skill-refactor

Analyzes bounded skill evidence, classifies root causes, and recommends a lifecycle lane such as keep, observe, improve through Skill Factory hardening, merge with approval, or retire with approval. Use when a skill is not working, a skill is not triggering correctly, evals or Tessl disagree, repeated failures need debugging, or skill performance issues need evidence-backed repair handoff items.

Quality

92%

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 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a concrete output template, clear gated workflow, and well-structured external references that all resolve. Its main weakness is verbosity and repetition of the approval/gating language across several sections.

Suggestions

Consolidate the repeated 'do not edit, merge, retire, install, sync, publish, or write externally without approval' phrasing into a single Execution Boundaries statement and reference it elsewhere rather than restating it.

Trim redundancy between First-Principles Gate, Constraints, and Execution Boundaries, which restate overlapping approval and evidence-strength rules.

Consider moving the long SDK handoff proof ladder enumeration (step 7 and Validation) into a reference file so the core workflow stays lean.

Dimension	Reasoning	Score
Conciseness	The body is information-dense but repeats the same approval and gating language across First-Principles Gate, Constraints, Execution Boundaries, and Validation (e.g. 'do not edit, merge, retire, install, sync, publish...'). It is mostly efficient yet could be tightened, so it is not the lean score-3 nor the padded score-1.	2 / 3
Actionability	Provides a copy-paste-ready YAML output template with exact field names, a worked example, and concrete commands such as './bin/ask sdk start <skill-path> --json --robot' plus an enumerated SDK handoff gate ladder. Fully executable guidance, not the incomplete score-2.	3 / 3
Workflow Clarity	A clearly sequenced 7-step workflow with explicit validation checkpoints ('stop at the first failed gate', 'Fail fast') and a blocked->request-evidence feedback loop for recovery. This matches the explicit-validation-with-feedback-loops anchor.	3 / 3
Progressive Disclosure	SKILL.md is an overview with well-signaled one-level-deep references (taxonomy, discovery-interview, evidence-routing, harness-evidence-mapping) and an assets image; all referenced paths exist as real bundle files and detail is appropriately split out.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 specific, trigger-rich, and complete with explicit what-and-when guidance in third person. It is well-positioned to fire for the right skill and avoid conflicts.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Analyzes bounded skill evidence, classifies root causes, and recommends a lifecycle lane'), matching the multiple-specific-actions anchor rather than the single-action score 2.	3 / 3
Completeness	Explicitly answers what (analyze, classify, recommend lifecycle lane) and when via an explicit 'Use when...' clause with concrete triggers. Not score 2 because the 'when' is explicit, not implied.	3 / 3
Trigger Term Quality	Covers natural user phrasing such as 'a skill is not working', 'not triggering correctly', 'evals or Tessl disagree', and 'repeated failures need debugging'. It is not the level below because it goes beyond a single keyword to several common variations.	3 / 3
Distinctiveness Conflict Risk	Targets a distinct lifecycle-routing niche (evidence-backed repair handoff, eval/Tessl disagreement) unlikely to conflict with creation or install skills, and uses third-person voice throughout.	3 / 3
	Total	12 / 12 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_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Plugins/skill-factory/skills/data_fetch_analysis/skill-refactor/SKILL.md
Commit: 46e4be2

Reviewed: 4 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.