CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-updater

Apply improvements to Claude Code skills systematically. Workflow for planning updates, implementing changes, validating improvements, and documenting changes. Use when applying review recommendations, updating skills based on feedback, enhancing existing skills, or implementing systematic improvements across multiple skills.

60

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-updater/SKILL.md

The canonical home for this skill is skill-updater in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

60%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 presents a clear, well-sequenced 5-step workflow with a sensible backup-first safety step, but most steps lack executable specifics and the workflow content is repeated across three sections. Adding concrete validation commands and an error-recovery loop would lift both actionability and workflow clarity.

Suggestions

Replace high-level hints in Steps 1, 3, and 4 with concrete, executable guidance — e.g., the exact command or check to run for "Test after each change" and "Run skill-validator", and measurable before/after comparison criteria.

Remove the duplicated 5-step listing from the Overview (keep the detailed Update Workflow section and the one-line Quick Reference) and trim the "When to Use" section, which restates the frontmatter description.

Add an error-recovery feedback loop to Step 4 (what to do when validation fails or a regression appears: revert from backup, fix, re-validate) to close the workflow-clarity gap.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows and has no fluff paragraphs, but the 5-step workflow is stated three times (Overview list, detailed Update Workflow section, Quick Reference) and "When to Use" restates the description, fitting the "mostly efficient but could be tightened" anchor rather than the noticeably-verbose 2 or lean 5.

3 / 5

Actionability

Step 2's backup commands (`cp -r ...`, `git commit`) are executable and the Step 5 log template is concrete, but Steps 1, 3, and 4 offer only high-level hints ("Test after each change", "Compare before/after (metrics, quality)", "Run skill-validator") with no concrete commands or criteria — incomplete concrete guidance matching the score-3 anchor.

3 / 5

Workflow Clarity

The five steps are clearly sequenced with a backup before changes and explicit validation checkpoints (Step 3 "Test after each change", Step 4 "Verify no regressions"), fitting the score-4 anchor; it misses a 5 because there is no error-recovery feedback loop describing what to do when validation fails.

4 / 5

Progressive Disclosure

The single-file body is well-sectioned (Overview, When to Use, Update Workflow, Quick Reference) with no buried references, but at ~120 lines with duplicated sections and inline content like the Updates Log template that could be split out, it fits the score-4 "minor organization gaps" anchor rather than an ideally split score-5 structure.

4 / 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/when structure and an actionable "Use when" trigger clause. Its main weaknesses are trigger terms that overlap with adjacent review/validation skills and actions phrased as generic workflow stages rather than concrete operations.

DimensionReasoningScore

Specificity

The description lists several concrete workflow actions ("planning updates, implementing changes, validating improvements, and documenting changes") comparable to the score-4 anchor, but the actions are workflow-stage names rather than fully concrete operations, so it falls short of the comprehensive coverage of a 5 and well above the 1-2 actions of a 3.

4 / 5

Completeness

It clearly answers "what" ("Apply improvements to Claude Code skills systematically. Workflow for planning updates, implementing changes, validating improvements, and documenting changes") and "when" with an explicit "Use when..." clause listing concrete trigger scenarios, matching the score-5 anchor.

5 / 5

Trigger Term Quality

It includes natural phrases users would say such as "applying review recommendations", "updating skills based on feedback", and "enhancing existing skills" — good coverage per the score-4 anchor — but misses common variations like "edit", "revise", or "SKILL.md", keeping it below a 5.

4 / 5

Distinctiveness Conflict Risk

The niche (applying improvements to existing skills) is clear, but the trigger terms overlap somewhat with closely related skills like skill-reviewer and skill-validator, fitting "mostly distinct; minor overlap risk" rather than the minimal-conflict score-5 anchor.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
fernandezbaptiste/Skrillz
Reviewed

Table of Contents

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.