prp-debug

Deep root cause analysis - finds the actual cause, not just symptoms. Use when the user reports a bug, error, or stacktrace, wants to debug or do root-cause analysis, or invokes $prp-debug.

Quality

83%

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 well-structured, highly actionable RCA workflow with clear phases, checkpoints, executable commands, and error-recovery feedback loops. Its two weaknesses are monolithic inline content (no progressive disclosure into reference files) and some rule restatement that pads the token budget.

Suggestions

Move the full report template and/or the PRP store resolver script into a references/ or scripts/ bundle file and link to it, keeping SKILL.md as an overview to improve progressive disclosure.

Consolidate the evidence rules so they appear once — merge the 'Rules' list, the Evidence Standards table, and Critical Reminder #3 ('No evidence = no claim') to remove restatement and tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The ~320-line body is mostly procedural and earns its tokens, but it restates rules across the Evidence Standards table, the Investigation rules, and the Critical Reminders section ('No evidence = no claim'), so it could be tightened rather than being fully lean.	2 / 3
Actionability	It provides copy-paste-ready, executable commands (git log/blame/diff, the PRP store resolver block), a concrete 5 Whys template, a full report markdown template, and an explicit codebase-analyst subagent spawn prompt.	3 / 3
Workflow Clarity	A clear 6-phase sequence carries an explicit PHASE_N_CHECKPOINT after every phase, plus feedback loops ('If evidence refutes a hypothesis, pivot', 'If any test fails → go deeper or broader') and a three-tests validation table.	3 / 3
Progressive Disclosure	No bundle files exist and the body has no external references — all content lives inline in one 320+ line file, so it is well-organized but monolithic rather than split across one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

90%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 description that clearly states capability and gives explicit, natural-language 'Use when...' triggers covering bug, error, stacktrace, and debug scenarios. Its main weakness is specificity — it states the domain and one defining behavior rather than listing multiple concrete techniques.

Suggestions

Add 2-3 concrete techniques to the description (e.g., 'runs the 5 Whys, checks git history, and validates with causation/necessity/sufficiency tests') to lift specificity from 'some actions' to 'multiple specific concrete actions'.

Tighten the trigger list slightly or keep the broad 'debug' term but pair it with the more specific 'root-cause analysis' to reduce overlap with generic troubleshooting skills.

Dimension	Reasoning	Score
Specificity	It names the domain ('Deep root cause analysis') and a defining behavior ('finds the actual cause, not just symptoms'), but does not enumerate multiple concrete actions/techniques, matching the 'names domain and some actions' anchor rather than the 'lists multiple specific concrete actions' level.	2 / 3
Completeness	It explicitly answers what ('Deep root cause analysis - finds the actual cause, not just symptoms') and when via an explicit 'Use when...' clause, satisfying the level-3 anchor.	3 / 3
Trigger Term Quality	Natural user terms 'bug, error, or stacktrace' and 'debug or do root-cause analysis' are exactly what a user would say, giving good coverage rather than just 'some relevant keywords'.	3 / 3
Distinctiveness Conflict Risk	The deep-RCA niche plus the explicit $prp-debug invocation trigger carves a clear niche unlikely to conflict, though 'debug' alone is somewhat broad.	3 / 3
	Total	11 / 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: Wirasm/prp
Path: .agents/skills/prp-debug/SKILL.md
Commit: 1142738

Reviewed: 11 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.