CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

qa-bug-reporting

Write, dedupe, and rank defect records with minimal repro steps, expected-versus-actual results, sanitized evidence, reproducibility counts, and root-cause confidence. Use whenever a test fails or an anomaly is found.

67

Quality

84%

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

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.

An efficient, well-sequenced procedure body whose main weaknesses are two dangling artifacts: the referenced bug-report template file does not exist in the bundle, and "pattern F4" is never defined. Fixing those would make the guidance fully executable.

Suggestions

Add the actual templates/bug-report.md file (with its field list) to the bundle, or inline the template's required fields in the body so step 3 is executable.

Define or remove the unexplained "pattern F4" reference in step 6, e.g. replace it with the concrete reachability check it names.

Add brief guidance for the non-reproducible case (e.g., how a failure that cannot be reproduced from a clean state is recorded and ranked) to close the workflow validation gap.

DimensionReasoningScore

Conciseness

The body is lean and fully instructional ("Reproduce at least twice from a clean state. Record failures over attempts."), assumes Claude's competence, explains no known concepts, and has no padding, matching the every-token-earns-its-place anchor.

5 / 5

Actionability

Most steps give specific, executable guidance (reproduction counts, redaction list, CONFIRMED/SUSPECTED/UNKNOWN taxonomy), but step 3 depends on "templates/bug-report.md" which does not exist in the bundle, and step 6 hinges on the undefined "pattern F4" — missing key details that block full execution, fitting the incomplete-guidance anchor rather than the minor-gaps anchor.

3 / 5

Workflow Clarity

The numbered 1–8 procedure is clearly sequenced with explicit checkpoints (reproduce twice with recorded failure counts, reachability confirmation, and an Exit criteria gate), but there are minor validation gaps such as no defined handling for non-reproducible failures or UNKNOWN root causes, placing it just below the feedback-loop-rich anchor 5.

4 / 5

Progressive Disclosure

The short, well-sectioned body would otherwise qualify for the simple-skill exception, but its single external reference ("templates/bug-report.md") points to a file absent from the bundle, so the structure is undermined by a dangling reference rather than cleanly self-contained or properly backed by bundle files.

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, concrete about both the actions and the artifact contents, with an explicit 'Use whenever' trigger clause. The trigger vocabulary is slightly narrow and 'anomaly' is somewhat broad, which is the only noticeable weakness.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions ("Write, dedupe, and rank defect records") and comprehensively specifies the record contents ("minimal repro steps, expected-versus-actual results, sanitized evidence, reproducibility counts, and root-cause confidence"), matching the comprehensive-coverage anchor rather than the minor-gaps anchor below it.

5 / 5

Completeness

It explicitly answers both what (write/dedupe/rank defect records with concrete content elements) and when ("Use whenever a test fails or an anomaly is found") with concrete trigger phrases, matching the top anchor; it is well above the score-4 anchor where the 'when' is merely generic.

5 / 5

Trigger Term Quality

"Use whenever a test fails or an anomaly is found" provides natural trigger phrases, but common variations users would say ("bug", "regression", "error", "crash") are missing, so it falls between the good-coverage (4) and comprehensive-synonym (5) anchors.

4 / 5

Distinctiveness Conflict Risk

The defect-record/QA niche is mostly distinct with minor overlap risk, but "an anomaly is found" is broad enough to also trigger general debugging or investigation skills, keeping it below the minimal-conflict anchor 5.

4 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

itsablabla/qa-bug-agent-skills

Path

skills/qa-bug-reporting/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.