Skills
Run a skill by typing its name, for example /implement TOOL-123.
| Skill | What it does |
|---|---|
/ticket | Create, read or update a Linear ticket |
/epic | Create a Linear project with its tickets |
/read | Groom a ticket: explore the code, estimate size, draft the technical plan |
/implement | Assign a ticket, branch from origin/main, and plan the work |
/commit | Commit with the ticket ID taken from the branch name |
/review | Run Biome, the type check and tests, then review the diff |
/pr | Push and open a draft PR from the repo's template |
/qa | Test the branch's changes in a browser with Playwright |
/fix | Run a bug fix end to end: read, implement, commit, QA, PR |
/triage | Investigate a bug with its Slack thread and post the findings |
Planningβ
/ticket β /read β /epic (for larger work)
Ends with a groomed ticket in Linear: acceptance criteria, a technical plan and a size.
Implementationβ
/implement β write the code β /commit β /review β /pr
Ends with a draft PR that has passed the repo's checks and a local review. Run /qa before /pr for anything visible in a browser.
Per-repo configurationβ
Some skills read a file from the project repo, so their behavior differs between repos:
| File | Read by |
|---|---|
.claude/rules/architecture.md | /read, /implement, /review (and they add to it) |
.claude/rules/pr-review.md | /review |
.claude/rules/qa.md | /qa, for URLs, login and routes |
.github/pull_request_template.md | /pr |
Adding a skillβ
- Add a folder under
skills/with aSKILL.md. Its frontmatter sets the name, description, allowed tools and argument hint. - Refer to the skill's own files with relative paths (
.claude/skills/<name>), so it works from any repo. - If it has scripts, give it a
package.jsonand run them withnpx tsx. - If it needs keys, add a
.env.example. - A skill that builds on others should call them, not copy their steps.