x-skill-improve

Use when the user wants to evaluate x-skill alignment and improve a skill based on real session usage — searches Claude Code session history automatically

Quality

66%

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 ./skills/x-skill-improve/SKILL.md

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.

The skill body is well-structured, actionable, and uses progressive disclosure effectively to keep the overview lean while delegating detail. The main weakness is moderate verbosity in the memory-recall/persistence blocks that could be condensed.

Suggestions

Condense the memory-recall and persist-lesson checkbox blocks into a compact one-liner plus a reference, cutting the inline parameter lists that duplicate mcp-toolbox guidance.

Make post-fix validation an enforced checkpoint rather than an optional offer, given skill edits are destructive to shared source files.

Move the severity table to a shared reference (it duplicates ../x-shared/severity-guide.md) and keep only a one-line pointer in the body.

Dimension	Reasoning	Score
Conciseness	The body mostly delegates detail to reference files and avoids re-teaching basics, but the inline memory-recall and basic-memory persistence checkbox blocks are wordy and could be tightened.	3 / 5
Actionability	Provides concrete invocation patterns, file-resolution precedence with runnable git commands, MCP call signatures with parameters, and classification/verdict tables, with only minor gaps delegated to references.	4 / 5
Workflow Clarity	A clear five-step workflow with checklists, severity guidance, and a post-fix validation offer; minor validation gaps remain since the fix-validation step is optional rather than enforced.	4 / 5
Progressive Disclosure	The body is a clean overview pointing one level deep to real, well-signaled reference files (argument-parsing, session-discovery, analysis-rubric, output-template) plus shared x-shared docs, with appropriate inline quick-reference material.	5 / 5
	Total	16 / 20 Passed

Description

62%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 well-formed with an explicit 'Use when' trigger and a clear, distinct niche, but its keyword coverage and concrete-action list are only moderate. Tightening trigger synonyms and naming more concrete actions would raise it.

Suggestions

Add natural synonyms users would actually say (e.g. 'skill alignment check', 'improve skill from session', 'did the skill work right') to broaden trigger matching.

Expand the concrete action list beyond evaluate/improve to cover the key sub-steps (e.g. 'locates past sessions, classifies deviations, proposes targeted edits').

Distinguish more sharply from sibling review skills (e.g. 'improves a skill from real usage history' vs. static review) to reduce overlap risk.

Dimension	Reasoning	Score
Specificity	Names the domain and a few concrete actions ('evaluate x-skill alignment', 'improve a skill', 'searches Claude Code session history automatically'), but the action list is not comprehensive, matching the anchor for 1-2 named actions.	3 / 5
Completeness	Both what and when are answered explicitly via the 'Use when the user wants to evaluate...' clause with concrete trigger phrasing, though the when could be a touch more specific.	4 / 5
Trigger Term Quality	Relevant keywords are present ('evaluate x-skill alignment', 'improve a skill', 'real session usage') but 'x-skill alignment' is jargon and common natural synonyms are missing.	3 / 5
Distinctiveness Conflict Risk	The 'x-skill alignment / real session usage' niche is mostly distinct, but there is minor overlap risk with the closely related sibling skill-review/improve skills.	4 / 5
	Total	14 / 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
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: quangtran88/x-skills
Path: skills/x-skill-improve/SKILL.md
Commit: f17a69e

Reviewed: 6 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.