CtrlK
BlogDocsLog inGet started
Tessl Logo

bug-analysis

Analyze software bugs for the PigeonPod project with a bugfix-first workflow. Use when users report broken behavior, regressions, incorrect results, crashes, data inconsistencies, sync/download failures, or ask for root-cause analysis, fix strategy, repro analysis, severity assessment, or regression-risk evaluation. Read current repository docs and code first, then use MCP tools including Context7 only when framework, library, API, or external-service behavior must be verified.

72

Quality

87%

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

75%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 well-structured, actionable analysis workflow with explicit file paths, commands, an output template, and a validation checklist. It is concise and assumes competence, with only minor organization and validation-checkpoint gaps.

Suggestions

Tighten the Context7 section: collapse 'Typical triggers' into the rules list or reference it once instead of restating library-specific examples that pad the skill.

Make the verification plan an enforced mid-flow checkpoint (e.g., 'Do not output a recommendation until a verification/rollback step is specified') rather than only an output field to fill.

Consider extracting the full output template and decision heuristics into a reference file so the main SKILL.md stays a lean overview, improving progressive disclosure toward one-level-deep references.

DimensionReasoningScore

Conciseness

Lean, task-specific guidance that assumes Claude's competence (no padding about what bugs or frameworks are), with only minor instances that could be trimmed such as the Context7 'Typical triggers' list restating intent; clearly above the mostly-efficient level 3 but not perfectly lean at level 5.

4 / 5

Actionability

Provides concrete executable guidance — real file paths (backend/src/main/java/top/asimion/pigeon/), runnable rg discovery commands, and a fill-in output template — which is highly actionable for an instruction-only skill, though some template fields remain abstract and it lacks full code examples by design.

4 / 5

Workflow Clarity

A clear 10-step sequenced workflow with an explicit reproduction fallback and a Quality Bar validation checklist, plus a required verification/rollback plan; above level 3, but the verification step is framed as output to produce rather than a self-enforcing mid-flow checkpoint, leaving minor validation gaps short of level 5.

4 / 5

Progressive Disclosure

Well-organized into clearly headed thematic sections with no monolithic wall or nested references, and no bundle files exist to mis-cite; cohesive single-file guidance that is appropriately placed, falling just short of the ideal one-level-deep-reference level 5.

4 / 5

Total

16

/

20

Passed

Description

100%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 is specific, trigger-rich, and cleanly scoped to bug analysis for PigeonPod, answering both what the skill does and when to invoke it. It reads as a strong, low-conflict skill description.

DimensionReasoningScore

Specificity

Enumerates multiple concrete bug-analysis actions — 'root-cause analysis, fix strategy, repro analysis, severity assessment, or regression-risk evaluation' — with comprehensive coverage of the domain, matching the score-5 anchor rather than the several-actions-with-gaps level 4.

5 / 5

Completeness

Explicitly answers both 'what' ('Analyze software bugs ... bugfix-first workflow') and 'when' ('Use when users report ...') with concrete trigger phrases, matching the clearly-both anchor at level 5.

5 / 5

Trigger Term Quality

Natural user-facing trigger phrases like 'broken behavior, regressions, incorrect results, crashes, data inconsistencies, sync/download failures' give comprehensive keyword coverage a reporter would actually say, beyond the few-terms-missing level 4.

5 / 5

Distinctiveness Conflict Risk

Scoped to a single project (PigeonPod) with a defined bugfix-first workflow and an explicit hand-off to requirements-analysis, giving a clear niche with minimal conflict risk.

5 / 5

Total

20

/

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
aizhimou/pigeon-pod
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.