tooluniverse-self-review

Review existing work against the user's actual goal and surface evidence-backed strengths, gaps, risks, and next fixes. Use when asked to eval, evaluate, review, assess, or check current/this/my/our work; decide whether a task is complete; build a definition-of-done checklist or rubric; or perform grading, LLM-as-judge, Qworld, or RET evaluation. Treat plain eval/review requests as qualitative: resolve "current work" from the conversation, artifacts, files, or diff, and never assign numeric scores unless the user explicitly requests scores, grades, points, ratings, weighted criteria, Qworld, or RET. Do not use for implementing automated eval suites, tests, graders, or benchmarks.

Quality

81%

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

71%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 well-structured, actionable instruction-only skill with clear routing, a sequenced default workflow, and an appropriately split one-level reference. The main weakness is redundancy between the upfront Non-Negotiable Rules and the later sections, which inflates token cost.

Suggestions

Collapse the 'Non-Negotiable Rules' into the sections that already enforce them, or keep the rules as one-line reminders and remove the duplicated elaboration in the modes/workflow sections.

Tighten the 'Resolve the Review Target' priority list and the deictic-phrase paragraph; the resolution order is already implied by the numbered list and the examples add length without new guidance.

Move the full 'Examples of Correct Routing' table into the reference file, keeping only two or three illustrative rows inline to reduce body length.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and skill-specific, but the "Non-Negotiable Rules" section restates points elaborated later (e.g., rule 2's eval≠scoring reappears in the modes table), and the body could be tightened without losing clarity.	3 / 5
Actionability	Provides concrete, executable guidance: a numbered 7-step qualitative workflow, an explicit priority order for resolving the review target, a fixed verdict vocabulary, and a routing examples table; only minor gaps keep it below 5.	4 / 5
Workflow Clarity	The default workflow is clearly sequenced with guardrails ("Proceed without asking when...", "Ask one short clarifying question only when...") and a defined output shape; this is a review skill so the destructive-operation validation cap does not apply.	4 / 5
Progressive Disclosure	The SKILL.md serves as an overview and delegates the heavy scored-evaluation detail to one real, one-level-deep reference ("read and follow [references/ret-scored-evaluation.md]"), which exists in the bundle and is clearly signaled.	5 / 5
	Total	16 / 20 Passed

Description

91%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, trigger-rich description that clearly states both capability and activation conditions, with an explicit out-of-scope boundary. It is slightly verbose and the generic review/check verbs leave minor conflict risk with adjacent review skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("surface evidence-backed strengths, gaps, risks, and next fixes", "decide whether a task is complete", "build a definition-of-done checklist or rubric", "perform grading, LLM-as-judge, Qworld, or RET evaluation") with only minor gaps; actions are conceptual rather than file-operational, keeping it just below a 5.	4 / 5
Completeness	Explicitly answers both what ("Review existing work against the user's actual goal and surface evidence-backed strengths, gaps, risks, and next fixes") and when ("Use when asked to eval..."), with concrete trigger phrases throughout.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage with synonyms and jargon users actually say: "eval, evaluate, review, assess, or check", "current/this/my/our work", "definition-of-done", "grading, LLM-as-judge, Qworld, or RET".	5 / 5
Distinctiveness Conflict Risk	Clear self-review niche with an explicit boundary ("Do not use for implementing automated eval suites, tests, graders, or benchmarks"); minor overlap risk remains because generic verbs like "review" and "check" could match a code-review skill.	4 / 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: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-self-review/SKILL.md
Commit: 1b02920

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.