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 $prp-codebase-question.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%Weight 40%Scale 1-5

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 research workflow with concrete prompts, commands, and templates. The main weakness is redundancy of the documentarian mandate across multiple sections, which inflates token cost without adding guidance.

Suggestions

Consolidate the documentarian/evidence mandate: state it once in "Your Mission" or "Critical: Documentarian Only" and remove the overlapping restatements in "Golden Rule", "Critical Reminders", and "Success Criteria" to reduce token cost.

Consider extracting the PRP store resolver bash block and the research-document markdown template into a references/ file referenced one level deep, improving progressive disclosure for this longer skill.

Trim the repeated checkpoint prose so each PHASE_N_CHECKPOINT relies on its checklist alone, cutting redundant framing sentences.

Dimension	Reasoning	Score
Conciseness	Mostly efficient actionable process guidance with no concept-explanation fluff, but the documentarian/evidence mandate is restated across "Golden Rule", "CRITICAL: Documentarian Only", "Critical Reminders", and "Success Criteria", creating noticeable redundancy. Not 4 because the repeated messaging is padding that could be tightened; not 2 because the bulk is useful structured instruction rather than verbosity.	3 / 5
Actionability	Provides concrete, copy-paste-ready agent prompt templates, executable bash (PRP store resolver, metadata gathering, permalink checks), and a complete research-document markdown scaffold with specific field placeholders. Matches the fully-executable anchor; not 4 because examples cover the common cases comprehensively.	5 / 5
Workflow Clarity	A clear six-phase sequence (PARSE→DECOMPOSE→EXPLORE→SYNTHESIZE→DOCUMENT→OUTPUT) each with an explicit PHASE_N_CHECKPOINT checklist, plus a "wait for ALL agents" gate. Matches the clear-sequence-with-checklists anchor; the destructive/batch cap does not apply to read-only research.	5 / 5
Progressive Disclosure	Well-organized into clearly headed phases with templates and commands appropriately placed, but everything is inlined in one ~398-line file with no external reference files (none provided in the bundle). Not 5 because there are no one-level-deep references to separate detailed materials; not 3 because sectioning and placement are genuinely good.	4 / 5
	Total	17 / 20 Passed

Description

87%Weight 40%Scale 1-5

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 both the skill's purpose and its trigger conditions with natural user phrasing. Minor room to expand the concrete action list for fuller specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — "Research codebase questions using parallel agents", "documents what exists, not what should change" — with minor gaps (synthesis and output-document creation are not surfaced in the description). Not 3 because more than 1-2 concrete actions are named; not 5 because coverage is not comprehensive.	4 / 5
Completeness	Explicitly answers both what ("Research codebase questions using parallel agents - documents what exists") and when ("Use when the user asks how the codebase works, where something lives, or invokes $prp-codebase-question") with concrete trigger phrases. Clearly matches the 5 anchor; neighboring anchors lack one of the two.	5 / 5
Trigger Term Quality	Includes natural user phrases like "how the codebase works" and "where something lives", plus the explicit invocation token. Not 5 because common synonyms ("explain", "trace", "find") and a few natural variations are absent; not 3 because coverage is good rather than partial.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (read-only codebase documentation) with distinct triggers ("how the codebase works", "where something lives", $prp-codebase-question invocation), minimizing conflict with edit/refactor skills. Not 4 because the trigger set is specific enough to avoid meaningful overlap.	5 / 5
	Total	18 / 20 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-codebase-question/SKILL.md
Commit: 2cced43

Reviewed: 3 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.