Make repo-root `skills/` and `agents/` the canonical source for the `sentry-skills` plugin by loading the plugin from repo root instead of from `plugins/sentry-skills`. The earlier refactor moved the tree to top level, but leaving a plugin-local `skills` symlink still created a loader risk for marketplace installs. This removes that dependency entirely: the marketplace entry now points at `./`, the root plugin manifest uses repo-root `skills/` and `agents/`, and the old plugin-local `skills` path goes away. This pass also tightens the repo guidance around standard skill locations. `skill-writer` goes back to using `.agents/skills` as its default local target, `skill-writer` and `skill-scanner` now explicitly recognize canonical `skills/<name>/` roots, and the repo docs and registrations are updated to match the new layout, including `presentation-creator`. I validated the change with strict-depth validation for `skill-writer` and `skill-scanner`, plus a local Claude marketplace add/install smoke test that produced real `skills/` and `agents/` directories in the installed plugin cache without any plugin-local `skills` symlink. --------- Co-authored-by: Codex <noreply@openai.com> Co-authored-by: Codex <codex@openai.com>
2.0 KiB
Contributing
Philosophy
This repository favors incremental change over perfection. Skills are living documents that improve over time through small, iterative updates.
- Bias toward action - Ship small improvements rather than waiting for the perfect solution
- Self-review is the default - You know your changes best
- Iterate freely - Don't hesitate to refine existing skills
Testing Skills
Before merging, test your changes locally:
-
Install the plugin from your local clone
claude plugin marketplace add ~/path/to/sentry-skills claude plugin install sentry-skillsIf you use
claude plugin marketplace add --sparsefor this repo, includeskillsandagentsin addition to.claude-pluginbecause the root plugin manifest loads repo-rootskills/andagents/. -
Restart Claude Code to pick up changes
-
Invoke the skill in a relevant context
# For explicit invocation /skill-name # Or describe a task that should trigger the skill -
Verify behavior - Check that the skill produces the expected guidance and handles edge cases appropriately
Pull Request Workflow
All changes go through the PR flow, but formal review is optional.
- Self-review and merge when you're confident in your change
- Request review only when you want a second pair of eyes
- Keep PRs focused - one skill or one improvement per PR when practical
Adding a New Skill
-
Create
skills/<skill-name>/SKILL.md -
Add required YAML frontmatter:
--- name: skill-name description: What this skill does. Include trigger keywords. --- -
Update
README.mdto add the skill to the Available Skills table in alphabetical order by skill name -
Add the skill to
.claude/settings.json:"Skill(sentry-skills:skill-name)" -
Update the skills allowlist in
skills/claude-settings-audit/SKILL.md
See README.md for the full skill template and optional frontmatter fields.