cmdk-actions

Guide for adding new actions to Sentry's Command+K palette. Use when implementing new cmdk actions, registering page-level or global actions, building async resource pickers, or adding contextual actions to a view.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An excellent, actionable reference for an internal command-palette system: executable examples, concrete file paths, and a verification checklist. Its only real weakness is progressive disclosure — everything lives in one large SKILL.md with no referenced detail files.

Suggestions

Move the CMDKAction prop reference and/or the nine action patterns into separate reference files under references/ (e.g. PROPS.md, PATTERNS.md) and link to them from SKILL.md so the overview stays lean.

Fix the duplicate "### 7" section headers ("trailingItem" and "Query-content-gated resource" are both numbered 7) to keep the pattern catalog navigable.

Consider pulling the closing checklist into its own short section or file so the inline rules and the verification list do not repeat the same guidance verbatim.

Dimension	Reasoning	Score
Conciseness	The body is long but dense with executable code and terse rules about an internal API Claude does not already know; it avoids explaining generic React/JSX concepts and nearly every section earns its tokens.	3 / 3
Actionability	Provides complete, copy-paste-ready tsx examples for every pattern, concrete file paths, a full prop interface, and named helpers like cmdkQueryOptions and renderAsyncResult.	3 / 3
Workflow Clarity	Patterns are clearly sequenced (Core files → Slots → Props → Patterns → splitting → registering → gating → checklist), the workflow section shows explicit step gating, and the closing checklist gives verification steps; no destructive/batch operation is involved that would require a validate-fix-retry loop.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers and tables, but the ~690-line body is monolithic with no bundle files and no split-out references, so content that could live in separate files (the prop reference, the pattern catalog) is inline.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states concrete capabilities and provides an explicit "Use when" trigger covering several natural entry points. It is specific to Sentry's cmdk system, so conflict risk is low.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "implementing new cmdk actions, registering page-level or global actions, building async resource pickers, or adding contextual actions to a view" — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ("Guide for adding new actions to Sentry's Command+K palette") and when ("Use when implementing new cmdk actions, registering page-level or global actions, building async resource pickers, or adding contextual actions to a view").	3 / 3
Trigger Term Quality	Covers natural terms a Sentry developer would say — "Command+K palette", "cmdk actions", "page-level or global actions", "async resource pickers", "contextual actions" — with good variation.	3 / 3
Distinctiveness Conflict Risk	Tightly scoped to "Sentry's Command+K palette" and the cmdk action system, giving it a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (691 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: getsentry/sentry
Path: .agents/skills/cmdk-actions/SKILL.md
Commit: b4b3565

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.