verify

Verify a Bun runtime change by driving the debug binary end-to-end.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/verify/SKILL.md

Quality

Content

93%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.

The body is a tight, highly actionable verification playbook: concrete commands, an explicit validation gate, and a remediation feedback loop, with no wasted tokens on background concepts. The only minor weakness is that the validation checkpoint sits in Gotchas rather than the main Build/Drive sequence.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: concrete commands and Bun-internal gotchas with no padding about what Bun or a debug binary is, so every token earns its place. It is not 4 because there is no over-explanation of concepts Claude already knows to trim.	5 / 5
Actionability	It provides fully executable, copy-paste-ready commands (bun bd --version, bun bd -e '<repro>', node -e, ./build/debug/bun-debug <file>, PATH="$HOME/.cargo/bin:$PATH", touch ... && rebuild) covering build, drive, worker, and remediation cases. It is not 4 because guidance is concrete and complete, with the <repro> placeholder being justified flexibility rather than a gap.	5 / 5
Workflow Clarity	There is a clear Build → Drive sequence plus an explicit validation gate ("Gate on the binary, not the build") and a feedback loop ("If false, touch ... and rebuild"). It is not 5 because that validation/checkpoint lives under Gotchas rather than being sequenced into the main flow, leaving a minor integration gap.	4 / 5
Progressive Disclosure	At under 50 lines with no need for external references (references/, scripts/, assets/ are all empty) and well-organized Build/Drive/Gotchas sections, this matches the simple-skill exception where well-organized sections alone earn a 5. It is not 4 because no content is misplaced or begging to be split out.	5 / 5
	Total	19 / 20 Passed

Description

53%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.

The description is concrete and specific with a clear niche, but it omits any explicit trigger ("Use when...") guidance and lacks synonym coverage, capping completeness and trigger-term quality. Adding a when-clause and natural phrasing variants would lift it into the 4-5 band.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when verifying a Bun runtime change or confirming a JS-visible edit actually reached the debug binary."

Include natural trigger-term synonyms (test, check, reproduce/repro, debug build) so users phrasing the need differently still surface the skill.

Optionally enumerate 1-2 more concrete actions (build the debug binary, run a repro with -e, cross-check against node) to lift specificity toward 4-5.

Dimension	Reasoning	Score
Specificity	"Verify a Bun runtime change by driving the debug binary end-to-end" names the domain (Bun runtime) and one concrete action (driving the debug binary e2e), but lists only a single action rather than several, matching the 1-2-concrete-actions anchor. It is not 4 because no multiple specific actions are enumerated, and not 2 because the action is concrete rather than minimal/generic.	3 / 5
Completeness	The "what" is clear (verify a Bun runtime change via the debug binary), but there is no "Use when..." clause or equivalent trigger guidance, so per the rubric completeness is capped at 3. It is not 4 because the "when" is entirely absent rather than merely weak, and not 2 because the "what" is concrete rather than vague.	3 / 5
Trigger Term Quality	It surfaces relevant keywords ("verify", "Bun", "runtime change", "debug binary") a user might say, but offers no synonyms or variations (e.g., test, check, repro), matching the some-keywords-but-missing-variations anchor. It is not 4 because coverage is thin on natural phrasings users would actually utter.	3 / 5
Distinctiveness Conflict Risk	The niche is specific (Bun runtime changes verified through the debug binary), giving it a clear identity with only minor overlap risk against a general Bun-testing skill. It is not 5 because "verify a Bun change" could plausibly collide with broader Bun test/CI skills, and not 3 because the debug-binary framing is genuinely distinguishing.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: oven-sh/bun
Path: .claude/skills/verify/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.