CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

auto-updater

Automatically apply improvements to skills and the ecosystem based on system-reviewer findings and best-practices-learner insights. Workflow for automated improvement identification, priority assessment, safe application, validation, and rollback capability. Use when applying systematic improvements, automating enhancement cycles, bulk updating multiple skills, or implementing ecosystem-wide improvements.

Quality

72%

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/auto-updater/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

66%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 an exceptionally clear 5-step workflow with explicit validation and rollback feedback loops appropriate to a batch-modification skill, and organization is solid. It is held back by duplicated content (the safe/unsafe lists and triple workflow summary) and validation steps that name tools without providing executable commands.

Suggestions

Remove the duplicated Safe/NOT-Safe automation lists (keep only the Quick Reference copy) and collapse the triple workflow summary into the detailed steps plus the Quick Reference table.

Replace vague validation directions with the concrete commands or invocation syntax for running skill-validator and the review-multi structure check, and drop the per-step wall-clock time estimates, which are not actionable for Claude.

Provide a concrete template or before/after snippet for a standard update (e.g., the Quick Reference section format used in the example) so the 'apply' step is copy-paste ready.

DimensionReasoningScore

Conciseness

The bullet-driven body assumes Claude's competence and explains no known concepts, but the Safe/NOT-Safe automation lists are duplicated verbatim in Step 2 and Quick Reference, the 5-step workflow is summarized three times (Overview, detailed steps, Quick Reference table), and per-step wall-clock estimates ('15-30 minutes') add padding, so it could be meaningfully tightened.

3 / 5

Actionability

Concrete process steps and named validators exist ('Backup affected skills (git commit or copy)', 'Run skill-validator (pass/fail)', 'Run review-multi structure check'), but no executable commands or invocation syntax are given, and the example is a simulated outcome transcript rather than instructions — key execution details are left to inference.

3 / 5

Workflow Clarity

The batch-operation validation cap does not apply because validation is explicit: five clearly sequenced steps each declare outputs, Step 4 validates every updated skill (validator pass/fail, structure check, visual inspection), and Step 5 is a full feedback loop (identify failure, restore backup, analyze why, mark manual-only) with backup-first and one-skill-at-a-time ordering.

5 / 5

Progressive Disclosure

No bundle files exist, so all content is inline in one file; sections are well organized (Overview, When to Use, Steps, Example, Quick Reference) with clear headers and nothing buried, but the ~35-line simulated example could live in a separate file and there is no quick-start orientation — good structure with minor gaps.

4 / 5

Total

15

/

20

Passed

Description

67%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.

The description clearly answers what the skill does and when to use it, with a well-scoped niche (validated auto-application of improvements with rollback). Its weaknesses are trigger phrasing that leans on internal ecosystem jargon and trigger clauses that restate the skill's function rather than naming natural user situations.

Suggestions

Replace jargon-heavy triggers ('automating enhancement cycles', 'ecosystem-wide improvements') with phrases a user would naturally say, such as 'after running a skill review', 'apply the reviewer's recommended fixes', or 'add a missing section to all skills'.

Ground the 'what' in concrete artifacts — e.g., which sections or templates get added or edited in SKILL.md files — instead of the abstract term 'improvements'.

DimensionReasoningScore

Specificity

Lists several specific actions ('improvement identification, priority assessment, safe application, validation, and rollback capability'), matching the several-actions anchor rather than the comprehensive one, since 'improvements' remains abstract with no concrete artifact-level actions named.

4 / 5

Completeness

Both a clear 'what' (apply improvements from system-reviewer findings and best-practices-learner insights) and an explicit 'Use when' clause with four triggers are present, but the triggers largely restate the what ('apply improvements... use when applying systematic improvements') instead of naming concrete user situations, so the 'when' could be more specific.

4 / 5

Trigger Term Quality

'bulk updating multiple skills' is a natural phrase, but 'automating enhancement cycles', 'systematic improvements', and 'ecosystem-wide improvements' read as internal jargon rather than what a user would naturally say, and common variations or synonyms are missing.

3 / 5

Distinctiveness Conflict Risk

The skill is tied to a distinct niche — auto-applying validated improvements sourced from specific companion skills ('system-reviewer findings and best-practices-learner insights') — with only minor overlap risk from generic triggers like 'applying systematic improvements'.

4 / 5

Total

15

/

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

Path

.claude/skills/auto-updater/SKILL.md

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.