critic-loop

Run an explicitly requested execution, independent critique, and revision workflow for a task or artifact, with evidence-backed scoring, category floors, a brief security screen, and at most three review rounds. Use only when the user invokes $critic-loop or explicitly requests this bounded critic workflow; do not add it to ordinary reviews.

Quality

86%

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

85%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-structured, validation-rich workflow with clear sequencing, feedback loops, and clean progressive disclosure into real reference and script bundles. Its only gaps are placeholder-laden commands and a high rule density that could be slightly tightened.

Dimension	Reasoning	Score
Conciseness	The body is dense and rule-driven with no padding or re-explanation of concepts Claude already knows, and detail is appropriately offloaded to references; the sheer volume of 12 rules plus runtime behavior and three code blocks could still be trimmed slightly, keeping it just below the leanest anchor.	4 / 5
Actionability	Provides concrete, mostly executable bash commands (verify-evidence.mjs, validate-scorecard.mjs, verify-review-run.mjs) and specific rules, but the commands contain substitution placeholders like <skill-directory> and <executable> that prevent fully copy-paste-ready execution.	4 / 5
Workflow Clarity	Sequences the full freeze-execute-critique-verify-report pipeline with explicit validation checkpoints ("Do not report PASS if root verification was not run successfully", validate-scorecard, verify-review-run) and a clear REVISE feedback loop where the critic re-verifies prior defects, matching the top anchor.	5 / 5
Progressive Disclosure	SKILL.md is an overview that points to five one-level-deep reference files under a clear "Before execution, read" list, with detail split into real bundle files (protocol.md, rubric.md, security-screen.md, evidence-protocol.md, scorecard-schema.md) and scripts, giving easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

87%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 strong: it concretely states what the skill does and precisely when to use it, gated by a distinct invocation token and a negative boundary that limits false triggers. Its only weakness is that the lead action "execution" is generic and it offers few trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("execution, independent critique, and revision workflow", "evidence-backed scoring, category floors, a brief security screen", "at most three review rounds") but the lead term "execution" is somewhat generic, leaving minor coverage gaps versus a fully granular action list.	4 / 5
Completeness	Explicitly answers both what (the bounded execution/critique/revision workflow with scoring, floors, and security screen) and when ("Use only when the user invokes $critic-loop or explicitly requests this bounded critic workflow"), with concrete trigger phrasing matching the top anchor.	5 / 5
Trigger Term Quality	Provides good natural coverage with the invocation token "$critic-loop" and the phrase "explicitly requests this bounded critic workflow", plus a negative boundary ("do not add it to ordinary reviews"), though it lacks synonyms or variants beyond the canonical trigger.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche gated by a specific invocation token and an explicit exclusion ("do not add it to ordinary reviews"), giving it distinct triggers and minimal conflict risk with other review skills.	5 / 5
	Total	18 / 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: stevenknowswhy/single-critic-skill
Path: SKILL.md
Commit: 3a35912

Reviewed: ~24 hours 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.