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.

74

Quality

92%

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

The canonical home for this skill is maintenance in Chachamaru127/claude-code-harness

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a lean, well-structured overview with a clear destructive-operation workflow that includes an explicit SSOT-sync validation gate and before/after reporting. Its main weakness is actionability: the actual archive/delete operations live in cleanup.md, so the body reads more as a router than as copy-paste-ready guidance.

Suggestions

Inline a minimal executable example of the primary operation (e.g., the plans-archive one-liner from cleanup.md) so the body provides at least one copy-paste-ready command for the core task, not just a pointer to the reference.

The body references scripts/auto-cleanup-hook.sh and auto_cleanup_hook.go, but no scripts/ directory exists in the bundle — either add the scripts or remove/qualify these references to avoid dead pointers.

Surface the concrete default thresholds (PLANS_MAX_LINES=200, LOGS_RETAIN_DAYS=30, etc.) in the Quick Reference table so users get the key numeric parameters at a glance without opening cleanup.md.

DimensionReasoningScore

Conciseness

The ~57-line body is lean and assumes Claude's competence, with no explanation of concepts Claude already knows; each section (Quick Reference, steps, hook integration, notes, related skills) earns its place. It is not a 2 because there is no padded or unnecessary explanation to tighten.

3 / 3

Actionability

The body gives concrete subcommands, specific paths, and an executable backup one-liner ("cp <file> <file>.bak.$(date +%s)"), but the core archive/delete operations are delegated to cleanup.md (Step 3 says open the reference and run the section), so the body itself is incomplete executable guidance. It is not a 3 because no inline executable example of the primary operation is provided, and not a 1 because concrete commands and paths are present.

2 / 3

Workflow Clarity

The 4-step 実行手順 has a clear sequence with an explicit pre-flight validation gate (Step 2 checks the .ssot-synced-this-session flag and prompts /memory sync before touching Plans.md), plus a backup requirement and before/after reporting. It is not a 2 because validation/verification is explicitly present for the destructive batch operations rather than missing.

3 / 3

Progressive Disclosure

The body is a well-organized overview pointing to one real, one-level-deep reference ([cleanup.md](./references/cleanup.md), verified present), with content appropriately split between overview and detail. It is not a 2 because the reference is clearly signaled and shallow rather than nested or buried.

3 / 3

Total

11

/

12

Passed

Description

100%

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 is strong across all dimensions: it names concrete actions on specific file targets, supplies natural trigger terms, explicitly answers both what and when, and uses a negative-trigger exclusion list to reduce conflict risk. Voice is correctly third person.

DimensionReasoningScore

Specificity

"File cleanup and archiving. Tidies up bloated Plans.md, session-log.md, old logs, and state files" lists multiple concrete actions (cleanup, archiving, tidying) applied to specific named targets, matching the score-3 anchor of multiple specific concrete actions. It is not a 2 because the actions are paired with explicit file targets rather than only naming a domain.

3 / 3

Completeness

It states both what ("File cleanup and archiving... state files") and when via an explicit "Trigger:" clause plus a "Do NOT load for:" exclusion list. This clearly answers both what and when with explicit triggers, matching the score-3 anchor.

3 / 3

Trigger Term Quality

"Trigger: /maintenance, cleanup, archive, organize, split session-log" gives good coverage of natural terms a user would actually say, including the specific "split session-log". It is not a 2 because these are varied, user-natural keywords rather than only a single generic term.

3 / 3

Distinctiveness Conflict Risk

Specific targets (Plans.md, session-log.md, state files) plus explicit "Do NOT load for: implementation, review, release, new feature development" carve out a clear niche unlikely to trigger the wrong skill. It is not a 2 because the exclusion list removes the obvious overlap candidates.

3 / 3

Total

12

/

12

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.