skill-improver

This skill should be used when the user asks to "apply skill improvements", "update skill from plan", "execute improvement plan", "fix skill issues", "implement skill recommendations", or mentions applying improvements from quality review reports. Reads improvement-plan-{name}.md files generated by skill-quality-reviewer and intelligently merges and executes the suggested changes to improve Claude Skills quality.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-improver/SKILL.md

Quality

Content

63%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 delivers a well-sequenced, largely actionable workflow with backup and verification checkpoints, and appropriately pushes detail to reference files. Its weaknesses are notable redundancy (Priority Handling, When to Use, and Usage Examples sections restate other content), a non-executable 'read' command, and two referenced example files missing from the bundle.

Suggestions

Remove or merge redundant sections: fold "Priority Handling" into Step 4, drop the duplicated trigger-phrase list in "When to Use", and cut the "Usage Examples" section that merely restates the workflow steps.

Fix broken references: either create the referenced examples/improvement-plan-example.md and examples/update-report-example.md files or remove the pointers and the "Example Files" subsection from Additional Resources.

Add an explicit error-recovery loop after Step 6 verification, e.g. 'If verification fails: restore from ~/.claude/skills/backup/{skill-name}-{timestamp}/ and re-apply changes', and replace the pseudo-shell 'read /path/to/...' snippet with the actual Read tool invocation.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes competence, but carries several redundant sections: "Priority Handling" restates Step 4's sort order, "When to Use" duplicates the frontmatter triggers, and "Usage Examples" restate the workflow steps twice. Fits anchor 3 ('mostly efficient but includes some unnecessary explanation') rather than anchor 2 since there is no explanation of concepts Claude already knows.	3 / 5
Actionability	Concrete guidance throughout: "~/.claude/skills/skill-improver/scripts/backup-skill.sh <skill-path>", verify script invocation, backup path pattern, and a step-by-step queue structure. Not anchor 5 because "read /path/to/improvement-plan-my-skill.md" is not an executable shell command (the Read tool is meant), and the update-queue snippet is illustrative pseudocode; above anchor 3 since real commands and paths dominate.	4 / 5
Workflow Clarity	A clear six-step sequence with explicit checkpoints: validation of the plan in Step 1, backup before execution, and a four-item verification checklist plus verify script in Step 6. Not anchor 5 because the body never states what to do when verification fails (no explicit restore-backup/retry loop in SKILL.md itself); anchor 3 would require missing or implicit checkpoints, which is not the case.	4 / 5
Progressive Disclosure	References are clearly signaled inline ("See references/plan-format.md for detailed plan structure") and are one level deep, but scored against the actual bundle: the referenced "examples/improvement-plan-example.md" and "examples/update-report-example.md" do not exist in the bundle (no examples/ directory), leaving dead navigation paths. Combined with the "Additional Resources" listing duplicating the inline pointers, this sits between anchors 3 and 4 — good signaling undermined by broken referenced paths.	3 / 5
	Total	14 / 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.

A strong description with explicit what-and-when structure, concrete actions, and multiple natural trigger phrases tightly scoped to the improvement-plan workflow. Main weaknesses are a generic 'fix skill issues' trigger with some conflict risk and a slightly incomplete action inventory padded with 'intelligently'.

Dimension	Reasoning	Score
Specificity	"Reads improvement-plan-{name}.md files generated by skill-quality-reviewer and intelligently merges and executes the suggested changes" names the domain and several concrete actions (read, merge, execute). Falls short of anchor 5 because notable capabilities (backup, verification, report generation) are unmentioned, and 'intelligently' is mild fluff; above anchor 3 since more than 1-2 actions are listed.	4 / 5
Completeness	Explicitly answers 'when' ("This skill should be used when the user asks to... or mentions applying improvements from quality review reports") with concrete trigger phrases, and 'what' (reads plan files, merges and executes suggested changes). Matches the anchor-5 pattern of both what and when stated explicitly; anchor 4 would require the 'when' to be less specific than it is.	5 / 5
Trigger Term Quality	Six quoted trigger phrases ("apply skill improvements", "update skill from plan", "execute improvement plan", "fix skill issues", "implement skill recommendations") give good, natural keyword coverage. Not anchor 5 because common variations like "improve my skill" or "address the review findings" are missing, and "update skill from plan" is slightly stilted; well above anchor 3's partial coverage.	4 / 5
Distinctiveness Conflict Risk	Clear niche tied to skill-quality-reviewer's improvement-plan files, so mostly distinct with minimal overlap. Not anchor 5 because the trigger "fix skill issues" is generic enough to fire when a user wants any skill fixed without an improvement plan; above anchor 3 because the core triggers are tightly scoped to this pipeline.	4 / 5
	Total	17 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: Galaxy-Dawn/claude-scholar
Path: skills/skill-improver/SKILL.md
Commit: 9037873

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.