CtrlK
BlogDocsLog inGet started
Tessl Logo

defrag

Weekly vault defragmentation. Runs a 5-phase structural audit: inbox hygiene, area completeness, project archival, MOC refresh, tag consistency, structure evolution, and generates a report. Triggers: EN: "defragment the vault", "reorganize the vault", "structural maintenance", "vault defrag", "weekly defrag". IT: "deframmenta il vault", "riorganizza il vault", "manutenzione strutturale", "defrag settimanale". FR: "defragmenter le vault", "reorganiser le vault". ES: "desfragmentar el vault", "reorganizar el vault". DE: "Vault defragmentieren", "Vault reorganisieren". PT: "desfragmentar o vault", "reorganizar o vault".

68

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

68%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 well-structured, actionable multi-phase workflow with concrete paths and templates, but it performs destructive batch file operations without any validation or verification checkpoints, which caps workflow clarity. Progressive disclosure is good despite the absence of bundle files.

Suggestions

Add explicit validation checkpoints to each destructive phase (e.g., after moving files verify no broken links remain; after archiving confirm the project still resolves; after tag consolidation re-scan to confirm no orphaned tags) to lift workflow clarity above 3.

Convert open-question steps ('Are the sub-folders still relevant?') into concrete checks with a decision rule and an action so the guidance is fully executable.

Either pull the full Area Scaffolding Procedure into a bundled reference file under references/ and link to it, or remove the external agents/architect.md pointer so all needed detail is self-contained within the skill.

DimensionReasoningScore

Conciseness

Largely lean and list-driven with specific paths, assuming Claude's competence; only minor over-explanation such as 'This is a structural operation — not a quality audit (that is the Librarian's job)' could be trimmed.

4 / 5

Actionability

Gives concrete, path-specific guidance ('create `_index.md`', 'move them to `04-Archive/`', 'consolidate') with ready-to-use report and Post-it templates, though a few steps are framed as open questions ('Are the sub-folders still relevant?') rather than executable commands.

4 / 5

Workflow Clarity

The five phases are clearly sequenced with numbered steps, but this is a batch/destructive operation (moving, archiving, renaming, tag consolidation, link removal) with no validation or verification checkpoints, so per the rubric cap workflow clarity cannot exceed 3.

3 / 5

Progressive Disclosure

Well-organized into clear sections with the Area Scaffolding Procedure summarized inline and a clearly signaled one-level-deep pointer ('see the Architect agent, agents/architect.md, Section 4'), though no bundle files exist and the single external reference is outside the skill bundle.

4 / 5

Total

15

/

20

Passed

Description

95%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: third-person voice, explicit what-and-when, comprehensive multilingual triggers, and a distinct niche. The only weakness is that the listed capabilities are category nouns rather than verb-driven concrete actions, and the '5-phase' label lists six audit dimensions plus a report.

Suggestions

Reconcile the '5-phase' label with the six listed audit dimensions plus the report to avoid an internal inconsistency.

Reframe the capability list with verbs (e.g., 'Audit inbox hygiene, verify area completeness, archive completed projects, refresh MOCs, consolidate tags, evolve structure') to lift specificity from category-level to concrete-action level.

DimensionReasoningScore

Specificity

Lists six specific audit dimensions plus report generation ('inbox hygiene, area completeness, project archival, MOC refresh, tag consistency, structure evolution, and generates a report'), but these are category-level noun phrases rather than verb-driven concrete actions like the 5-anchor examples, so it sits just below comprehensive.

4 / 5

Completeness

Explicitly answers both what ('Runs a 5-phase structural audit... and generates a report') and when ('Triggers:' with concrete phrases in multiple languages), matching the anchor for clearly answering both with concrete triggers.

5 / 5

Trigger Term Quality

Provides extensive natural trigger phrases across six languages with synonyms ('defragment the vault', 'reorganize the vault', 'structural maintenance', 'vault defrag', 'weekly defrag'), matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (weekly vault structural maintenance) with distinct, domain-specific triggers that are unlikely to fire for unrelated skills, matching the minimal-conflict-risk anchor.

5 / 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.