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

74%

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 ./Infrastructure/references/deferred-skill-context/skill-factory-skill-refactor/SKILL.md

Quality

Content

60%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, instruction-oriented skill body with clear sequencing and validation, but it is held back by redundant evidence-handling rules spread across several sections, high-level procedure steps, and a couple of broken asset reference paths.

Suggestions

Consolidate the repeated 'do not invent/infer evidence' guidance from Constraints, Anti-patterns, and Gotchas into a single canonical statement to tighten conciseness.

Add concrete, executable specifics to the procedure steps (e.g. the actual collector invocation or the exact command form) rather than delegating all detail to reference files.

Fix or remove the broken asset references to ./agents/assets/icon-small.png and icon-large.png, which do not exist in the bundle.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but the same evidence-handling rule is restated across Constraints ('Do not invent evidence'), Anti-patterns ('Concluding low quality without citing failure evidence'), and Gotchas ('Do not infer outcomes without evidence'), which could be consolidated.	3 / 5
Actionability	It names concrete artifacts (collector root, two scripts, root-cause taxonomy, output table), but the six procedure steps themselves stay high-level ('Gather evidence...', 'Rank recommendations by impact, confidence, and implementation cost') without executable specifics in the body.	3 / 5
Workflow Clarity	A clearly sequenced six-step procedure is paired with an explicit Validation section and a 'Fail fast: stop at first missing or unreadable evidence source' checkpoint, covering most validation needs for this batch analysis task.	4 / 5
Progressive Disclosure	Content is well split into a lean overview with one-level-deep, clearly signaled references (contract.yaml, session-evidence-workflow.md, scripts), though some referenced asset paths (./agents/assets/icon-small.png, icon-large.png) do not exist in the bundle.	4 / 5
	Total	14 / 20 Passed

Description

88%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, specific description that clearly states capabilities and an explicit 'Use when' trigger clause with natural phrasing. Its only weakness is minor overlap risk with adjacent skill-lifecycle skills and a few missing synonym triggers.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Scan Codex session history for skill failures, usage patterns, and coverage gaps' and 'recommendations about installing, improving, merging, or pruning skills' — giving comprehensive, specific coverage rather than vague language.	5 / 5
Completeness	It explicitly answers both what (scan session history for failures, patterns, gaps and produce recommendations) and when ('Use when the user wants daily skill-health monitoring or evidence-backed recommendations...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases like 'skill failures', 'daily skill-health monitoring', and 'installing, improving, merging, or pruning skills' map well to user requests, though common variations such as 'audit my skills' or 'which skills to keep' are absent.	4 / 5
Distinctiveness Conflict Risk	The Codex-session-history plus skill-reliability niche is clearly distinguished, but related skills mentioned in the body (e.g. skillify, general skill review) create minor overlap risk on the install/merge/prune triggers.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 2 missing, 2 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Infrastructure/references/deferred-skill-context/skill-factory-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.