CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

health-bugs

Inline orchestration workflow for automated bug detection and fixing with Beads integration. Provides step-by-step phases for bug-hunter detection, history enrichment for priority bugs, priority-based fixing with bug-fixer, and verification cycles.

60

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/health-bugs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 body is a highly actionable, well-sequenced orchestration workflow with strong validation gates and error-recovery loops — actionability and workflow clarity are excellent. Its main weaknesses are moderate prompt duplication between the inline phases and references/worker-prompts.md, and a redundant quick-reference table, which hurt both conciseness and progressive disclosure.

Suggestions

Remove the full inline worker-prompt blocks from Phases 2, 5, and 6 and reference the versions in references/worker-prompts.md (or keep only a one-line summary inline), eliminating the duplication.

Drop the Quick Reference table or fold it into the workflow diagram at the top, since it restates commands already shown per phase.

Trim the Phase 2.5 example block to a single representative bd search call, since the step list above it already covers the variations.

DimensionReasoningScore

Conciseness

The body is dense with commands, prompt blocks, and templates rather than concept explanations, assuming Claude's competence throughout. Minor tightening is possible: the Quick Reference table repeats phase-level Beads commands already given, and Phase 2.5's example block partly restates its own steps — noticeable but not to the level of anchor 3's 'several unnecessary explanations'.

4 / 5

Actionability

Nearly everything is copy-paste ready: exact bash commands ('bd mol wisp healthcheck', 'bd create "BUG: {bug_title}" -t bug -p {1|2} --deps discovered-from:{wisp_id}'), a full TodoWrite JSON array, complete Task-tool prompt blocks, and a ready-to-render summary template. Placeholders are appropriately parameterized for a workflow, matching the anchor-5 'copy-paste ready' standard.

5 / 5

Workflow Clarity

Phases are explicitly sequenced with a workflow diagram, an iteration cap ('Max iterations: 3'), validation checkpoints before and after each fixing priority ('pnpm type-check / pnpm build — if FAIL → suggest rollback, exit'), a verification feedback loop that re-runs detection and decides iterate-vs-complete, and a dedicated Error Handling section with rollback steps — matching the anchor-5 'explicit validation steps; feedback loops for error recovery' standard for batch code-modifying operations.

5 / 5

Progressive Disclosure

The body does point to a real one-level-deep bundle file ('See references/worker-prompts.md for detailed prompts'), but the full inline prompt blocks in Phases 2, 5, and 6 substantially duplicate the content of that reference file, i.e. content that clearly belongs in the separate file is inlined. This matches anchor 3 ('content that should be separate is inline') better than anchor 4.

3 / 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 clearly states what the skill does with several concrete, domain-specific actions, but it lacks any explicit 'when to use' trigger guidance and leans on internal jargon (Beads, bug-hunter, bug-fixer) instead of natural user phrases. Adding a 'Use when...' clause with plain-language triggers would address the two weakest dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to find and fix bugs, run a code health check, or clean up a codebase before release.'

Replace or supplement internal jargon ('Beads integration', 'bug-hunter') with natural terms users would say, such as 'bug scan', 'fix bugs automatically', 'regression check'.

Mention the full scope of phases (issue tracking, priority-based fixing order, rollback) so the capability list is comprehensive rather than partial.

DimensionReasoningScore

Specificity

Quotes several concrete actions — 'bug-hunter detection', 'history enrichment for priority bugs', 'priority-based fixing with bug-fixer', 'verification cycles' — which is specific and coverage-oriented, but it omits other phases the skill performs (issue creation/closing, rollback, summary), so it is not fully comprehensive at the score-5 anchor.

4 / 5

Completeness

The 'what' is clear ('step-by-step phases for bug-hunter detection... verification cycles'), but there is no 'Use when...' clause or equivalent trigger guidance anywhere, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Relevant keywords exist ('bug detection', 'fixing', 'verification'), but natural user phrasings like 'find and fix bugs', 'health check', 'scan my codebase', or 'regression' are absent, and terms like 'Beads integration' and 'bug-hunter'/'bug-fixer' are internal jargon rather than words a user would naturally say. It sits between anchor 3 (missing common variations) and anchor 4, closer to 3.

3 / 5

Distinctiveness Conflict Risk

The 'Beads integration' and named 'bug-hunter'/'bug-fixer' phases carve out a fairly distinct niche, but 'automated bug detection and fixing' alone would overlap with generic bug-fixing or code-review skills, so it is mostly distinct with minor overlap risk rather than a clear niche.

4 / 5

Total

14

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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/health-bugs/SKILL.md

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.