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

80%

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

70%

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

The body presents a clear, well-sequenced workflow with explicit verification checkpoints and good progressive disclosure into real reference files and scripts. Its weaknesses are moderate verbosity from duplicated priority/best-practices content and abstract central execution guidance that defers the real logic to references.

Suggestions

Collapse the standalone 'Priority Handling' section and the Before/During/After 'Best Practices' into the existing steps to remove redundancy and reduce token cost.

Make the core 'Apply changes' step more actionable with a concrete Edit/Write decision example showing file path, current snippet, and suggested snippet rather than the abstract tool-use summary.

Either create the referenced example files (examples/improvement-plan-example.md, examples/update-report-example.md) or remove the dangling references to avoid broken navigation.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with a clear step structure, but repeats content: the 'Priority Handling' section restates the High/Medium/Low ordering already covered in Steps 4 and 5, and 'Best Practices' Before/During/After largely restate the workflow steps. Not 3 due to this redundant padding; not 1 because it avoids explaining concepts Claude already knows and is not a wall of fluff.	2 / 3
Actionability	Quotes concrete guidance like '~/.claude/skills/skill-improver/scripts/backup-skill.sh <skill-path>' and the update-report field list, but the core 'Apply changes' step is abstract ('Use Edit tool for existing content, Use Write tool for new files') and the by_file block is illustrative pseudocode rather than executable logic. Not 3 because the central execution guidance is not copy-paste ready; not 1 because real script invocations and checklists are provided.	2 / 3
Workflow Clarity	Quotes a clear six-step sequence with explicit validation in Step 6 ('Verification checks: 1. YAML syntax valid...') plus a verify script invocation, and feedback loops via backup/restore for this batch/destructive operation. Not 2 because validation checkpoints and error-recovery paths are explicit rather than missing or implicit.	3 / 3
Progressive Disclosure	Quotes well-signaled one-level references ('See references/plan-format.md', 'See references/merge-strategies.md') backed by real files, plus a References/Scripts listing; detail is appropriately split out. Not 2 because the overview points cleanly to one-level-deep real bundles rather than nesting references; the only minor defect is two cited example paths (examples/improvement-plan-example.md, examples/update-report-example.md) that do not exist, which is not enough to drop it below the strong-structure anchor.	3 / 3
	Total	10 / 12 Passed

Description

90%

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 clearly states what the skill does and when to use it, with strong, natural trigger phrases and a distinct niche tied to skill-quality-reviewer's improvement plans. The only weaker area is specificity, where the action verbs are generic rather than a comprehensive list of concrete operations.

Suggestions

Replace generic verbs ('reads, merges, executes') with more specific concrete operations, e.g. 'parses High/Medium/Low priority items, resolves line-range conflicts, backs up originals, applies edits, and verifies YAML integrity'.

Tighten the description length; the long trigger list could keep the most common three phrases and drop redundant synonyms to stay within an ideal character range.

Dimension	Reasoning	Score
Specificity	Quotes 'Reads improvement-plan-{name}.md files' and 'intelligently merges and executes the suggested changes' name the domain and a few actions, but the verbs (reads, merges, executes) are generic and applied to a single object rather than a comprehensive list of concrete actions. Not 3 because it lacks multiple distinct specific actions; not 1 because it does name concrete actions and domain.	2 / 3
Completeness	Quotes 'This skill should be used when the user asks to...' (explicit when) and 'Reads improvement-plan...merges and executes...to improve Claude Skills quality' (explicit what). Both what and when are clearly answered with explicit triggers, matching the 3 anchor. Not 2 because the when is explicit, not merely implied.	3 / 3
Trigger Term Quality	Quotes six natural trigger phrases a user would say ('apply skill improvements', 'update skill from plan', 'execute improvement plan', 'fix skill issues', 'implement skill recommendations') giving good coverage of natural terms. Not 2 because the coverage is broad and user-aligned rather than missing common variations.	3 / 3
Distinctiveness Conflict Risk	Quotes 'improvement-plan-{name}.md files generated by skill-quality-reviewer' and the trigger set tie the skill to a specific reviewer's output, giving it a clear niche unlikely to conflict with other skills. Not 2 because the triggers are distinctive and anchored to a specific workflow, not broadly overlapping.	3 / 3
	Total	11 / 12 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: 2f7766f

Reviewed: about 12 hours 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.