review

Perform Fallow's comprehensive pre-merge review. Use after implementation or when asked to review a branch, pull request, or diff.

Quality

85%

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

Quality

Content

88%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.

A tight, well-sequenced review workflow with strong conciseness and an explicit fix-then-rerun feedback loop. The main improvement area is progressive disclosure: external references are signaled inline but not organized into a navigable section, and the actual gate commands remain one indirection away.

Suggestions

Add a short 'References' section listing `docs/development/quality-gates.md` and `docs/development/review-routing.md` as markdown links so the supporting materials are discoverable at a glance rather than buried inside steps.

Inline the one or two most common gate commands (e.g. the canonical lint/test invocation) so reviewers can act without opening the referenced file for the typical case.

Spell out the termination condition explicitly, e.g. 'Only finish when no result remains BLOCK', to make the fix→rerun loop's exit criterion unambiguous.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with zero padding: every line is an actionable instruction and it assumes Claude's competence, matching the 'every token earns its place' anchor.	5 / 5
Actionability	Provides concrete, specific guidance — exact file paths, an explicit APPROVE/CONCERN/BLOCK classification, and a fix-then-rerun instruction — but the actual gate commands and reviewer-selection details are delegated to referenced files rather than given inline, leaving a minor gap versus the fully copy-paste 5 anchor.	4 / 5
Workflow Clarity	A clear seven-step numbered sequence with an explicit validation feedback loop in step 7 ('Fix every block, rerun the blocking reviewer, and update verification') and a classification checkpoint in step 6, matching the 'clear sequence with explicit validation steps and feedback loops' anchor.	5 / 5
Progressive Disclosure	The body is a concise overview that points to one-level-deep, clearly signaled references (quality-gates.md, review-routing.md), but the references are embedded inline in steps rather than presented as a navigation section, and the referenced files are external to the bundle and unverifiable, so it sits just below the cleanly-organized 5 anchor.	4 / 5
	Total	18 / 20 Passed

Description

82%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.

A concise, well-structured description that clearly states both the skill's purpose and its trigger conditions with natural, distinctive terms. Its only soft spot is specificity, since the description names the review domain without enumerating the concrete review actions (which live in the body).

Dimension	Reasoning	Score
Specificity	Names the domain ('pre-merge review') and one concrete action ('Perform ... review') but does not list multiple specific sub-actions, matching the 'names domain and 1-2 concrete actions, not comprehensive' anchor rather than the multi-action examples at 4-5.	3 / 5
Completeness	Explicitly answers both 'what' ('Perform Fallow's comprehensive pre-merge review') and 'when' ('Use after implementation or when asked to review a branch, pull request, or diff') with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	'branch, pull request, or diff' plus 'after implementation' give good natural keyword coverage with synonyms users actually say; a few common variations like 'code review' or 'merge request' are absent, so it sits below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The 'Fallow's' brand qualifier and pre-merge scoping to branch/PR/diff give a clear niche with distinct triggers and minimal conflict risk against generic review skills.	5 / 5
	Total	17 / 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: fallow-rs/fallow
Path: .claude/skills/review/SKILL.md
Commit: 7e1e075

Reviewed: 3 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.