agents-md
Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files. Use when asked to create AGENTS.md, update…
Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy
Claude Code
$ npx -y skills add getsentry/skills --skill typing-exclusion-worker --agent claude-code
Codex
$ npx skills add getsentry/skills --skill typing-exclusion-worker -a codex -y
Cursor
$ npx skills add getsentry/skills --skill typing-exclusion-worker -a cursor -y
Gemini CLI
$ npx skills add getsentry/skills --skill typing-exclusion-worker -a gemini-cli -y
GitHub Copilot
$ npx skills add getsentry/skills --skill typing-exclusion-worker -a github-copilot -y
OpenCode
$ npx skills add getsentry/skills --skill typing-exclusion-worker -a opencode -y
Windsurf
$ npx skills add getsentry/skills --skill typing-exclusion-worker -a windsurf -y
name: typing-exclusion-worker description: "Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy exclusion overrides."
Execute one assigned typing batch safely and predictably:
Before starting, confirm these inputs exist in the task prompt:
If any are missing, ask for them before editing.
1. Only remove assigned module entries from the mypy exclusion list in `pyproject.toml`. 2. Keep code changes in assigned scope unless a direct dependency is required to pass typing/tests. 3. Do not expand to cross-team modules unless explicitly approved by the manager. 4. Avoid blanket `# type: ignore`; if unavoidable, use narrow `ignore[code]` with a short reason.
1. **Apply exclusion change**
2. **Run mypy on assigned scope**
3. **Run tests for touched area**
4. **Run pre-commit on changed files**
5. **Final verification**
Return this exact structure at the end of each batch:
## Batch Summary - Branch/worktree: `<name>` - Ownership/domain: `<team-or-domain>` ### Modules Removed From Exclusion - `<module.path.one>` - `<module.path.two>` ### Files Changed - `<path>` - `<path>` ### Key Typing Fixes - `<short rationale + fix>` - `<short rationale + fix>` ### Validation - `mypy`: `<pass/fail + scope>` - `pre-commit --files`: `<pass/fail>` - `pytest`: `<pass/fail + scope>` ### Notes - Remaining blockers: `<none or details>` - Any new ignore entries: `<none or file + ignore code + reason>`
Stop and report instead of widening scope when:
Agent skills for Sentry employees, following the Agent Skills open format.
Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files. Use when asked to create AGENTS.md, update…
Write, review, and improve blog posts for the Sentry engineering blog following Sentry's specific writing standards, voice, and…
Write copy following Sentry brand guidelines. Use when writing UI text, error messages, empty states, onboarding flows, 404…
Analyze a repository to generate recommended Claude Code settings.json permissions. Use when setting up a new project, auditing…
Perform code reviews following Sentry engineering practices. Use when reviewing pull requests, examining code changes, or…
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Use when asked to…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.