skill-refactor

Scan Codex session history for skill failures, usage patterns, and coverage gaps. Use when the user wants daily skill-health monitoring or evidence-backed recommendations about installing, improving, merging, or pruning skills.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./Plugins/skill-factory/fixtures/budget-archive/2026-04-19/skills/data_fetch_analysis/skill-refactor/SKILL.md

Quality

Content

51%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 admirably concise but underspecifies execution: it states an objective and one reference while leaving the actual scripts, workflow sequence, and validation steps unmentioned. Actionability and workflow clarity suffer most because the bundle's executable material is never surfaced.

Suggestions

Name and briefly describe the bundled scripts (e.g. scan_codex_sessions.pyw, correlate_multi_source_skill_failures.pyw) with invocation examples so Claude knows how to execute the analysis.

Add a short sequenced workflow (scan sessions -> correlate failures -> prioritize recommendations) with a validation checkpoint before returning recommendations, mirroring the rollback/observability gates in contract.yaml.

Link to or signpost the other relevant bundle files (scripts/, assets/skill-refactor.png) so progressive disclosure covers the whole skill, not just contract.yaml.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean — a one-line objective plus a single reference pointer — with no padding or over-explanation of concepts Claude already knows, so every token earns its place per anchor 5.	5 / 5
Actionability	The body gives only a high-level objective ('Analyze skill reliability from session evidence and return prioritized recommendations') with no concrete code, commands, or named scripts, even though executable scripts exist in the bundle, leaving the specific execution steps missing per anchor 2.	2 / 5
Workflow Clarity	No sequenced steps or validation checkpoints are provided; the implied scan-then-correlate process and the validation gates described in contract.yaml are never surfaced in the body, leaving only a rough implied single action per anchor 2.	2 / 5
Progressive Disclosure	The body signals one real one-level-deep reference (contract.yaml, which exists), but it ignores the analysis scripts and asset that form the bulk of the bundle, so much of the relevant material is unmentioned and navigation is incomplete per anchor 3.	3 / 5
	Total	12 / 20 Passed

Description

83%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 clearly states both what the skill does and when to use it with concrete, mostly-distinct trigger phrases. Minor gaps in action comprehensiveness and trigger-term synonyms keep specificity, trigger quality, and distinctiveness at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the domain (Codex session history) and several concrete actions ('Scan... for skill failures, usage patterns, and coverage gaps', 'recommendations about installing, improving, merging, or pruning skills'), but coverage of concrete actions is not fully exhaustive, sitting just below the comprehensive anchor 5.	4 / 5
Completeness	Explicitly answers both 'what' ('Scan Codex session history for skill failures, usage patterns, and coverage gaps') and 'when' ('Use when the user wants daily skill-health monitoring or evidence-backed recommendations about installing, improving, merging, or pruning skills') with concrete trigger phrases, matching the anchor 5 example.	5 / 5
Trigger Term Quality	Includes natural phrases a user might say ('daily skill-health monitoring', 'installing, improving, merging, or pruning skills') with good coverage, but the triggers lean toward longer compound phrases and miss some common simple synonyms, keeping it below anchor 5.	4 / 5
Distinctiveness Conflict Risk	The skill has a clear niche (Codex session-history analysis for skill health) with mostly distinct triggers and minimal overlap risk, but phrases like 'evidence-backed recommendations' are slightly broad, so it sits below the tightly-differentiated anchor 5.	4 / 5
	Total	17 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Plugins/skill-factory/fixtures/budget-archive/2026-04-19/skills/data_fetch_analysis/skill-refactor/SKILL.md
Commit: 2f91362

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.