cleanup-health-inline

Inline orchestration workflow for dead code detection and removal with Beads integration. Provides step-by-step phases for dead-code-hunter detection, priority-based cleanup with dead-code-remover, and verification cycles.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/cleanup-health-inline/SKILL.md

Quality

Content

81%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.

The content is a well-structured, actionable orchestration workflow with strong validation and feedback loops appropriate for a destructive batch operation. Its main weakness is minor conciseness padding and unfilled placeholder templates rather than any structural or clarity gap.

Suggestions

Consolidate the repeated 'Update TodoWrite: mark X complete' instructions into a single stated convention to reduce per-phase padding.

Provide one fully-resolved concrete example of a bd create / bd close invocation with realistic values, so the {placeholder} templates are copy-paste ready for the common case.

Move the full Markdown summary template to a short outline with a note that the detailed format is generated, to tighten token usage without losing clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with direct concrete commands and no concept-teaching of things Claude already knows, though it has minor padding (repeated per-phase TodoWrite update notes and a verbose summary template) that could be trimmed, fitting the 'efficient; minor over-explanation' anchor.	4 / 5
Actionability	Provides concrete executable bash (mkdir, bd create, pnpm type-check, bd close) and full Task-tool prompt bodies with clear placeholders, matching 'mostly executable; concrete code with minor gaps' rather than 5 (some placeholders like {item_title} are not pre-filled for the common cases).	4 / 5
Workflow Clarity	A clear 7-phase sequence with explicit validation checkpoints (Phase 4 pre-removal gate, per-priority gates in Phase 5) and a genuine feedback loop (Phase 6 verification -> re-scan -> retry up to 3 iterations) plus rollback/error handling, hitting the 'explicit validation with feedback loops' anchor for a destructive batch operation.	5 / 5
Progressive Disclosure	No bundle files exist and the skill is a single well-sectioned file (phases, error handling, quick-reference table) with no nested references; structure is good with only minor organization gaps (inline full TodoWrite/summary templates), fitting the 'good structure; minor organization gaps' anchor rather than 5 (no one-level-deep references, though none are warranted here).	4 / 5
	Total	17 / 20 Passed

Description

58%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.

The description is specific and clearly scoped to dead-code cleanup, but it omits any explicit 'Use when...' trigger guidance, which caps completeness at 3 and limits the trigger-term coverage. Adding a concrete when-to-use clause with common synonyms would lift the two weakest dimensions.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user asks to find or remove dead code, unused imports/exports, or unreachable code') to satisfy the completeness 'when' requirement and raise the cap.

Include natural synonyms users actually say ('unused code', 'unused exports', 'unreachable code') alongside 'dead code' to broaden trigger-term coverage.

Drop or de-emphasize user-facing jargon like 'Beads integration' and 'inline orchestration' from the description since they are not terms a user would naturally say.

Dimension	Reasoning	Score
Specificity	Names the dead-code domain and multiple concrete actions ('dead code detection and removal', 'priority-based cleanup', 'verification cycles') with specific tools (dead-code-hunter, dead-code-remover), matching the 'several specific actions; minor gaps' anchor rather than 3 (more than 1-2 actions) or 5 (issue creation/tracking not enumerated).	4 / 5
Completeness	Clearly answers 'what' (detection/removal workflow with phases) but provides no explicit 'when'/Use-when trigger guidance, which per the rubric caps completeness at 3 even though the what-side is strong.	3 / 5
Trigger Term Quality	Includes natural terms a user might say ('dead code', 'cleanup', 'dead code detection and removal') but misses common synonyms ('unused code', 'unused exports') and mixes in jargon ('Beads integration', 'inline orchestration') users would not say, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Scoped to a specific niche (dead code cleanup with Beads-tracked orchestration and named subagents) with distinct triggers and only minor overlap risk with general cleanup skills, fitting the 'mostly distinct; minor overlap risk' anchor.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: maslennikov-ig/claude-code-orchestrator-kit
Path: .claude/skills/cleanup-health-inline/SKILL.md
Commit: 8c3b576

Reviewed: 6 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.