CtrlK
BlogDocsLog inGet started
Tessl Logo

tag-garden

Analyze all vault tags: find unused, orphan, near-duplicate, over-used, and under-used tags. Suggest merges and cleanup actions. Triggers: EN: "tag garden", "clean up tags", "tag cleanup", "tag audit". IT: "tag garden", "pulizia tag", "revisione tag". FR: "jardinage des tags", "nettoyer les tags". ES: "jardín de tags", "limpiar tags". DE: "Tag-Garten", "Tags aufräumen". PT: "jardim de tags", "limpar tags".

72

Quality

87%

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

75%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-organized, actionable instruction skill with a clear workflow and appropriate safety guardrails for batch tag operations; main room for improvement is trimming the orchestration section and adding explicit post-fix verification.

Suggestions

Move the detailed inter-agent coordination/output-format material into the already-referenced .claude/references/agent-orchestration.md and keep SKILL.md to a brief pointer, reducing token cost.

Add an explicit post-application verification step (e.g., re-running the audit to confirm merges resolved the flagged issues) to strengthen the workflow's feedback loop.

Tighten the workflow steps with concrete execution detail (e.g., how to compute usage counts) so the guidance is fully executable rather than high-level.

DimensionReasoningScore

Conciseness

The body is mostly lean operational guidance that assumes Claude's competence (no basic concept explanations), though the inter-agent coordination section with multiple output-format templates could be trimmed slightly.

4 / 5

Actionability

Provides concrete workflow steps, a copy-paste-ready report template, and an automated-fix suggestion template; the high-level workflow steps lack specific commands but the guidance is actionable for an instruction-only skill.

4 / 5

Workflow Clarity

A clear 4-step sequence (Collect → Identify → Suggest → Visualize) with explicit confirmation checkpoints for batch merges ('Apply all N fixes?', 'Conservative by default — never delete without asking'), though it lacks a post-application re-validation step.

4 / 5

Progressive Disclosure

Well-sectioned single-file structure with clearly signaled one-level references to external vault files (Meta/tag-taxonomy.md, user-profile.md, agents-registry.md); no nested references, though the orchestration material is inlined rather than split out.

4 / 5

Total

16

/

20

Passed

Description

100%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, third-person description that concretely states capabilities and provides explicit multilingual trigger guidance, cleanly answering both what the skill does and when to use it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'find unused, orphan, near-duplicate, over-used, and under-used tags' plus 'Suggest merges and cleanup actions' — giving comprehensive coverage rather than vague domain naming.

5 / 5

Completeness

Explicitly answers both 'what' (analyze vault tags, find issues, suggest merges/cleanup) and 'when' via a concrete 'Triggers:' clause with specific phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases across seven languages ('clean up tags', 'tag cleanup', 'tag audit', 'pulizia tag', etc.) provide comprehensive coverage including synonyms users would actually say.

5 / 5

Distinctiveness Conflict Risk

The vault-tag-maintenance niche with distinctive triggers ('tag garden', 'tag audit') is unlikely to fire for unrelated skills; conflict risk is minimal.

5 / 5

Total

20

/

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.