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-engineered debugging workflow with strong sequencing, checkpoints, feedback loops, and executable commands. Its weaknesses are conciseness (some aphoristic padding) and progressive disclosure (a long single-file monolith with no offloaded references).

Suggestions

Trim the 'Critical Reminders' section or fold its rules into the relevant phases; aphorisms like 'Symptoms lie' and 'First explanation is often wrong' restate knowledge Claude already has.

Move the large Phase 5 report template (and/or the PRP store resolver bash block) into a references/ file (e.g. references/rca-report-template.md) and link to it one level deep, turning SKILL.md into a leaner overview.

Pull the 5 Whys template and evidence-standards table into a short reference so the main flow stays scannable while preserving the detail for the investigation phase.

Dimension	Reasoning	Score
Conciseness	Most of the body is actionable structure (phases, tables, commands, templates), but the aphoristic 'Critical Reminders' section and some restated guidance ('Symptoms lie', 'First explanation is often wrong') are things Claude already knows and could be tightened.	2 / 3
Actionability	It provides fully executable bash (the PRP store resolver script, git log/blame/diff commands), a concrete Task-tool invocation with a copy-paste prompt, and ready-to-fill report templates — copy-paste ready.	3 / 3
Workflow Clarity	Six explicitly sequenced phases each carry a PHASE_N_CHECKPOINT checklist, and Phase 4's three tests plus 'If any test fails -> go deeper' give explicit validate-to-fix feedback loops matching the score-3 anchor.	3 / 3
Progressive Disclosure	Internal sectioning is clear, but it is a ~330-line monolith with no reference files, and the detailed Phase 5 report template / bash resolver are large blocks that could live in separate reference files; the under-50-line exception does not apply.	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: third-person voice, explicit 'Use when' trigger guidance, and natural trigger terms including a slash command. The only soft spot is specificity, which frames a single capability rather than listing several concrete actions.

Dimension	Reasoning	Score
Specificity	It names the domain and a concrete action ('finds the actual cause, not just symptoms') but does not enumerate multiple distinct actions like the score-3 anchor does; it stops at a single capability framing.	2 / 3
Completeness	It clearly states what ('Deep root cause analysis - finds the actual cause, not just symptoms') and an explicit 'Use when the user reports a bug, error, or stacktrace...' trigger clause, answering both what and when.	3 / 3
Trigger Term Quality	It covers natural terms a user would say — 'bug, error, or stacktrace', 'wants to debug', 'root-cause analysis', plus the explicit '/prp-debug' invocation — matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Root-cause analysis is a clear niche and the '/prp-debug' slash command is a distinct trigger; although 'bug'/'error' are broad, the root-cause framing keeps it unlikely to fire for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Wirasm/prp
Path: .claude/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.