David Cramer
9c0e34277f
* fix(skills): Standardize allowed-tools to comma-separated format Claude Code docs specify comma-separated format for allowed-tools. Update all skill frontmatters, documentation, and the scan_skill.py parser to use and support comma-separated tool lists. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(skills): Remove model attribute from skill documentation Skills should not hardcode model overrides — let users control which model runs their skills. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2.2 KiB
Sentry Agent Skills
A collection of agent skills for use by Sentry employees, primarily designed for Claude Code.
This repository is structured as a Claude Code plugin (see plugins/sentry-skills/), but the skills themselves follow the open Agent Skills specification format to maintain compatibility with other tools that adopt the standard.
Structure
plugins/sentry-skills/skills/<skill-name>/SKILL.md
Each skill is a directory containing a SKILL.md file with YAML frontmatter (name, description) and markdown instructions.
Creating a Skill
- Create
plugins/sentry-skills/skills/<skill-name>/SKILL.md - Add YAML frontmatter (see below)
- Write clear instructions in markdown
- Update
README.mdto include the new skill in the Available Skills table - Update the skills allowlist in
plugins/sentry-skills/skills/claude-settings-audit/SKILL.md - Add the skill to
.claude/settings.jsonin thepermissions.allowarray asSkill(sentry-skills:<skill-name>)
Frontmatter
Important: The YAML frontmatter must be at the very beginning of the file. Do not place comments or any other content before it—parsers expect --- as the first line.
Required:
name- kebab-case, 1-64 charsdescription- up to 1024 chars, include trigger keywords
Optional:
allowed-tools- comma-separated list of permitted toolslicense- license name or path (for attribution, place a LICENSE file in the skill directory)compatibility- environment requirements (max 500 chars)
---
name: example-skill
description: What this skill does and when to use it. Include trigger keywords.
allowed-tools: Read, Grep, Glob, Bash
license: LICENSE
---
<!-- Attribution comments go AFTER the frontmatter -->
# Example Skill
Instructions for the agent.
Skill Design Guidelines
When writing skills that include Python scripts, always instruct the agent to use uv run <script> instead of python <script> or python3 <script>.