd/templates/manifests/`
- Check current templates in `tools/cc-sdd/templates/agents/{agent-id}/`
- Check existing real-manifest test coverage in `tools/cc-sdd/test/`

3. Define migration target
- New variant id: `{agent-id}-skills`
- New templates root: `tools/cc-sdd/templates/agents/{agent-id}-skills/`
- New manifest: `tools/cc-sdd/templates/manifests/{agent-id}-skills.json`
- New test: `tools/cc-sdd/test/realManifest{AgentName}Skills.test.ts`

4. Implement skills-specific behavior
- Registry `layout.commandsDir` points to skills directory
- Registry `commands.*` examples use Skills invocation syntax
- Manifest artifact switches from `commands` to `skills` templateDir when needed
- Template payload contains Skill folders with `SKILL.md` files

5. Verify backward compatibility
- Existing `--{agent-id}` flow still works
- New `--{agent-id}-skills` flow works
- Dry-run for both outputs expected artifact destinations
- Real manifest tests exist for both variants

## Recommended Base Example

Use these files as concrete reference for skills-mode implementation:
- `tools/cc-sdd/src/agents/registry.ts` (`claude-code-skills` entry)
- `tools/cc-sdd/templates/manifests/claude-code-skills.json`
- `tools/cc-sdd/templates/agents/claude-code-skills/`
- `tools/cc-sdd/test/realManifestClaudeCodeSkills.test.ts`

## Review Output Requirement

Always include a short migration impact section in the plan/result:
- Compatibility impact (`none` for additive)
- CLI flag changes
- Documentation updates required
- Rollback path (remove new variant only)
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall