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.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies a specific domain (Sentry's Command+K palette), lists concrete actions, and provides explicit 'Use when' triggers. The description is concise, uses third person voice, and includes natural keywords that users would use when needing this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: adding new actions to Command+K palette, registering page-level or global actions, building async resource pickers, and adding contextual actions to a view. | 3 / 3 |
Completeness | Clearly answers both 'what' (guide for adding new actions to Sentry's Command+K palette) and 'when' (explicit 'Use when' clause listing four specific trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'Command+K', 'cmdk', 'palette', 'actions', 'resource pickers', 'contextual actions', 'page-level', 'global actions'. These cover both the feature name and common variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific UI component (Sentry's Command+K palette / cmdk) with clear niche triggers that are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, highly actionable skill with excellent executable examples covering a wide range of command palette patterns. Its main weakness is length — at 400+ lines it could benefit from splitting advanced patterns into referenced files and trimming some explanatory prose that Claude doesn't need. The workflow clarity is strong with good decision tables, guard patterns, and a comprehensive checklist.
Suggestions
Split advanced patterns (workflow state machine, resource render-props, query-content-gated resources) into a separate ADVANCED_PATTERNS.md and reference it from the main skill to improve progressive disclosure and reduce token cost.
Trim explanatory sentences that describe what things are rather than what to do — e.g., 'Sentry's Command+K palette is built on a tree-collection system where...' could be removed since the patterns themselves make the architecture clear.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive and mostly efficient, but at ~400+ lines it includes some patterns that could be consolidated (e.g., patterns 6-9 could be more terse) and the checklist partially repeats guidance already given in the body. Some explanatory text is unnecessary for Claude (e.g., explaining what slots are, what a command palette is). | 2 / 3 |
Actionability | Every pattern includes complete, executable TSX code with real imports, real component names, and real API patterns from the Sentry codebase. The props interface is fully typed, the resource pattern shows exact `cmdkQueryOptions` usage, and even edge cases like render-prop children and type-narrowing have copy-paste-ready examples. | 3 / 3 |
Workflow Clarity | The skill clearly sequences how to add actions (choose slot → create component → register in correct location), includes explicit validation via the checklist, and the workflow/sequential state machine section demonstrates proper gating with canContinue guards and step-by-step progression. The decision table for static children vs resource is a strong checkpoint. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and a logical progression from core concepts to advanced patterns, but it's entirely monolithic — all content lives in a single file with no references to external files for advanced patterns, API reference, or examples. Given the length (~400+ lines), splitting the advanced patterns (workflow state machines, resource render-props) into separate files would improve navigability. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 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 | 10 / 11 Passed | |
- Repository
- getsentry/sentry
- Commit
552fb5c
- Reviewed
Table of Contents
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.