CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 an exemplary lean orchestrator page: concise, well-sequenced routing with an explicit stop-on-failure escalation rule. Its effectiveness is undermined, however, by the fact that every file it dispatches to is missing from the bundle, leaving the skill non-executable as delivered despite its clean structure.

Suggestions

Ship the referenced bundle files (commands/*.md, skills/controller.md, skills/unattended.md, guidelines.md) alongside SKILL.md, or inline the minimal content needed for each dispatch path so the skill is executable as delivered.

Add a fallback for missing dispatch targets (e.g., "if commands/{command}.md does not exist, list the available phases and ask the user") so routing does not dead-end when a file is absent.

State where the command and skill files live relative to the skill root (or verify the paths resolve after installation) so the progressive-disclosure pointers are guaranteed to be navigable.

DimensionReasoningScore

Conciseness

The 15-line body is lean and dense: numbered dispatch steps, a failure-handling rule, and one pointer — no explanation of concepts Claude already knows and nothing to trim. Matches the "every token earns its place" anchor; not 4 because there are no instances of over-explanation at all.

5 / 5

Actionability

Routing guidance is concrete and conditional ("read `commands/{command}.md` and follow it", "If the user provided a bug report or issue URL, execute the `/assess` phase"), but every actionable path terminates in a file (commands/, skills/controller.md, skills/unattended.md, guidelines.md) that is not shipped in the skill bundle, so the instructions cannot actually be executed. Not 4: missing the entire referenced bundle is more than a minor gap; not 2: the dispatch logic itself is specific and well-structured.

3 / 5

Workflow Clarity

A clearly numbered 1-2-3 sequence with explicit branch conditions and an explicit validation checkpoint with recovery options ("If a step fails or produces unexpected output, stop and report the error to the user. Do not advance to the next phase. Offer to retry the failed step or escalate."). Not 5: the underlying phase-by-phase workflow and its validation are delegated to unshipped files, so only the routing layer is specified here; not 3: a stop-on-failure checkpoint with escalation is explicitly present.

4 / 5

Progressive Disclosure

The structure is right — one-level-deep pointers, each clearly signaled with its purpose ("For principles, hard limits, safety, quality, and escalation rules, see `guidelines.md`") — but scored against the actual bundle, none of the referenced files (commands/{command}.md, skills/unattended.md, skills/controller.md, guidelines.md) exist, so the navigation is unresolvable as shipped. Not 4: broken reference targets are more than a minor organization gap; not 2: nothing is wrongly inlined and references are prominently, not buriedly, signaled.

3 / 5

Total

15

/

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: third-person, concise, with four concrete capability statements and an explicit, well-phrased "Use when" clause. Trigger coverage is good with synonym variation; the only weakness is minor collision risk from generic slash-command names and the PR-submission trigger.

DimensionReasoningScore

Specificity

"analyzes error logs, traces root causes, implements fixes, and verifies with regression tests" lists four concrete actions covering the full diagnose-to-verify arc, matching the comprehensive-coverage anchor. Not 4: there are no coverage gaps in the stated workflow.

5 / 5

Completeness

Clearly answers both: what ("analyzes error logs, traces root causes, implements fixes, and verifies with regression tests") and when ("Use when fixing bugs, debugging runtime errors or exceptions...") with concrete trigger phrases. Not 4: the when-clause is explicit and specific rather than merely present.

5 / 5

Trigger Term Quality

"fixing bugs, debugging runtime errors or exceptions, investigating test failures or crashes" provides good natural-phrase coverage with synonym pairs (errors/exceptions, failures/crashes). Not 5: common phrasings like "stack trace", "traceback", or "why is X failing" are absent.

4 / 5

Distinctiveness Conflict Risk

The bug-diagnosis/repair niche is mostly distinct, but "submitting bug-fix pull requests" and generic commands like "/review, /test, /document" overlap with PR-generation and review skills. Not 5 due to that minor overlap; not 3 since the core triggers are firmly scoped to bug fixing rather than broadly generic.

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

flightctl/ai-workflows

Path

bugfix/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.