slowest-tests

Find the top-N slowest test files in CI from a recent BuildKite run, optionally posting the results to a Slack channel as a formatted table. Use when asked to find slow CI tests, "what's making CI slow", or to post a slow-test report to Slack.

Quality

85%

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

76%Weight 40%Scale 1-5

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

Highly actionable, concrete content with excellent executable commands and a clear two-phase workflow. The main gap is the absence of validation/verification checkpoints in the batch Slack-posting flow, which caps workflow clarity.

Suggestions

Add an explicit verification checkpoint after gist creation (e.g. confirm the gist URL is returned) before posting the main Slack message, and confirm the main message posted successfully before threading rows 21–N.

Add a fallback/validation note for the channel lookup step — what to do if slack_search_channels returns no match or multiple matches.

State the expected script output format up front (TSV columns) so Claude can verify the gather-data step succeeded before moving to Slack posting.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence — the bullet list of script internals and Slack formatting rules are non-obvious specifics that earn their place. A few explanatory clauses (e.g. the parenthetical about Slack MCP having no file-upload tool) could be trimmed, keeping it just below a 5.	4 / 5
Actionability	Fully executable guidance throughout — concrete commands ('bun run ci:slowest 47324 100', 'gh gist create ...', 'gh pr list --state merged --limit 10 ...'), exact file paths, and a copy-paste-ready bullet row format with padding rules.	5 / 5
Workflow Clarity	The two-phase flow (gather data, then post to Slack) and the 4-step Slack procedure are clearly sequenced, but this is a batch operation (chunked posting of N rows) with no explicit validation/verification checkpoints — e.g. confirm the channel ID was found, verify the gist was created before posting, or confirm the main message posted before threading — so it is capped at 3 per the batch-operation rule.	3 / 5
Progressive Disclosure	Well-organized into two clear sections with the bulk of detail appropriately inline for a ~45-line skill; the referenced script (scripts/ci-slowest-tests.ts) is a repo artifact rather than a bundled skill file, so navigation stays one level deep. Not a 5 because no bundle exists to verify referenced paths and the structure is flat rather than explicitly pointing to deeper materials.	4 / 5
	Total	16 / 20 Passed

Description

95%Weight 40%Scale 1-5

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 clearly answers both 'what' and 'when' with concrete, natural-language triggers. Minor room to broaden the action list, but otherwise excellent.

Dimension	Reasoning	Score
Specificity	Names concrete actions — 'Find the top-N slowest test files in CI from a recent BuildKite run' and 'optionally posting the results to a Slack channel as a formatted table' — giving several specific capabilities; not a 5 because the action set is narrow (find + post) rather than a comprehensive list.	4 / 5
Completeness	Explicitly states both what it does (find slowest test files, optionally post a formatted table to Slack) and when to use it via a concrete 'Use when...' clause with multiple trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would actually say — 'find slow CI tests', the quoted 'what's making CI slow', and 'post a slow-test report to Slack' — covering synonyms and the reporting variant comprehensively.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (slowest CI tests from BuildKite + Slack reporting) with distinct, specific triggers that are unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: oven-sh/bun
Path: .claude/skills/slowest-tests/SKILL.md
Commit: abe2ad4

Reviewed: 1 day 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.