Skip to content

CherryHQ/cherry-studio / .agents/skills/create-skill

create-skill

Verified

Create a new skill in the current repository. Use when the user wants to create/add a new skill, or mentions creating a skill from scratch. This skill follows the workflow defined in .agents/skills/README.md and helps scaffold, validate, and sync new skills.

FileKindSize
SKILL.mdskill md3.2 KB
---
name: create-skill
description: Create a new skill in the current repository. Use when the user wants to create/add a new skill, or mentions creating a skill from scratch. This skill follows the workflow defined in .agents/skills/README.md and helps scaffold, validate, and sync new skills.
---

# Create Skill

Create a new skill in `.agents/skills/<skill-name>/` following the workflow defined in `.agents/skills/README.md`.

## Workflow

### Step 1: Gather Intent

Before creating anything, ask the user:

1. **Skill name**: What should the skill be called? (lowercase, digits, hyphens only, e.g., `gh-create-pr`, `prepare-release`)
2. **Description**: What should this skill do? Include specific trigger contexts (e.g., "Use when user asks to create PRs")
3. **Is this a public skill?**: Should it be synced to `.claude/skills/` for shared use? (default: no, private only)
4. **Test cases** (optional): Does the user want to set up evals for this skill?

If the user provides partial info (e.g., just a name), proceed with reasonable defaults and ask to confirm.

### Step 2: Read Guidelines

Always read `.agents/skills/README.md` before creating a new skill to ensure compliance with the current workflow.

### Step 3: Create Skill Structure

Create the following directory structure:

```
.agents/skills/<skill-name>/
└── SKILL.md
```

**SKILL.md template:**

```markdown
---
name: <skill-name>
description: <description>
---

# <Skill Name>

[Instructions for the skill]
```

**Frontmatter fields:**
- `name`: Skill identifier (lowercase, digits, hyphens)
- `description`: When to trigger (what the skill does + specific contexts)

### Step 4: Sync (if public)

If the user wants a **public skill**, before validation:

1. Add the skill name to `.agents/skills/public-skills.txt` (one per line, no inline comments)
2. Run sync:
   ```bash
   pnpm skills:sync
   ```

This creates a symlink at `.claude/skills/<skill-name>/` pointing to `.agents/skills/<skill-name>/`.

**Note**: `pnpm skills:check` primarily validates public skills (those in `public-skills.txt`) and also verifies related governance files, so you must sync first before validating.

### Step 5: Validate

Run the validation command:

```bash
pnpm skills:check
```

If there are issues, fix them and re-run.

### Step 6: Summary

Present the user with:
- Created files
- Validation result
- Next steps (how to use the skill)

## Naming Rules

- Use lowercase letters, digits, and hyphens only
- Prefer short, action-oriented names (e.g., `gh-create-pr`)

## Public vs Private Skills

| Type | Location | Sync | Requires |
|------|----------|------|----------|
| Private | `.agents/skills/` | No | Just create the folder |
| Public | Both | Yes | Add to `public-skills.txt` + run `pnpm skills:sync` |

## Commands Reference

```bash
# Validate skill structure
pnpm skills:check

# Sync public skills to Claude
pnpm skills:sync
```

## Constraints

- Never create skills outside `.agents/skills/<skill-name>/`
- Always run `pnpm skills:check` before completing
- Public skills require both adding to `public-skills.txt` AND running `pnpm skills:sync`
- If the skill-creator skill is available, you may use it for advanced skill development (evals, iterations), but this skill handles the basic creation workflow.
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: 471kUpdated 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