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 ./skills/skill-updater/SKILL.md
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 body presents a clearly sequenced five-step workflow with a genuinely useful backup command and documentation template, but a third of the guidance (planning, applying, validating) is abstract bullets lacking executable detail. Redundant Overview, When to Use, and Quick Reference sections dilute an otherwise lean document.

Suggestions

Replace abstract steps with executable detail: give the skill-validator invocation command in Step 4 and a concrete test procedure in Step 3 instead of 'Test after each change'.

Remove the redundant Purpose line, Integration bullets, and Quick Reference section — they restate the description and the step headings without adding guidance.

Add an error-recovery loop to Step 4 (e.g., 'If validation fails: revert from the backup, re-apply the last change, re-validate') to strengthen the workflow's checkpoints.

DimensionReasoningScore

Conciseness

The core steps are terse, but several sections pad without adding information: "**Purpose**: Systematic skill improvement and enhancement", the Integration bullet list, a "When to Use" section that restates the frontmatter description, and a Quick Reference that repeats the workflow a third time ("Plan → Backup → Apply → Validate → Document"). This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the level-2 anchor, since the padding is duplicative summary rather than extended over-explanation.

3 / 5

Actionability

Guidance is uneven: Step 2 provides copy-paste bash ("cp -r .claude/skills/skill-name .claude/skills/skill-name.backup-$(date +%Y%m%d)") and Step 5 a concrete log template, but Steps 1, 3, and 4 are abstract bullet lists with no executable detail — "Run skill-validator (structure, content, pattern)" gives no invocation command, and "Test after each change" says nothing about how to test. Concrete guidance exists but key execution details are missing, matching the level-3 anchor.

3 / 5

Workflow Clarity

The five steps (Plan → Backup → Apply → Validate → Document) are clearly sequenced, backup precedes mutation, and validation is a dedicated step including "Verify no regressions" and before/after comparison. It is not a 5 because there is no error-recovery loop (what to do when skill-validator fails) and the validation checkpoints are named but not operationalized; it is above a 3 because checkpoints are explicitly present as steps rather than missing or implicit.

4 / 5

Progressive Disclosure

The body is self-contained with no bundle files (no references/, scripts/, or assets/ exist), and sections are well organized with clear headers for each workflow step. Minor organization gaps — the Overview/When to Use/Quick Reference redundancy and the dangling mentions of sibling skills (skill-validator, skill-reviewer) with no pointers — keep it below the top anchor.

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 that explicitly answers both what the skill does and when to use it, with a clear 'Use when...' clause containing multiple concrete triggers. The main weakness is that the stated actions are generic process verbs (plan, implement, validate, document) rather than vivid skill-specific capabilities.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Workflow for planning updates, implementing changes, validating improvements, and documenting changes" — covering the full update lifecycle. It falls short of a 5 because the actions are process-level verbs rather than skill-specific concrete capabilities (compare 'Extract text and tables from PDF files, fill forms, merge documents'), and it stays above a 3 because four distinct actions are named with comprehensive workflow coverage.

4 / 5

Completeness

Both questions are explicitly answered: the what ("Apply improvements to Claude Code skills systematically. Workflow for planning updates, implementing changes, validating improvements, and documenting changes") and the when ("Use when applying review recommendations, updating skills based on feedback, enhancing existing skills, or implementing systematic improvements across multiple skills") with concrete trigger phrases. A clear, explicit 'Use when...' clause with multiple specific triggers matches the top anchor exactly.

5 / 5

Trigger Term Quality

Natural trigger phrases are present: "applying review recommendations", "updating skills based on feedback", "enhancing existing skills" — phrases a user would plausibly say. Not a 5 because common variations like "edit skill", "revise skill", or version-bump phrasing are absent; clearly above a 3 since multiple natural terms beyond generic keywords are covered.

4 / 5

Distinctiveness Conflict Risk

The skill- improvement niche ("Apply improvements to Claude Code skills", "applying review recommendations") is well scoped and distinct from general file- or code-editing skills. Not a 5 because "updating skills based on feedback" could mildly overlap with sibling skills in the same review/validate ecosystem (skill-reviewer, skill-validator) it references; well above a 3 since the core triggers are unlikely to fire for unrelated skills.

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.