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.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced bug-analysis methodology with concrete paths, commands, and a validation-backed workflow. Its main weaknesses are mild internal redundancy and a monolithic structure that does not progressively disclose the large output template into a reference file.

Suggestions

Reduce overlap between 'Follow This Workflow', 'Evaluate With These Dimensions', and the output template by merging the dimension prompts into the corresponding workflow/output sections.

Move the full 'Produce This Output Format' template into a references/ file (e.g. OUTPUT_TEMPLATE.md) and link to it one level deep, keeping only the section headers inline to improve progressive disclosure.

Tighten the 'Use Context7 and MCP Deliberately' triggers list by collapsing the library/runtime bullets into a compact table or single sentence to reclaim tokens.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept-padding Claude already knows, but the workflow steps, 'Evaluate With These Dimensions', and the large output template overlap enough that the body could be tightened without losing clarity.	2 / 3
Actionability	Provides concrete, executable guidance: specific file paths (README.md, backend/.../pigeon/, frontend/src/pages/), runnable rg commands, explicit Context7 triggers, and a copy-paste-ready output template.	3 / 3
Workflow Clarity	A clearly sequenced 10-step workflow with an explicit validation checkpoint (step 9 verification plan) and a final 'Quality Bar' checklist acting as a pre-finalization gate, satisfying the feedback-loop anchor.	3 / 3
Progressive Disclosure	Well-organized into clearly headed sections, but it is a single ~90-line monolithic SKILL.md with no bundle files and no one-level-deep references to split out the sizable output template or dimension definitions.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that clearly states capabilities, includes natural trigger terms and an explicit Use-when clause, and is scoped to a distinct niche. No fluff or over-claims; verbosity is well-controlled.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'root-cause analysis, fix strategy, repro analysis, severity assessment, or regression-risk evaluation' — beyond a single domain verb, matching the score-3 anchor.	3 / 3
Completeness	Explicitly answers both what ('Analyze software bugs... with a bugfix-first workflow') and when via an explicit 'Use when users report...' clause, satisfying the score-3 anchor.	3 / 3
Trigger Term Quality	Covers natural user phrasings such as 'broken behavior, regressions, incorrect results, crashes, data inconsistencies, sync/download failures' alongside root-cause/fix requests, giving broad natural-term coverage.	3 / 3
Distinctiveness Conflict Risk	Scoped to 'the PigeonPod project with a bugfix-first workflow' with distinct bug-report triggers, giving it a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

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
Path: .agent/skills/bug-analysis/SKILL.md
Commit: 27a1e11

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

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.