json-output-review

Review machine-readable JSON output changes for schema stability, determinism, and downstream usability. Use when changes affect JSON output, result fields, ordering, snapshots, or integration contracts.

Quality

80%

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

78%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-structured instruction-only review skill that assumes Claude's competence and uses a clean one-level reference plus an explicit verdict contract. Its main gap is actionability: the how-to for each review concern is deferred to an external file rather than surfaced inline.

Suggestions

Inline one or two concrete checks per focus area (e.g., how to detect ordering drift or null/empty regressions) instead of deferring all method to the external reviewer file.

Make the workflow sequence explicit (number the read -> check -> review -> verdict steps) so the order of operations is unambiguous.

Confirm the referenced .agents/agents/json-output-reviewer.md is bundled or reachable from the skill location, since no references/ bundle file exists to back the pointer.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding or explanation of concepts Claude already knows; every line (focus list, reference pointer, verdict contract) earns its place.	5 / 5
Actionability	Provides a concrete focus checklist and an explicit output contract ('End with APPROVE, CONCERN, or BLOCK'), but the actual evaluation method is deferred to an external file and 'check compatibility and drift risk' lacks how-to detail; not a 4 because executable guidance is incomplete.	3 / 5
Workflow Clarity	A clear loose sequence exists (read reviewer doc, check snapshots/schema/docs, review against focus list, emit verdict) and the read-only review task needs no destructive-validation checkpoint; not a 5 because ordering of 'Also check...' steps is implicit rather than explicitly sequenced.	4 / 5
Progressive Disclosure	A clear, well-organized overview under 50 lines with a single well-signaled one-level-deep reference ('Read .agents/agents/json-output-reviewer.md before reviewing'), matching the simple-skill exception for clean structure.	5 / 5
	Total	17 / 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 strong description with third-person voice, explicit what/when structure, and distinct JSON-output triggers. Its only weakness is that 'Review' is a single action verb rather than a list of distinct concrete operations.

Dimension	Reasoning	Score
Specificity	Names the domain ('JSON output changes') and several review concerns (schema stability, determinism, downstream usability) but offers only one concrete action ('Review') rather than multiple distinct actions, matching the 1-2 concrete actions anchor; not a 4 because it does not list several separate actions.	3 / 5
Completeness	Explicitly answers both what ('Review machine-readable JSON output changes for schema stability, determinism, and downstream usability') and when ('Use when changes affect JSON output, result fields, ordering, snapshots, or integration contracts') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('JSON output', 'result fields', 'ordering', 'snapshots', 'integration contracts') users would say; not a 5 because it lacks synonyms and file extensions like '.json'.	4 / 5
Distinctiveness Conflict Risk	Clear niche (machine-readable JSON output review) with distinct triggers ('snapshots', 'integration contracts', 'ordering') and minimal overlap risk with other 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: .agents/skills/json-output-review/SKILL.md
Commit: 03aad8c

Reviewed: 2 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.