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

82%

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 1-5

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 an exemplary sequenced, gated workflow and copy-paste templates. Its weaknesses are token efficiency (redundancy and rationale Claude already knows) and progressive disclosure (a monolithic single file with no reference split for the large embedded template).

Suggestions

Remove the redundant trailing Success Criteria section or fold it into the per-phase checkpoints to eliminate duplicate content and save tokens.

Move the full research-plan markdown template and the domain/complexity/model tables into a reference file (e.g. references/plan-template.md) and link to it one level deep, keeping only a compact quick-start in SKILL.md.

Trim explanations Claude already knows (the sonnet-vs-opus rationale, the generic complexity-factor bullet list) down to the operational choices themselves.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient with concrete templates and bash, but it includes redundancy (per-phase checkpoints repeated in the final Success Criteria) and rationale Claude already knows (the sonnet/opus model-selection rationale table, "Complexity factors" listing breadth/depth). Not a 4 because the padding is noticeable across multiple sections.	3 / 5
Actionability	Copy-paste-ready bash (the PRP store resolver), an exact filled-in markdown template with clearly marked placeholders, and concrete filename-conversion examples make the guidance fully executable for the common cases.	5 / 5
Workflow Clarity	Seven phases (PARSE→OUTPUT) are explicitly sequenced, each with a checkpoint checklist, and GATEs provide feedback loops (stop-and-ask when too vague; do-not-proceed until the plan file passes the 6-section validation). This matches the top anchor for clear sequencing with validation and error-recovery loops.	5 / 5
Progressive Disclosure	Internal sectioning is clear (per-phase headers, checkpoints), but the skill is a monolithic 540-line file with no bundle references and the full plan template plus domain/complexity tables inlined rather than split into reference files. Not a 2 because structure is good; not a 4 because content that belongs in separate files is inlined with no one-level-deep references.	3 / 5
	Total	16 / 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.

The description is strong: third-person voice, explicit what-and-when, concrete actions, and a distinct slash-command trigger. It is just short of maximum specificity and trigger-term breadth because the action list has minor overlap and lacks synonym variations.

Dimension	Reasoning	Score
Specificity	"Design a dynamic research team and plan... analyzes question, composes team, creates executable research plan" names the domain and lists several specific concrete actions. Not a 5 because the actions (design/composes team) partially overlap rather than showing fully comprehensive coverage.	4 / 5
Completeness	It clearly answers what ("analyzes question, composes team, creates executable research plan") and when ("Use when the user wants to plan multi-agent research... or invokes /prp-research-team") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	"Use when the user wants to plan multi-agent research on a question or topic, or invokes /prp-research-team" provides good natural keyword coverage including the slash-command trigger. Not a 5 because some natural synonym variations for multi-agent research planning are absent.	4 / 5
Distinctiveness Conflict Risk	The "agent teams" framing and the explicit "/prp-research-team" invocation carve a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 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 (541 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: 9724799

Reviewed: ~13 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.