bmad-party-mode

Orchestrates lively group discussions between installed BMAD agents or custom personas, and helps author custom parties. Use when the user requests party mode, a roundtable, or multiple agent perspectives — or wants to create/configure a party, define personas, or build an AI focus-group panel

Quality

84%

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

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.

The body is a well-structured, actionable orchestration guide with a strong sequenced activation workflow and validation checkpoints, supported by genuine one-level-deep reference files. The main weaknesses are a somewhat lengthy coaching section and template placeholders that prevent literal copy-paste execution.

Suggestions

Tighten the 'Keep It Feeling Like a Party' bullets to their operative directives to trim tokens while preserving the creative bar.

Resolve or document the {project-root}/{skill-root}/{workflow.*} placeholders with a one-line note on how they expand, so commands read as more directly executable.

Consider inlining the single sentence mode-auto borrows from mode-subagent to eliminate the inter-reference hop and keep references strictly one level deep.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence with no library or concept padding, but the 'Keep It Feeling Like a Party' coaching section runs long with philosophical directives that could be trimmed without losing the bar, so it sits just below the leanest anchor.	4 / 5
Actionability	Concrete, runnable commands with flags are given throughout ('uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --project-root {project-root} --key workflow'), but template placeholders and reliance on non-bundled _bmad/scripts keep it just short of copy-paste-ready.	4 / 5
Workflow Clarity	'On Activation' is a clearly sequenced 7-step workflow with explicit validation and feedback branches ('On failure, read customize.toml directly', 'if installed_agents_resolved is false... tell the user, carry on', 'confirm every entry ran'), matching the top anchor's checkpoints and error-recovery loops.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview pointing to real, well-signaled one-level-deep references (all referenced files exist and are loaded at the point of need), but minor cross-references between mode files (mode-auto.md -> mode-subagent.md) introduce light nesting, keeping it just below the cleanest anchor.	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.

The description is strong: it covers both what the skill does and when to invoke it with concrete, natural trigger phrases, and occupies a distinct niche. The only mild weakness is a touch of abstract phrasing ('orchestrates', 'lively') and a few missing synonym triggers.

Suggestions

Tighten 'Orchestrates lively group discussions' to a more concrete verb phrase (e.g., 'Runs multi-agent roundtable discussions') to lift specificity toward the top anchor.

Add one or two more natural trigger synonyms such as 'debate' or 'brainstorm with multiple voices' to round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Orchestrates lively group discussions', 'helps author custom parties', 'define personas', 'build an AI focus-group panel'), though 'orchestrates' and 'lively' stay slightly higher-level than the most concrete anchor examples, leaving minor coverage gaps.	4 / 5
Completeness	It explicitly answers both what ('Orchestrates lively group discussions... helps author custom parties') and when with a concrete 'Use when...' clause enumerating trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good coverage of natural terms and synonyms ('party mode', 'roundtable', 'multiple agent perspectives', 'focus-group panel'), but a few plausible natural phrases ('debate', 'brainstorm with multiple voices') are absent, so it falls just short of the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (BMAD party mode, roundtables, multi-agent panels) with distinct triggers that are unlikely to fire for unrelated skills, matching the minimal-conflict anchor.	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: bmad-code-org/BMAD-METHOD
Path: src/core-skills/bmad-party-mode/SKILL.md
Commit: 05bfbd4

Reviewed: 15 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.