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 the prp-debug skill.

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 thorough, highly actionable RCA workflow with strong sequencing and validation checkpoints. Its weaknesses are token redundancy between the Phase 5/6 report templates and a monolithic single-file structure with no progressive disclosure of the larger templates and scripts.

Suggestions

Collapse the Phase 5 report template and Phase 6 output template into one source of truth to remove the duplicated markdown blocks.

Extract the PRP store resolver bash script and the full RCA report template into reference files under ./references/ and link to them one level deep from the body, reducing inline bulk.

Trim 'Critical Reminders' to only items not already enforced by the phase checkpoints, since several points (evidence required, git history mandatory) are restated.

Dimension	Reasoning	Score
Conciseness	Largely efficient procedural guidance, but the ~330-line body carries redundancy (Phase 5 and Phase 6 both render near-duplicate report templates, and 'Critical Reminders' restates phase content), so it could be tightened rather than hitting the lean level-3 anchor.	2 / 3
Actionability	Provides concrete, executable guidance: bash commands (git log/blame/diff, the PRP store resolver script), explicit file:line evidence requirements, and copy-ready report templates.	3 / 3
Workflow Clarity	Six phases are clearly sequenced, each with an explicit CHECKPOINT checklist and feedback loops ('pivot to the next one', 'backtrack', 'go deeper or broader'), matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	Well-organized into phase sections but entirely monolithic with no bundle files or one-level-deep references; content that could be split (report templates, resolver script) is kept inline, so it does not meet the level-3 'well-signaled references' anchor.	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: it states a clear niche, includes an explicit 'Use when...' trigger clause with natural user-facing terms, and is well distinguished from generic debugging skills. The only gap is that it names one core action rather than enumerating multiple specific capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ('Deep root cause analysis - finds the actual cause, not just symptoms') but does not list multiple distinct concrete actions, so it falls short of the level-3 anchor.	2 / 3
Completeness	Explicitly answers both what (root cause analysis) and when via a clear 'Use when the user reports a bug, error, or stacktrace...' clause.	3 / 3
Trigger Term Quality	Covers natural terms users actually say ('bug, error, or stacktrace, wants to debug or do root-cause analysis'), matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche (root-cause analysis 'not just symptoms') with distinct triggers and a named skill invocation, making overlap with generic coding skills unlikely.	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: profiles/kild/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.