evaluate

Evaluate execution with three-stage verification pipeline

Quality

60%

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 ./.claude-plugin/skills/evaluate/SKILL.md

The canonical home for this skill is evaluate in Q00/ouroboros

Quality

Content

73%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 content is a well-structured, actionable guide with a clear sequenced workflow and explicit validation checkpoints; its main weakness is verbosity in the emphatic guard sections that could be tightened.

Suggestions

Tighten the 'CRITICAL — deferred-schema guard' block by stating the rule once ('re-run tool discovery before every ouroboros_start_evaluate call') instead of re-explaining the rationale twice.

Collapse the repeated 'IMPORTANT: Do NOT skip' preamble into a single concise directive.

Consider moving the full MCP argument table and the multi-line breadcrumb enumeration into a short reference section or file so the main flow stays lean.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete tool arguments, but contains padded emphatic passages ('IMPORTANT: Do NOT skip', the repeated 'CRITICAL — deferred-schema guard' rationale, and verbose fallback caveats) that could be trimmed without losing clarity.	3 / 5
Actionability	It provides the concrete MCP tool name, a full argument block with types and defaults, a named fallback agent, and breadcrumb templates — mostly executable guidance with only minor gaps around the illustrative discovery-query syntax.	4 / 5
Workflow Clarity	Steps are explicitly sequenced (1, 2, 2.5, 3, 4, 5) with concrete validation checkpoints (Stage 1 fails fast, acting verification in 2.5, the deferred-schema re-load guard, terminal-result handling) and feedback loops for recovery, matching the top anchor.	5 / 5
Progressive Disclosure	A single self-contained SKILL.md with well-organized sections and no bundle files; structure is good, though some inline detail (full argument schemas, breadcrumb enumeration) could arguably be split into a reference, keeping it just below the ideal split-out of a 5.	4 / 5
	Total	16 / 20 Passed

Description

46%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 a clear but terse one-liner: it states what the skill does but omits any 'when to use' trigger guidance and has no natural user-facing trigger phrases, relying on the body for triggers.

Suggestions

Add a 'Use when...' clause to the description, e.g. 'Use when reviewing an execution session, running a 3-stage check, or verifying acceptance criteria'.

Surface natural trigger terms ('evaluate this session', '3-stage check', 'verify the run') directly in the description field instead of only in the body.

Name the three stages briefly (mechanical, semantic, consensus) to lift specificity from 3 toward 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain ('execution evaluation') and one concrete mechanism ('three-stage verification pipeline'), matching the anchor that lists domain plus 1-2 concrete actions but is not comprehensive; it does not enumerate the actual stages, so it is not a 4.	3 / 5
Completeness	It gives a clear 'what' (evaluate execution via a three-stage pipeline) but no 'Use when...' or equivalent 'when' guidance; per the rubric a missing Use-when clause caps completeness at 3.	3 / 5
Trigger Term Quality	The description contains only the generic term 'Evaluate' with no natural trigger phrases or synonyms; the trigger keywords ('evaluate this', '3-stage check') live in the body, not the description, so it falls at the 'one or two generic keywords' anchor.	2 / 5
Distinctiveness Conflict Risk	The execution-evaluation niche with a verification pipeline is mostly distinct with only minor overlap risk against other evaluation skills; it lacks the concrete trigger phrases that would push it to a 5.	4 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Q00/ouroboros
Path: .claude-plugin/skills/evaluate/SKILL.md
Commit: 80333ae

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.