deepchat-sdd-cleanup

Use only when a developer explicitly asks to clean, prune, tidy, or organize DeepChat SDD documentation after implementation and validation. Scans docs/features, docs/issues, and docs/architecture; prefers multi-agent review when available; removes completed issue docs when a linked GitHub issue is closed or implementation and validation evidence proves the bug no longer exists, drops stale plans and legacy task files from completed feature or architecture goals, and deletes obsolete feature or architecture docs.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%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, lean instruction skill with concrete commands, clear sequencing, and strong guardrails for a destructive batch operation. The main gap is the absence of an explicit error-recovery feedback loop and a concrete template for the multi-agent review pass.

Suggestions

Add a concrete sub-agent invocation template for the parallel review passes (e.g., the prompt and per-directory scope) so the multi-agent step is executable rather than descriptive.

Add an explicit validate→fix→retry loop in the Validation section: after running the rg/git checks, state what to do when stale references or unexpected changes are found and that deletes only proceed once clean.

Spell out the rollback path (e.g., 'git restore <path>') so a mistaken delete can be undone before the change is committed.

Dimension	Reasoning	Score
Conciseness	Lean and purposeful with no concept explanations Claude already knows; every section (Rule, Workflow, Cleanup Rules, GitHub Checks, Never Delete, Validation) earns its place and assumes Claude's competence.	5 / 5
Actionability	Provides copy-paste-ready commands ('gh issue view <number> --json state,url,title', the rg validation string, 'git status --short') and concrete decision rules, but the multi-agent review step is described abstractly without a concrete invocation template.	4 / 5
Workflow Clarity	A clear 5-step sequence with a dedicated Validation section and a 'Never Delete' checklist plus an optional verifier pass; falls short of 5 because there is no explicit validate→fix→retry feedback loop for the destructive deletes.	4 / 5
Progressive Disclosure	No bundle files exist and none are needed; the body is a short, well-organized set of clearly headed sections with no nested references or monolithic walls, satisfying the simple-skill exception.	5 / 5
	Total	18 / 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 description: third-person voice, explicit trigger clause with natural synonym verbs, concrete enumerated actions, and a tightly scoped niche that limits conflict risk. It cleanly answers both what and when.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across named domains — 'Scans docs/features, docs/issues, and docs/architecture', 'removes completed issue docs', 'drops stale plans and legacy task files', 'deletes obsolete feature or architecture docs' — with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (scan, review, remove, drop, delete operations on named doc sets) and when ('Use only when a developer explicitly asks to clean, prune, tidy, or organize DeepChat SDD documentation after implementation and validation').	5 / 5
Trigger Term Quality	The trigger cluster 'clean, prune, tidy, or organize DeepChat SDD documentation' provides comprehensive synonym coverage of the natural verbs a developer would say, paired with the specific domain noun.	5 / 5
Distinctiveness Conflict Risk	The narrow 'DeepChat SDD documentation' niche plus the 'Use only when a developer explicitly asks' gating gives it a clear, distinct trigger with minimal overlap risk against other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

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: ThinkInAIXYZ/deepchat
Path: .agents/skills/deepchat-sdd-cleanup/SKILL.md
Commit: fa769d4

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.