ce-polish

Start the dev server, inspect the feature in browser, and iterate on polish.

Quality

72%

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 ./skills/ce-polish/SKILL.md

Quality

Content

85%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.

The content is a lean, well-structured orchestration overview with clear phased sequencing, real feedback checkpoints, and verified one-level-deep references; its main weakness is that the central server-start step (Phase 1.3) is described in prose rather than given as an executable command.

Suggestions

Replace the Phase 1.3 prose with a concrete executable command (or a script) that backgrounds the server, logs to a temp file, and polls the port, so the whole Phase 1 is copy-paste ready.

Provide an explicit default or resolution step for the <port> and <type> placeholders so the start sequence needs no manual substitution beyond the SKILL_DIR path.

Dimension	Reasoning	Score
Conciseness	The body is lean and every explanatory token earns its place — e.g. noting that 'shell state does not persist between Bash tool calls' is non-obvious guidance, not padding; it avoids re-explaining concepts Claude already knows, matching the 'lean and efficient; assumes Claude's competence' anchor; not a 2 because there is no unnecessary explanation to trim.	3 / 3
Actionability	Most blocks are executable (e.g. `bash "$SKILL_DIR/scripts/read-launch-json.sh"` and a type→recipe routing table), but Phase 1.3 ('Start the dev server in the background, log output to a temp file...') is described in prose without a concrete copy-paste command and several placeholders (<port>, <type>) remain; not a 3 due to those incomplete/abstract spots, not a 1 because concrete commands dominate.	2 / 3
Workflow Clarity	Phases 0–2 are clearly sequenced with checkpoints: 'Verify the current branch is not main/master' and the server probe with a feedback loop ('If it doesn't come up, show the last 20 lines of the log and ask the user what to do'). Matches the clear-sequence-with-error-recovery anchor.	3 / 3
Progressive Disclosure	The body is an overview that routes to one-level-deep references and scripts, all of which exist as real files (verified: every references/.md and scripts/.sh path listed is present), organized in a clearly signaled References section; matches the well-signaled one-level-deep anchor.	3 / 3
	Total	11 / 12 Passed

Description

60%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.

The description is concise and names concrete actions in proper third-person imperative voice, but it omits an explicit 'Use when...' trigger clause and lacks breadth of natural trigger terms, capping completeness and trigger quality at 2.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when the user wants to review and polish a feature in a running dev server before merging.'

Broaden trigger terms with natural phrasings users actually say, such as 'review the feature in the browser', 'UI polish', or 'see it running locally'.

Tie the workflow to a clearer niche (e.g. pre-merge polish loop) to reduce overlap with generic dev-server skills.

Dimension	Reasoning	Score
Specificity	Quotes three concrete actions — "Start the dev server", "inspect the feature in browser", "iterate on polish" — matching the 'lists multiple specific concrete actions' anchor; not a 2 because it names more than a domain plus partial actions.	3 / 3
Completeness	The description states the what (start server, inspect, iterate) but lacks any "Use when..." or explicit trigger for when to invoke it; per guidelines a missing 'Use when...' clause caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant terms like "dev server", "feature", and "polish" appear, but common user variations (e.g. "UI polish", "review the feature", "see it in the browser") are missing; not a 3 because coverage of natural phrasings is incomplete, not a 1 because real domain keywords are present.	2 / 3
Distinctiveness Conflict Risk	The dev-server-and-polish framing is somewhat specific, but without explicit triggers it could overlap with general dev-server skills; not a 3 because the niche is not sharply distinguished, not a 1 because it is not wholly generic.	2 / 3
	Total	9 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: EveryInc/compound-engineering-plugin
Path: skills/ce-polish/SKILL.md
Commit: a9f6d53

Reviewed: 7 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.