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

96%

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

92%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 well-structured, highly actionable orchestration skill with clear sequencing, validation checkpoints, and clean progressive disclosure across verified bundle files. The only slack is rhetorical flourish in the qualitative 'Keep It Feeling Like a Party' bar.

Suggestions

Tighten 'Keep It Feeling Like a Party': keep the behavioral bars but trim evocative asides like 'the party's dead' and 'A balanced panel is boring' to reduce token cost without losing the directive force.

Consider moving the long 'Keep It Feeling Like a Party' bullets into a reference file if further conciseness is desired, keeping only the top three bars inline.

Dimension	Reasoning	Score
Conciseness	Largely lean and directive with concrete commands and placeholders, but the 'Keep It Feeling Like a Party' section carries evocative prose ('the party's dead', 'A balanced panel is boring', 'tie a bow — resist it') that could be tightened without losing the behavioral bar.	4 / 5
Actionability	Fully executable guidance — concrete `uv run` commands with full argument signatures, flags (`--party`, `--group`, `--list-groups`, `--mode`, `--non-interactive`), and explicit routing rules covering the common cases.	5 / 5
Workflow Clarity	The 7-step 'On Activation' sequence has explicit validation and error-recovery checkpoints ('On failure, read customize.toml directly and use defaults'; 'if installed_agents_resolved is false... tell the user, carry on'; 'confirm every entry ran before continuing'), plus mode fallback and a clear wrap-up flow.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview with well-signaled one-level-deep references (create-party.md, party-memory.md, mode-auto/subagent/agent-team.md, resolve_party.py), all verified to exist, with authoring/memory/mode details appropriately split into separate files.	5 / 5
	Total	19 / 20 Passed

Description

100%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 is specific, third-person, and clearly states both what the skill does and when to use it with natural trigger terms. It is distinguishable and comprehensive without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Orchestrates lively group discussions', 'helps author custom parties', 'create/configure a party', 'define personas', 'build an AI focus-group panel' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ('Orchestrates lively group discussions... helps author custom parties') and when ('Use when the user requests party mode, a roundtable, or multiple agent perspectives...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms with synonyms: 'party mode', 'roundtable', 'multiple agent perspectives', plus 'create/configure a party', 'define personas', 'AI focus-group panel' — phrases a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	Clear niche — 'BMAD agents or custom personas', 'party mode', 'roundtable', 'AI focus-group panel' — with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	20 / 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: 67d876f

Reviewed: about 20 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.