CtrlK
BlogDocsLog inGet started
Tessl Logo

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/autoreview/SKILL.md

The canonical home for this skill is autoreview in openclaw/openclaw

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The content is highly actionable with clear, validated multi-step workflows and proper use of bundled scripts, but it is long for a SKILL.md with redundancy across sections and keeps reference-grade tables inline rather than offloading them to separate reference docs.

Suggestions

De-duplicate the Codex Sol->Terra fallback, model defaults, and isolation details that recur across the intro, tables, and Helper bullet list — state each once and cross-reference.

Move the large env-variable, model, and isolation-flag tables into a reference file (e.g. REFERENCE.md) linked from a short overview to improve progressive disclosure.

Trim the Helper bullet list, which largely restates flags already shown as examples and tables above.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence (no basic-concept padding), but ~410 lines with notable redundancy — Codex Sol->Terra fallback, model defaults, and isolation details each recur across the intro, tables, and Helper bullet list — so it could be tightened.

2 / 3

Actionability

Provides many concrete, copy-paste-ready commands with exact flags (e.g. '"$AUTOREVIEW" --mode branch --base origin/main', '--reviewers codex,claude,pi') and explicit env-var/flag tables, fully executable rather than pseudocode.

3 / 3

Workflow Clarity

The closeout workflow is clearly sequenced with explicit validation/feedback loops — 'rerun focused tests and rerun the structured review helper', 'rerun... until no accepted/actionable findings remain' — plus the Scope Governor's in-scope/follow-up/stop-and-escalate classification and two-cycle convergence checkpoint.

3 / 3

Progressive Disclosure

The heavy implementation is correctly externalized to bundled scripts referenced one level deep via $AUTOREVIEW/$AUTOREVIEW_HARNESS, and sections are well-organized, but reference-grade detail (full env-var, isolation-flag, and model tables) lives inline in SKILL.md rather than in separate reference files.

2 / 3

Total

10

/

12

Passed

Description

72%

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 specific with good natural trigger terms and a clear distinct niche, but it lacks an explicit 'Use when...' trigger clause, so completeness is capped at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for a second-model code review or a pre-commit/ship closeout check on a branch or PR.'

Optionally name one or two concrete review actions (e.g. 'runs a structured review bundle and validates findings') to lift specificity from 2 to 3.

DimensionReasoningScore

Specificity

Names the domain ('Pre-commit/ship code review') and the concrete engine-selection behavior ('Codex default; optional Claude or Pi'), but does not list multiple distinct concrete actions as a 3 would require.

2 / 3

Completeness

It states what the skill does (code review at closeout) but the 'when' is only implied via 'pre-commit/ship' with no explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

Includes natural terms a user would actually say — 'code review', 'pre-commit', 'ship', plus engine names 'Codex', 'Claude', 'Pi' — giving good coverage of likely trigger phrasings.

3 / 3

Distinctiveness Conflict Risk

The closeout code-review niche with named engines (Codex/Claude/Pi) is clearly distinct from other skills and unlikely to trigger for the wrong skill.

3 / 3

Total

10

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openclaw/acpx
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.