CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bug-fix-brief

Generates a structured Bug Fix Brief (BFB) to document issue corrections. Includes root cause analysis, repro steps, fix options, and fix checklist. Use when user asks to create a BFB, document a bug fix, or generate a bug correction document.

72

Quality

91%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 tight, highly actionable skill body: a clearly sequenced four-phase workflow with an explicit confirmation gate before writing, a complete template, and a worked example. The only notable gaps are mild repetition between Best Practices/Constraints and the instructions, and no use of reference files to keep the main file shorter.

Suggestions

Consolidate the 'Best Practices' and 'Constraints and Warnings' sections — several rules (max 3 lines for cause, concise title, confirmation required) are stated two or three times across the file.

Move the full BFB template and/or the worked example into a references/ file (e.g., references/template.md, references/example.md) and link to them from the main body, shortening SKILL.md.

Include the proposed-next-number logic in Phase 1 (e.g., how to derive BFB-XXX from the ls output) so the numbering step is fully deterministic.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: no concept explanations, compact template, one worked example. However, the 'Best Practices' section partially repeats guidance already stated ('Max 3 lines for cause' appears in both the template and Constraints, and 'concise title' is stated in Phase 1, Best Practices, and Constraints) — minor instances of repetition that could be trimmed, matching the score-4 anchor rather than the 5 anchor where every token earns its place.

4 / 5

Actionability

Fully executable guidance: a concrete bash command for checking numbering, a complete fill-in template, an explicit mkdir + file path for writing, and a fully worked end-to-end example (BFB-042) with real code (AuthManager.kt:34, a specific Kotlin fix, and a testable checklist item). Copy-paste ready with specific examples covering the common case, matching the score-5 anchor.

5 / 5

Workflow Clarity

Four clearly sequenced phases (gather → generate → confirm → write) with an explicit validation checkpoint: 'Only after approval' gates the disk write, and the AskUserQuestion step provides a feedback loop (edit-before-creating before any file is created). The write is non-destructive and gated by confirmation, so this fits the 'clear sequence with explicit validation steps' anchor; below 5 would require missing or only implicit checkpoints, which is not the case.

5 / 5

Progressive Disclosure

The body is well-organized into Overview, When to Use, phased Instructions, Examples, Best Practices, and Constraints, with no nested or buried references (no bundle files exist, so there is nothing to mis-navigate). It is not under 50 lines, however, and everything — including the full template and the complete worked example — is inlined in a single file; moving the template/example to a reference file would match the score-5 anchor's 'content appropriately split'. Fits 'good structure; most content is appropriately placed; minor organization gaps'.

4 / 5

Total

18

/

20

Passed

Description

92%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 that explicitly states what the skill does and when to use it, in third person, with concrete capabilities. The main improvement area is broadening trigger vocabulary to include natural synonyms like 'bug report', 'postmortem', or 'incident writeup'.

Suggestions

Add natural synonym trigger terms such as 'postmortem', 'incident writeup', or 'bug report' to the 'Use when' clause to improve trigger term coverage.

Consider mentioning the output location (docs/bfb/) in the description so users searching for where the document lands can find the skill.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Generates a structured Bug Fix Brief (BFB)', 'root cause analysis, repro steps, fix options, and fix checklist' — giving comprehensive coverage of what the skill produces. It is entirely third person with no vague filler; it clearly matches the 'multiple specific concrete actions; comprehensive coverage' anchor rather than the score-4 anchor, which implies minor gaps in coverage.

5 / 5

Completeness

It explicitly answers what ('Generates a structured Bug Fix Brief (BFB)... Includes root cause analysis, repro steps, fix options, and fix checklist') and when ('Use when user asks to create a BFB, document a bug fix, or generate a bug correction document') with concrete trigger phrases. Both elements are explicit, matching the score-5 anchor exactly.

5 / 5

Trigger Term Quality

Trigger phrases like 'create a BFB', 'document a bug fix' are natural, but the vocabulary is narrow — missing common synonyms users would say such as 'bug report', 'postmortem', 'incident writeup', or 'root cause'. Good keyword coverage with a few natural terms missing matches the score-4 anchor; not the 5 anchor's 'comprehensive coverage of natural terms including synonyms and file extensions'.

4 / 5

Distinctiveness Conflict Risk

The BFB artifact name is a clear niche with distinct triggers ('create a BFB', 'bug fix brief'), carrying minimal conflict risk. It could be confused with general bug-fixing skills, but the trigger terms are documentation-specific; this fits 'clear niche with distinct triggers; minimal conflict risk' rather than the 4 anchor's 'minor overlap risk with closely related skills'.

5 / 5

Total

19

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

giuseppe-trisciuoglio/developer-kit

Path

plugins/developer-kit-core/skills/bug-fix-brief/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.