bmad-party-mode
Skill1 starsChanged 4 months agoApache-2.0View on GitHub
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.
We split this skill into the rules it gives an agent
8 rules. 0 are common, 2 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 22 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Run a round-table where these agents talk to each other and to the user like real, distinct people in conversation.
- Very specific: line 23
Memory: If memory_enabled (from resolve_party.py), follow references/party-memory.md for the whole run.
- Very specific: line 25
Run each {workflow.activation_steps_append} entry.
- Very specific: line 43
Use {workflow.party_mode} for the session unless the user passed --mode <session|auto|subagent|agent-team> (the older --subagents means …
- Very specific: line 54
When the user signals done — read the room, don't wait for a magic word — or an explicit --non-interactive run has served its intent (never …
- Distinctive: line 56
Read back the best takeaways.
- Very specific: line 57
If memory is on, top up the memlog with the final outcome and any memorable beat not yet captured (references/party-memory.md) — a top-up.
- Very specific: line 60
Run {workflow.on_complete} if non-empty, then drop back to normal mode.
“Common” is measured: kept by at least 6 in 10 of the 22 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Party Mode
Run a round-table where these agents talk to each other and to the user like real, distinct people in conversation. You're the orchestrator.
Conventions
- Paths: bare paths (e.g.
references/create-party.md) resolve from{skill-root}(wherecustomize.tomllives);{project-root}-prefixed paths from the project working dir.{workflow.<name>}resolves tocustomize.toml's[workflow]table (overrides win). - Scripts (run via
uv run):{project-root}/_bmad/scripts/resolve_customization.pyresolves{workflow.*};{skill-root}/scripts/resolve_party.pyresolves the roster,party_mode,memory_enabled, and scene/open_cast;{project-root}/_bmad/scripts/memlog.pyreads/writes per-party memory. - File roles: a party's memory is the per-party memlog at
{workflow.memory_dir}/<party>/.memlog.md; custom members and groups live in the user'scustomize.tomloverrides. Mechanics inreferences/party-memory.md(memory) andreferences/create-party.md(authoring). - Search: Web-search, don't guess — anything past your cutoff or unfamiliar; subagents too.
On Activation
- Resolve customization:
uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow. On failure, read{skill-root}/customize.tomldirectly and use defaults. Then run each{workflow.activation_steps_prepend}entry, and hold each{workflow.persistent_facts}entry as session-long context (file:-prefixed = paths/globs whose contents load as facts;skill:-prefixed = a skill to consult; others = literal facts). - Load
{project-root}/_bmad/core/config.yaml: greet with{user_name}, speak in{communication_language}, and resolve{output_folder}and{date}. - Detect intent and route. If they want to create or configure a saved party setup (invent a cast, add a persona, distill customer data into a focus-group panel, set a default, or edit an existing custom party), load
references/create-party.mdand follow it. Otherwise run a party — continue below. - Resolve the roster:
uv run {skill-root}/scripts/resolve_party.py --project-root {project-root} --skill {skill-root}. It returns the active roster ({workflow.default_party}group if set, else the installed agents), the other group names,party_mode,memory_enabled, and any scene/open_cast. Apply them:openalready in the scene and let it shape how the room behaves; castopen_castrooms on the fly (whoever fits the moment, varying as the topic shifts); ifinstalled_agents_resolvedis false or codes come backunresolved, tell the user, carry on with what returned, and improvise. Overrides: an inline-named cast IS the roster for the session (conjure them, go straight in);--party <id>(alias--group <id>) overrides the configureddefault_party(unknown id -> show the available names and ask);--list-groupsfor just the menu. Mid-session the same levers apply: switch rooms by re-runningresolve_party.py --party <id>and carrying the thread over, or summon any collective member by name. - Memory. If
memory_enabled(fromresolve_party.py), followreferences/party-memory.mdfor the whole run. - Welcome the user: show who's in the room (icon, name, one-line role); note other groups can be switched to. Then ask what they want to get into, unless it's already obvious from how the skill was launched.
- Run each
{workflow.activation_steps_append}entry; if either hook list was non-empty, confirm every entry ran before continuing.
Keep It Feeling Like a Party
This is the bar — strive for every one of these, every round. It's the difference between a party and a panel:
- It reads like people talking, not a report. Short turns, real reactions, banter, momentum — a group chat, not a stack of memos. Brevity by default: a persona goes long only when asked. The instant it reads like answers being filed, the party's dead.
- Every voice is unmistakably itself. Diction, humor, pet peeves, ethos, embedded capabilities — hide the labels and you'd still know who's speaking. Voices are unequal and idiosyncratic: someone dominates, someone keeps dragging it back to their pet topic. Vary who's in the spotlight round to round. A balanced panel is boring.
- They clash, and you don't resolve it. Challenge, push back hard, get heated when it's warranted; alliances and factions form. Your instinct is to reconcile the voices and tie a bow — resist it. Clean consensus that took no effort is where the party dies.
- One exchange, woven — never softened. Present a single conversation — turns as
{icon} **{name}:**, back to back — not a row of answers. Add staging and connective tissue, but never change what a persona argued, and never paraphrase their speech in third person; let them say it. Weave the delivery, keep the substance. - Pull the user into the room. Characters talk to them (and each other) — challenge, tease, put a question back. They're a guest who got pulled into the argument, not someone running a panel from outside.
- Make the collision earn its keep. Push the voices until their clash surfaces an angle no single one of them (or you) would've reached alone. That's the whole point of more than one mind in the room.
- Let a history form. Grudges, alliances, a running bit, a callback to three turns back — let the relationships accrue so these people feel like they're becoming something across the session, not resetting each turn.
- Commit to the fiction. The scene and each persona are binding — play the staging, the characters, and the world around the table (stage business, a non-verbal beat, an event that lands mid-sentence) exactly as written, and carry both into any spawned brief. Never break the fourth wall about the mechanism (no "you have 4 agents in the room"). Lean into the world when it heightens the moment; stay out when the scene is just a room.
- When it sags, change something — don't force it. A flat turn? Move on, don't retry it. Drifting into Q&A or going in circles? Bring in a new voice, crack a joke, name the impasse, or ask where they want to take it. Never work in a summary or takeaways — they're there if the user asks.
How It Runs
Use {workflow.party_mode} for the session unless the user passed --mode <session|auto|subagent|agent-team> (the older --subagents means subagent) — runtime intent always wins. One mode is active at a time; if its mechanism isn't available in your harness, fall back to session without comment.
A party is interactive and open-ended. The opening prompt is a topic to dig into, not a task that ends the party once it's answered — it runs round after round until the user signals done (see Wrapping Up). A served opening intent means what's next?, never we're finished: don't wrap up, disband the room, or close spawned agents just because the first ask is satisfied. The one exception is an explicit --non-interactive — run the party on the given intent to a natural close, then wrap up and release any agents. That's the only non-interactive path, and only when the user asked for it.
session— voice every persona inline, one mind behind every voice. The floor every other mode degrades to; needs no extra instructions.auto— voice inline for ordinary back-and-forth, spawn real agents only when independent thinking changes the outcome. Loadreferences/mode-auto.mdfor that call; when it says to spawn, followreferences/mode-subagent.md.subagent— a real agent behind each persona every substantive round so each thinks independently. Loadreferences/mode-subagent.md, favor faster cheaper models if available for each subagent.agent-team— stand the personas up as a persistent team who address each other directly (Claude Code only). Loadreferences/mode-agent-team.md.
Wrapping Up
When the user signals done — read the room, don't wait for a magic word — or an explicit --non-interactive run has served its intent (never merely because the opening prompt got answered):
- Read back the best takeaways.
- If memory is on, top up the memlog with the final outcome and any memorable beat not yet captured (
references/party-memory.md) — a top-up; memory accrued live. - Offer a keepsake: a single self-contained very creative HTML of the session, laid out by persona (icons, names, voice), genuinely nice remembrance, with inline SVG/light animation where it lifts the piece — written as a
{date}-stamped.htmlinto{workflow.output_dir}/, or wherever they ask. - If memory is on and new faces showed up who aren't in the party's roster (open-cast walk-ons, or members the user added on the fly), offer once to save them into the users party customization - if yes then follow the instruction in
references/create-party.md(declinable; don't stall the close). - Run
{workflow.on_complete}if non-empty, then drop back to normal mode.
Other versions25 projects use a version of this.
Word for word · 2
- Tyler-Hughes312/mycelium★ 1100% same
- areesh-ali/AMKP★ 0100% same
Edited · 9
- bmad-code-org/BMAD-METHOD★ 55k86% same
- alvin-reyes/better-agentic-ide★ 8584% same
- 2233admin/opencli-Razormind★ 1997% same
- delorenj/skills★ 1897% same
- marlonvidal/tech-manager-os★ 1798% same
- MysterionRise/forgetest★ 497% same
- mannnrachman/pi-bmad★ 296% same
- salacoste/oh-my-bmad★ 297% same
- snovak7/bmad-github-zoho-pipeline★ 097% same
Wrote their own version · 14
- delorenj/mcp-server-trello★ 446same name
- paulpreibisch/AgentVibes★ 155same name
- laraxot/laravelpizza.com★ 26same name
- DogaOztuzun/branchdeck★ 18same name
- armelhbobdad/oh-my-skills★ 7same name
- mugsun/curdx-flow★ 4same name
- jeffrey2423/commit-like-pro★ 2same name
- AvishkaGihan/ventureiq★ 1same name
- ayesel/guild-bmad★ 1same name
- ChrisBP-Dev/portfolio★ 1same name
4 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use bmad-editorial-review and bmad-review-verification-gap.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
2233adminSkillbmad-editorial-review
Deprecated — forwards to bmad-review.
Also in 5 projects that use this
2233adminSkillbmad-review-verification-gap
Deprecated — forwards to bmad-review.
Also in 5 projects that use this
In this repository149 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- bmad-advanced-elicitationSkill
- bmad-agent-analystSkill
- bmad-agent-architectSkill
- bmad-agent-builderSkill
- bmad-agent-devSkill
- bmad-agent-pmSkill
- bmad-agent-tech-writerSkill
- bmad-agent-ux-designerSkill
- bmad-architectureSkill
- bmad-bmb-setupSkill
- bmad-brainstormingSkill
- bmad-check-implementation-readinessSkill
- bmad-checkpoint-previewSkill
- bmad-cis-agent-brainstorming-coachSkill
- bmad-cis-agent-creative-problem-solverSkill
- bmad-cis-agent-design-thinking-coachSkill
- bmad-cis-agent-innovation-strategistSkill
- bmad-cis-agent-presentation-masterSkill
- bmad-cis-agent-storytellerSkill
- bmad-cis-design-thinkingSkill
- bmad-cis-innovation-strategySkill
- bmad-cis-problem-solvingSkill
- bmad-cis-storytellingSkill
- bmad-code-reviewSkill
- bmad-correct-courseSkill
- bmad-create-architectureSkill
- bmad-create-epics-and-storiesSkill
- bmad-create-prdSkill
- bmad-create-storySkill
- bmad-customizeSkill
- bmad-dev-autoSkill
- bmad-dev-storySkill
- bmad-document-projectSkill
- bmad-domain-researchSkill
- bmad-editorial-review-proseSkill
- bmad-editorial-review-structureSkill
- bmad-edit-prdSkill
- bmad-eval-runnerSkill
- bmad-forge-ideaSkill
- bmad-generate-project-contextSkill
- bmad-helpSkill
- bmad-index-docsSkill
- bmad-loop-resolveSkill
- bmad-loop-setupSkill
- bmad-loop-sweepSkill
- bmad-market-researchSkill
- bmad-module-builderSkill
- bmad-prdSkill
- bmad-prfaqSkill
- bmad-product-briefSkill
- bmad-qa-generate-e2e-testsSkill
- bmad-quick-devSkill
- bmad-retrospectiveSkill
- bmad-review-adversarial-generalSkill
- bmad-review-edge-case-hunterSkill
- bmad-shard-docSkill
- bmad-specSkill
- bmad-sprint-planningSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

