CtrlK
BlogDocsLog inGet started
Tessl Logo

maintenance

File cleanup and archiving. Tidies up bloated Plans.md, session-log.md, old logs, and state files. Trigger: /maintenance, cleanup, archive, organize, split session-log. Do NOT load for: implementation, review, release, new feature development.

68

Quality

83%

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

78%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, mostly lean maintenance skill that delegates executable detail to a real one-level reference and includes the necessary destructive-operation safeguards (SSOT-sync gate, backups, dry-run, WIP exclusion, Before/After reporting). The body could tighten its contextual sections and surface a more explicit validate-then-proceed loop inline.

Suggestions

Tighten the "auto-cleanup-hook との連携" and "関連スキル" sections to one or two lines each, or fold them into the quick-reference table, to trim non-executable context.

Add an explicit "validate before proceeding" checkpoint in the 実行手順 sequence (e.g. run with --dry-run first, confirm the enumerated changes with the user, then execute) rather than relying on cleanup.md for the feedback loop.

Inline one short representative bash snippet (e.g. the logs find -delete or the state tail -2000 trim) so the most common subcommand is copy-paste ready without opening the reference.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (terse quick-reference table, numbered steps, no concept explanations), but the "auto-cleanup-hook との連携" and "関連スキル" sections are contextual handoff material that could be trimmed slightly without losing executability.

4 / 5

Actionability

Concrete subcommands, numbered execution steps, specific file paths, and an executable backup command ("cp <file> <file>.bak.$(date +%s)") are present, with the copy-paste-ready bash procedures delegated to cleanup.md; the body alone has minor gaps because the core deletion/split logic lives in the reference.

4 / 5

Workflow Clarity

A clear 4-step sequence includes an explicit SSOT-sync validation gate (step 2) and Before/After reporting (step 4), and cleanup.md adds dry-run, backups, WIP-tag exclusion, and stop-on-error; it falls short of 5 because the body's own validate-then-proceed loop is brief and the detailed feedback checkpoints rely on the reference.

4 / 5

Progressive Disclosure

A clear overview with well-organized sections points to a single one-level-deep reference ("[cleanup.md](./references/cleanup.md)") that exists and holds the detailed procedures; content is appropriately split and navigation is easy.

5 / 5

Total

17

/

20

Passed

Description

87%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, well-structured description that clearly states capabilities, provides concrete natural-language triggers, and adds explicit negative boundary guidance to avoid misfires. The only mild gap is verb distinctiveness and a few missing synonyms in the trigger list.

DimensionReasoningScore

Specificity

Names the domain and several concrete targets ("Plans.md, session-log.md, old logs, and state files") plus actions (cleanup, archiving, "split session-log"), but the core verbs (cleanup/archiving/tidying) overlap rather than being maximally distinct, leaving minor coverage gaps versus a fully comprehensive list.

4 / 5

Completeness

Explicitly answers both what ("File cleanup and archiving. Tidies up bloated Plans.md, session-log.md, old logs, and state files") and when ("Trigger: /maintenance, cleanup, archive, organize, split session-log") with concrete trigger phrases, and adds explicit negative boundary guidance.

5 / 5

Trigger Term Quality

Good keyword coverage with natural phrases users would say ("cleanup", "archive", "organize", "split session-log") plus the /maintenance slash command; falls short of 5 because a few natural synonyms (e.g. "tidy", "clear old logs") and any file-extension cues are absent.

4 / 5

Distinctiveness Conflict Risk

Clear niche (cleanup/archiving of specific internal state files) with distinct triggers, and the "Do NOT load for: implementation, review, release, new feature development" clause explicitly excludes adjacent skills, minimizing conflict risk.

5 / 5

Total

18

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
Chachamaru127/claude-code-harness
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.