CtrlK
BlogDocsLog inGet started
Tessl Logo

deep-clean

Extended vault cleanup: full audit PLUS stale content scan, outdated references, content quality review, redundant tags, broken external links, and template compliance. Triggers: EN: "deep clean", "deep cleanup", "thorough cleanup", "the vault is a mess". IT: "pulizia profonda", "pulizia completa", "il vault è un disastro". FR: "nettoyage en profondeur", "le vault est un désordre". ES: "limpieza profunda", "el vault es un desastre". DE: "Tiefenreinigung", "das Vault ist ein Chaos". PT: "limpeza profunda", "o vault está uma bagunça".

64

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 ./tests/regression/snapshot/.claude/skills/deep-clean/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

A detailed, actionable audit workflow with clear sequencing and strong safety principles, but it is monolithic and verbose and lacks a post-fix verification feedback loop that the rubric expects for batch/destructive operations.

Suggestions

Add an explicit validation/re-scan step after applying batch fixes (e.g., re-run the link and duplicate checks to confirm issues are resolved before writing the health report) to close the validate→fix→retry loop.

Move the large health-report and stale-content output templates into a bundled reference file (e.g. references/report-templates.md) and summarize them inline, reducing token cost and improving progressive disclosure.

De-duplicate the legacy agent-messages.md cleanup instruction — it appears in both Inter-Agent Coordination and Phase 6 — and tighten the placeholder-heavy report template.

DimensionReasoningScore

Conciseness

Mostly efficient actionable steps, but the body is long and padded by a large health-report template full of {{N}} placeholders, and the legacy agent-messages cleanup is repeated in both Inter-Agent Coordination and Phase 6 — could be tightened.

3 / 5

Actionability

Gives concrete paths (Meta/vault-structure.md, Meta/tag-taxonomy.md), specific checks, and example output blocks; minor gaps remain in vague phrasing like 'based on a quick comparison' and 'if tools available'.

4 / 5

Workflow Clarity

The 7-phase + 6-pass sequence is clearly ordered with user-confirmation gates, but there is no validate→fix→retry feedback loop (e.g., re-scan after applying fixes), and the rubric caps batch/destructive skills at 3 when that loop is missing.

3 / 5

Progressive Disclosure

References to vault/orchestration files are clearly signaled and one level deep, but no skill bundle files exist and the long output templates are inlined in a single monolithic document rather than split out.

3 / 5

Total

13

/

20

Passed

Description

96%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, specific description that clearly states what the skill does and when to use it, with rich multilingual trigger coverage. The only soft spot is mild overlap risk with the lighter audit/clean skill it extends.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'full audit', 'stale content scan', 'outdated references', 'content quality review', 'redundant tags', 'broken external links', 'template compliance' — giving comprehensive coverage rather than a single generic verb.

5 / 5

Completeness

Explicitly answers both 'what' (extended vault cleanup with a concrete action list) and 'when' via a dedicated 'Triggers:' clause with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Comprehensive natural terms including synonyms ('deep clean', 'deep cleanup', 'thorough cleanup') and the colloquial 'the vault is a mess', plus equivalent phrases across six languages — well beyond the anchor's synonym coverage.

5 / 5

Distinctiveness Conflict Risk

'full audit PLUS ...' carves a clear deep-clean niche with distinct triggers, but the 'PLUS' framing implies overlap with a base audit/clean skill it extends, so minor conflict risk remains.

4 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
gnekt/My-Brain-Is-Full-Crew
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.