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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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

The body is a well-structured, actionable workflow with strong progressive disclosure and clear sequencing, checklists, and validation offers; its only real weakness is verbosity in the conditional memory-recall and pinned-capability prose.

Suggestions

Tighten the memory-recall checkbox paragraph by extracting the gating condition and the consumer-rule filter into a short bulleted form, removing the nested parenthetical qualifications.

Move the long capability-pinning / fallback prose in Bootstrap and step 2's path-precedence list into a reference file, keeping SKILL.md to the one-line rule plus a pointer.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (no basic-concept padding), but the memory-recall checkbox paragraph and several over-qualified conditional clauses ('only when mcp.agentmemory pinned... skip silently') could be tightened; it is accurate but not fully lean.	2 / 3
Actionability	Provides concrete, executable guidance — specific MCP call signatures (e.g. mcp__plugin_agentmemory_agentmemory__memory_sessions({ limit: 20 }), session_search), a real shell command (git -C "$dir" config --get remote.origin.url \| grep -q x-skills), concrete paths, and a copy-paste JSONL log example; instruction-only yet actionable.	3 / 3
Workflow Clarity	Clear numbered sequence (1. Locate Session → 5. Present Report) with sub-steps, a status classification table, a verdict taxonomy, checklists ([ ] items), a defined output format, a severity scale, and a post-fix validation offer (Validate with /x-skill-review?).	3 / 3
Progressive Disclosure	The body is an overview that offloads detail to well-signaled one-level-deep references (argument-parsing.md, session-discovery.md, analysis-rubric.md, output-template.md), all of which exist in the bundle; navigation is clear and content is appropriately split.	3 / 3
	Total	11 / 12 Passed

Description

75%

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 cleanly answers both what and when with an explicit 'Use when' clause and a distinct niche, but its action list is somewhat abstract and its trigger terms lean technical rather than mirroring natural user phrasing.

Suggestions

Replace abstract verbs with concrete actions, e.g. '...searches Claude Code session history, classifies each instruction as followed/deviated/skipped, and proposes targeted edits to the skill.'

Add natural-user trigger phrasing such as 'improve skill from session', 'did the skill work right', or 'skill alignment check' so the description matches what users actually say.

Sharpen distinctiveness from the sibling x-skill-review by stating the session-usage basis up front, e.g. 'Use when improving a skill from how it was actually used in past sessions (vs. reviewing it speculatively).'

Dimension	Reasoning	Score
Specificity	Quotes 'evaluate x-skill alignment and improve a skill based on real session usage — searches Claude Code session history automatically' — it names the domain and a few actions (evaluate, improve, search), but the actions are more abstract than the score-3 multi-action example and not a comprehensive concrete list.	2 / 3
Completeness	Explicitly answers both — 'Use when the user wants to evaluate x-skill alignment and improve a skill based on real session usage' provides an explicit trigger clause, and the rest states what it does; satisfies the 'Use when...' requirement so it is not capped at 2.	3 / 3
Trigger Term Quality	Contains natural phrases like 'improve a skill' and 'evaluate', but leans technical with 'x-skill alignment' and 'real session usage' and omits common variations a user might say (e.g., 'did the skill work', 'fix my skill').	2 / 3
Distinctiveness Conflict Risk	The session-history-driven skill-improvement niche ('based on real session usage — searches Claude Code session history automatically') is a clear, distinct trigger unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: quangtran88/x-skills
Commit: 6381b15

Reviewed: 2 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.