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

75%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/prp-codebase-question/SKILL.md

Quality

Content

71%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 thorough, well-sequenced research workflow with strong validation checkpoints and concrete executable bash, but it carries repeated restatements of the same 'document only' rule and inlines material (agent prompt templates, the full output scaffold) that could live in one-level-deep reference files.

Suggestions

State the 'document what IS, not what SHOULD BE' rule once authoritatively (e.g., in the CRITICAL section) and remove the redundant restatements from agent prompts, Critical Reminders, and Success Criteria to recover tokens.

Move the ready-to-use agent prompt templates (sections 3.1/3.2) and the research-document scaffold (5.4) into reference files like AGENT_PROMPTS.md and RESEARCH_TEMPLATE.md, referenced one level deep, to shorten SKILL.md and aid navigation.

The bash store resolver (5.2) is duplicated across skills per its own comment; consider extracting it to a shared script in a scripts/ bundle rather than inlining the full block.

Dimension	Reasoning	Score
Conciseness	The body is well-structured and mostly efficient, but at ~390 lines it reiterates the 'document what IS, not what SHOULD BE' / 'no suggestions' rule across Mission, CRITICAL, agent prompts, Critical Reminders, and Success Criteria, adding padding beyond what Claude needs once the rule is stated once.	3 / 5
Actionability	Provides concrete, copy-paste-ready bash for store resolution, metadata, and permalinks, plus ready-to-use agent prompt templates and a full document scaffold; minor gaps are the templated placeholders users must fill and the non-executable markdown scaffolds.	4 / 5
Workflow Clarity	A clear six-phase sequence (PARSE → DECOMPOSE → EXPLORE → SYNTHESIZE → DOCUMENT → OUTPUT) with explicit PHASE_N_CHECKPOINT checklists after every phase, a 'wait for all agents' synchronization gate, and feedback loops (gap identification, follow-up re-runs).	5 / 5
Progressive Disclosure	Good single-file structure with clear section headers and self-contained phases; however no bundle files exist and all detail (agent prompts, full document template, bash resolver) is inlined in SKILL.md rather than split into reference files, leaving minor organization room.	4 / 5
	Total	16 / 20 Passed

Description

78%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, third-person description that clearly distinguishes its research-only niche and provides explicit trigger guidance including a slash command. It would benefit from a slightly broader set of natural trigger synonyms drawn from the body's own query-type table.

Suggestions

Add common user phrasings like 'explain', 'trace', 'locate', or 'what is X' to broaden trigger coverage beyond 'how' and 'where'.

Consider noting the --web and --follow-up flags in the description so users discover those entry points at trigger time.

Dimension	Reasoning	Score
Specificity	Names the domain ('codebase questions') and several concrete actions ('research', 'spawn parallel agents', 'synthesize findings', 'documents what exists'), with only minor gaps in coverage relative to the full multi-phase workflow.	4 / 5
Completeness	Clearly states both what it does (research via parallel agents, document what exists) and when to use it ('Use when the user asks how the codebase works, where something lives, or invokes /prp-codebase-question'), with the 'when' slightly constrained to a few example triggers rather than fully comprehensive.	4 / 5
Trigger Term Quality	Includes natural phrases a user would say ('how the codebase works', 'where something lives') plus the explicit slash command invocation, but is missing common synonyms like 'explain', 'trace', 'locate' that appear in the body.	4 / 5
Distinctiveness Conflict Risk	The 'document what IS, not what SHOULD BE' framing plus the specific slash-command trigger carves a clear niche distinct from refactoring/review skills, with minimal overlap risk.	5 / 5
	Total	17 / 20 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-codebase-question/SKILL.md
Commit: 9724799

Reviewed: ~12 hours 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.