CtrlK
BlogDocsLog inGet started
Tessl Logo

bugfix

Diagnostic and repair workflow that analyzes error logs, traces root causes, implements fixes, and verifies with regression tests. Use when fixing bugs, debugging runtime errors or exceptions, investigating test failures or crashes, or submitting bug-fix pull requests. Activated by commands: /unattended, /assess, /diagnose, /reproduce, /fix, /test, /review, /document, /pr, /feedback, /start.

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

Low

Low-risk findings worth noting

The canonical home for this skill is bugfix in flightctl/ai-workflows

SKILL.md
Quality
Evals
Security

Quality

Content

96%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.

An exemplary lean orchestrator body: unambiguous routing, explicit stop-on-failure validation with retry/escalate, and clearly signaled one-level-deep references with no token waste. The single material defect is that the referenced bundle files (commands/, skills/, guidelines.md) are absent, so the progressive-disclosure structure cannot actually deliver its destinations.

Suggestions

Ship the referenced bundle files (commands/{command}.md for each listed command, skills/unattended.md, skills/controller.md, guidelines.md) or inline minimal stubs so the routing targets resolve.

Consider a fallback line for when a referenced command file is missing, mirroring the existing stop-and-report failure policy.

DimensionReasoningScore

Conciseness

The ~15-line body is pure routing and safety instruction with zero padding — every sentence either directs the next action, defines the failure policy, or points to guidelines. It assumes Claude's competence and matches the 'lean and efficient; every token earns its place' anchor; a 4 would require minor trimming, which is not needed.

5 / 5

Actionability

The guidance is fully executable as instruction-only content: 'read commands/{command}.md and follow it', 'read skills/unattended.md', 'read skills/controller.md', with explicit conditional branches (bug report present → /assess, else → /start). Per the scoring notes, absence of code in an instruction-only skill is not penalized when the guidance is this actionable; a 4 would require minor gaps in specificity.

5 / 5

Workflow Clarity

The numbered Quick Start gives a clear decision sequence, and the failure policy — 'If a step fails or produces unexpected output, stop and report the error... Offer to retry the failed step or escalate' — is an explicit validation checkpoint with a retry/escalate feedback loop. This matches the top anchor with explicit validation steps and error-recovery loops; a 4 would have only most checkpoints present.

5 / 5

Progressive Disclosure

Structure is clean and well-signaled with one-level-deep references (commands/{command}.md, skills/unattended.md, skills/controller.md, guidelines.md), fitting 'good structure; references mostly clear'. However, none of these referenced files exist in the bundle (no commands/, skills/, or guidelines.md are present), so the skill's core routing targets are missing and navigation breaks — a gap that keeps it below the 5 anchor's 'easy navigation' bar.

4 / 5

Total

19

/

20

Passed

Description

88%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: concrete four-action capability statement paired with an explicit, natural 'Use when...' trigger clause in third-person voice. Keyword coverage is good but misses a few common phrasings (stack traces, regressions), and the PR/review-related triggers introduce minor overlap with adjacent code-workflow skills.

Suggestions

Add a few missing natural trigger terms such as 'stack traces', 'regressions', or 'CI failures' to trigger_term_quality coverage.

Narrow the PR-related trigger (e.g., 'when a bug fix is ready to be packaged into a pull request') to reduce overlap with dedicated PR/commit-message skills.

DimensionReasoningScore

Specificity

The description lists four concrete actions — "analyzes error logs, traces root causes, implements fixes, and verifies with regression tests" — which comprehensively covers the diagnostic-and-repair workflow. This matches the anchor for multiple specific concrete actions with comprehensive coverage; a 4 would require minor coverage gaps, which are not evident.

5 / 5

Completeness

It explicitly answers both 'what' (the four diagnostic/repair/verify actions) and 'when' ("Use when fixing bugs, debugging runtime errors or exceptions, investigating test failures or crashes, or submitting bug-fix pull requests") with concrete trigger phrases. This matches the top anchor; a 4 would require the 'when' clause to be less explicit or specific.

5 / 5

Trigger Term Quality

Triggers include natural phrases users would say — "fixing bugs", "debugging runtime errors or exceptions", "investigating test failures or crashes", "submitting bug-fix pull requests" — with good synonym coverage. A few common natural terms are still missing (e.g., "stack traces", "regressions", "broken builds"), which fits the 'good keyword coverage; a few natural terms missing' anchor rather than the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

The bugfix diagnostic/repair niche is clear with distinct triggers, but "submitting bug-fix pull requests" and the broad command list (/pr, /review, /document) create minor overlap with PR-writing, commit-message, and code-review skills. This fits 'mostly distinct; minor overlap risk with closely related skills' rather than the minimal-conflict 5.

4 / 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.

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
amir-yogev-gh/ai-workflows
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.