prp-research-team

Design a dynamic research team and plan using agent teams -- analyzes question, composes team, creates executable research plan. Use when the user wants to plan multi-agent research on a question or topic, or invokes /prp-research-team.

Quality

88%

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

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 body is highly actionable with executable bash, an exact plan template, and an exemplary multi-phase workflow with checkpoints and validation gates. Its main weakness is conciseness and a lack of progressive disclosure: a large monolithic file with execution-phase content that could be trimmed or moved to reference files.

Suggestions

Move the embedded research-plan template (lines 304-462) into a bundled reference file (e.g. references/plan-template.md) and link to it from Phase 6, turning the 530-line SKILL.md into a lean overview that practices one-level-deep progressive disclosure.

Remove or condense the "Output Format: Final Report Structure" section (lines 451-461) and "Manual Execution Alternative" (lines 511-516): both describe execution-time behavior outside this skill's plan-only scope and add length without aiding planning.

De-duplicate the "Plan Approval" checklist (lines 431-434) against the Phase 6 GATE validation (lines 472-478) so the same verification is stated once, reducing token cost.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient and assumes Claude's competence (no basic-concept explanations), but at ~530 lines it includes tangential execution-phase content (the "Output Format: Final Report Structure" and "Manual Execution Alternative" sections) and a checklist that overlaps the Phase 6 gate, so it could be tightened.	2 / 3
Actionability	Provides copy-paste-ready bash for the output directory and state sentinel, exact filename-conversion rules, and a complete fill-in markdown plan template with structured field tables — fully executable guidance rather than pseudocode.	3 / 3
Workflow Clarity	Seven phases are clearly sequenced (PARSE through OUTPUT), each with an explicit PHASE_N_CHECKPOINT, and error-recovery GATEs that STOP/ASK (empty question, vague decomposition, pre-Phase-7 validation) — matching the anchor for clear sequence with validation steps and feedback loops.	3 / 3
Progressive Disclosure	This is a single ~530-line monolithic file with no bundle references; the large embedded plan template (lines 304-462) and report-structure content are inline material that could be split into separate reference files, matching the anchor where content that should be separate is 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 concise, specific, and complete: it states concrete actions, gives an explicit "Use when" trigger with natural terms and a slash-command invocation, and carves out a distinct niche. It avoids vague fluff and verbosity.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "analyzes question, composes team, creates executable research plan" — matching the anchor that lists several specific actions rather than a vague single domain.	3 / 3
Completeness	Answers both what (analyze, compose, create plan) and when, with an explicit "Use when the user wants to plan multi-agent research... or invokes /prp-research-team" trigger clause.	3 / 3
Trigger Term Quality	Captures natural phrasing users would say ("plan multi-agent research on a question or topic") plus an explicit slash-command trigger ("or invokes /prp-research-team"), giving good coverage of likely terms.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (multi-agent research planning via agent teams) with a distinct slash-command trigger, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (537 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Wirasm/prp
Path: .claude/skills/prp-research-team/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.