build-test

Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.

Quality

63%

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 ./plugins/_official/atoms/build-test/SKILL.md

Quality

Content

68%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 concise, actionable, and well-structured with executable commands and concrete output specs. Its main weakness is workflow clarity: for a skill that runs build/test as a batch operation, it lacks explicit validation checkpoints and a documented fix-and-retry feedback loop.

Suggestions

Add an explicit validation/feedback-loop section (e.g. on failure: read failures[] -> apply patch-edit -> re-run build-test until passing or iterations exhausted) to lift workflow clarity past the destructive/batch cap of 3.

Clarify how the 'custom' framework resolves typecheck/test from package.json scripts so the command table is fully executable.

Consider trimming the legacy critique.score rationale or moving it to a note so the primary signals stay focal.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence, providing a compact table of commands, an output spec, and a convergence example without padding; only minor lines (the legacy score rationale) could be trimmed.	4 / 5
Actionability	It gives executable commands (pnpm typecheck / pnpm test), a concrete output JSON shape, and a copy-ready devloop wiring example, with only minor gaps such as how the custom-framework package.json scripts are resolved.	4 / 5
Workflow Clarity	A sequence is implied (patch-edit then build-test, gated on plan step state) and the convergence example shows an until-loop, but explicit validation checkpoints and a validate->fix->retry feedback loop for the destructive/batch test run are absent, capping this at 3.	3 / 5
Progressive Disclosure	Content is well organized into Inputs, Default commands, Output, Convergence, Anti-patterns, and Status sections with no bundle files to manage; the only gap is that the implementation pointer to build-test.ts is a status note rather than a signaled reference.	4 / 5
	Total	15 / 20 Passed

Description

58%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 states concrete capabilities and is reasonably distinctive, but it omits an explicit "Use when..." trigger clause and leans on technical jargon over natural user phrasings. It is solid but not exemplary.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when a code-migration or tune-collab run needs to prove the build and tests still pass.'

Broaden trigger terms with natural phrasings users would say (e.g. 'run my tests', 'is the build passing') alongside the technical 'build.passing / tests.passing' signals.

Confirm third-person voice is preserved and avoid over-claiming coverage beyond the declared build/typecheck/lint/test commands.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("Run the project's build / typecheck / lint / test commands" and "emit the build.passing + tests.passing signals") rather than vague language, though it does not enumerate every command variant.	4 / 5
Completeness	The "what" is clear (run build/test commands and emit signals), but there is no explicit "Use when..." trigger clause telling Claude when to invoke this skill, which caps completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	Includes relevant technical terms (build, typecheck, lint, test) but lacks the natural phrasings a user would say (e.g. "run my tests", "is the build passing") and common synonyms, leaning toward jargon.	3 / 5
Distinctiveness Conflict Risk	The narrow niche of emitting build.passing/tests.passing signals for devloop convergence distinguishes it from generic build/test skills, with only minor overlap risk with sibling critique atoms.	4 / 5
	Total	14 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: plugins/_official/atoms/build-test/SKILL.md
Commit: 1a7a23d

Reviewed: about 7 hours 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.