autoreview

Run structured AI code review as an advisory closeout gate for local diffs, PR branches, or commits when the user asks for autoreview, Codex review, second-model review, or pre-ship validation.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./Skills/agent-ops/autoreview/SKILL.md

Quality

Content

66%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 well-sequenced, validation-rich review workflow with concrete executable commands, but it is longer than necessary due to repeated scope/routing policy and has a broken reference ('agents/openai.yaml') plus inlined content that could live in references.

Suggestions

Fix or remove the broken reference to 'agents/openai.yaml', which does not exist in the bundle.

De-duplicate the scope/routing guidance repeated across When To Use, When Not To Use, Routing Boundaries, Scope Governor, and Release Branches — consolidate once and cross-reference.

Convert the References list to linked, one-level-deep pointers with brief labels (e.g. 'contract.yaml — engine/finding schema') and move inlined policy detail into reference files.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no tutorials on what a diff or library is), but the Scope Governor, Release Branches, and Procedure sections restate routing/scope guidance already in When To Use / When Not To Use. Not 4 because the redundancy is more than minor trimming; not 2 because it is not explaining known concepts.	3 / 5
Actionability	Provides concrete, mostly executable commands across the common cases ('--mode branch --base origin/main', '--mode commit --commit HEAD', 'gh pr view --json baseRefName --jq .baseRefName', the ordered py_compile/audit/evals validation block) with a full flag inventory. Not 5 because the '<autoreview-helper>' placeholder and repo-specific 'Skills/agent-ops/...' paths prevent pure copy-paste readiness.	4 / 5
Workflow Clarity	Sequences Preflight -> Pick Target -> Procedure -> Validation -> Final Report with explicit validation checkpoints and feedback loops (verify findings against real code, rerun focused tests and the review helper after a fix, stop on exit 0, two-cycle pause and reclassify). Matches the anchor-5 example.	5 / 5
Progressive Disclosure	Structure exists and most listed references resolve (contract.yaml, evals.yaml, discovery-interview.md, task-profile.json all present), but the body lists 'agents/openai.yaml' which does not exist in the bundle, references are plain backtick paths rather than linked one-level-deep pointers, and substantial policy content is inlined. Not 4 because of the broken reference and buried signaling; not 2 because organization is genuinely present.	3 / 5
	Total	15 / 20 Passed

Description

92%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 specific, complete, and distinctive: it states both what the skill does and when to invoke it, with concrete review targets and natural trigger phrases. Its only gap is slightly limited synonym breadth in the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and surfaces ('Run structured AI code review', 'advisory closeout gate for local diffs, PR branches, or commits') with comprehensive coverage. Matches the anchor-5 example; not 4 because coverage has no notable gaps.	5 / 5
Completeness	Explicitly answers both what ('Run structured AI code review as an advisory closeout gate for local diffs, PR branches, or commits') and when ('when the user asks for autoreview, Codex review, second-model review, or pre-ship validation') with concrete triggers.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('autoreview, Codex review, second-model review, or pre-ship validation') with good coverage. Not 5 because it leans on product/tool names rather than broad synonyms or phrasings like 'review my diff'.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (advisory second-model closeout review) with distinct triggers and an explicit advisory-not-approval framing that separates it from merge/CI/thread-mutation skills. Minimal conflict risk.	5 / 5
	Total	19 / 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: jscraik/Agent-Skills
Path: Skills/agent-ops/autoreview/SKILL.md
Commit: f1f2f21

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.