prp-codebase-question

Research codebase questions using parallel agents - documents what exists, not what should change. Use when the user asks how the codebase works, where something lives, or invokes the prp-codebase-question skill.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

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.

The content is highly actionable and the workflow is exceptionally well-sequenced with per-phase checkpoints. Its weaknesses are verbosity from restated documentarian directives and the absence of any progressive disclosure (no bundle files or separate references), keeping it from the top tier.

Suggestions

Consolidate the repeated 'document, don't evaluate / no suggestions / no critique' guidance (CRITICAL section, Golden Rule, Critical Reminders #1, NO_OPINIONS success criterion) into a single statement to reduce token cost.

Move the large research-document template (Phase 5.4) and the agent prompt templates (Phase 3) into reference files under references/ and link to them one level deep, improving progressive disclosure.

Trim the boilerplate 'Kild lane' note if it is not essential to the skill's core instruction, or relocate it to a reference, since it competes with the actual workflow content for context.

Dimension	Reasoning	Score
Conciseness	The body is well-organized and largely avoids explaining concepts Claude already knows, but it is long (~390 lines) with some redundancy — the 'Documentarian Only' directives, Golden Rule, and 'Critical Reminders' restate the same no-suggestion/no-critique point multiple times, which could be tightened.	2 / 3
Actionability	It provides concrete, copy-paste-ready bash (PRP store resolver, metadata gathering), explicit agent prompt templates with placeholders, and exact output document scaffolding — executable guidance throughout.	3 / 3
Workflow Clarity	Six phases are clearly sequenced, each with an explicit PHASE_N_CHECKPOINT checklist, and Phase 5 includes a validate-then-act ordering ('No placeholder values remain') with feedback for follow-up handling, giving strong error-recovery guidance.	3 / 3
Progressive Disclosure	There are no bundle files (references/, scripts/, assets/ absent) and the skill is a single monolithic SKILL.md with no one-level-deep references, so while sections are well-organized, content that could be split (e.g., output templates, agent prompts) is all inline.	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.

The description is strong: it states concrete capabilities, gives explicit 'Use when' triggers, uses third person, and is clearly distinct from other skills. No significant weaknesses; it is concise rather than padded.

Dimension	Reasoning	Score
Specificity	The description names multiple concrete actions ('Research codebase questions using parallel agents', 'documents what exists, not what should change'), clearly identifying both the activity and its distinctive documentarian stance.	3 / 3
Completeness	It answers 'what does this do' (research codebase questions via parallel agents, documenting what exists) and 'when to use it' ('Use when the user asks how the codebase works, where something lives, or invokes the skill'), giving explicit trigger guidance.	3 / 3
Trigger Term Quality	It surfaces natural user phrasings ('how the codebase works', 'where something lives') and explicit skill-invocation language, covering the common ways a user would ask for this skill.	3 / 3
Distinctiveness Conflict Risk	The 'documents what exists, not what should change' framing carves a clear niche distinct from general coding or refactoring skills, making misfires unlikely.	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: Wirasm/prp
Path: profiles/kild/skills/prp-codebase-question/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.