board-worker
Skill1 starsChanged 4 months agoApache-2.0View on GitHub
Operating manual for autonomous Vodou Board workers spawned by the dispatcher.
- Deletes or force-pushes
- Commits and pushes
In this repository64 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- board-triage-specifierSkill
- create-a-skillSkill
- execdesk-action-board-prepSkill
- execdesk-action-competitor-monitorSkill
- execdesk-action-competitor-positioningSkill
- execdesk-action-content-calendarSkill
- execdesk-action-decision-frameworkSkill
- execdesk-action-growth-hack-runnerSkill
- execdesk-action-icp-profileSkill
- execdesk-action-quarterly-goals-reviewSkill
- execdesk-action-twitter-thread-drafterSkill
- execdesk-action-weekly-briefSkill
- execdesk-ceoSkill
- execdesk-chief-of-staffSkill
- execdesk-cmoSkill
- think-deepSkill
- docker-compose-devSkill
- calendar-hold-approvalSkill
- chuck-norrisSkill
- email-send-approvalSkill
- graph-ask-demoSkill
- inbox-and-agendaSkill
- meeting-brief-graphSkill
- multi-mcp-testSkill
- schedule-badge-proofSkill
- stopping-point-testSkill
- turn-log-smokeSkill
- code-review-templateSkill
- custom-skill-templateSkill
- daily-research-briefSkill
- pr-review-pipelineSkill
- research-analysis-templateSkill
- ship-a-featureSkill
- autonomous-planSkill
- browser-toolsSkill
- code-reviewSkill
- deep-thinkingSkill
- first-skillSkill
- helloSkill
- implementation-planningSkill
- install-mcp-serverSkill
- masterySkill
- mcp-builderSkill
- mcp-installerSkill
- morning-briefSkill
- new-user-walkthroughSkill
- oauth-authenticationSkill
- onboardingSkill
- parallel-code-analysisSkill
- project-wizardSkill
- qa-reportSkill
- qa-testingSkill
- regression-testSkill
- self-improveSkill
- self-learningSkill
- skill-developmentSkill
- social-media-marketingSkill
- soulSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Call board_show(task_id) to read your assignment.
- Very specific: line 16
Do the work. Use available MCP tools (vodou-core call <server> <tool>).
- Very specific: line 27
Token budget is enforced: If you hit 90% of your max_runtime_seconds, call board_block with reason "budget_exceeded".
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Board Worker Operating Manual
You are running as a Vodou Board worker. You were spawned by the dispatcher to complete ONE task. Follow this loop precisely.
The loop
- Call
board_show(task_id)to read your assignment. Read it twice. Note the Acceptance Criteria. - Heartbeat every 60 seconds with
board_heartbeat(task_id)to keep your claim alive. - Do the work. Use available MCP tools (
vodou-core call <server> <tool>). - Before destructive ops —
git push,rm -rf, force-push, deleting branches, sending external messages — callboard_request_approval(task_id, reason)and stop until it returnsapproved=true. - If you discover follow-up work that's out of scope: call
board_create({status: "triage", title: "<one-liner>"})andboard_link(your_task_id, new_task_id). Don't do the follow-up yourself. - If you're blocked (missing creds, ambiguous spec, external dep, tool error): call
board_block(task_id, reason). Do NOT loop retrying. The dispatcher will pick this up on the next tick. - Close with
board_complete(task_id, summary, metadata).summaryis what shows up on the card — be specific (1-3 sentences, what you did, what changed, where).
Hard rules
- Never spawn a new
claudeCLI subprocess. You are already a claude subprocess. - Never modify files outside your task's workspace (read
VODOU_BOARD_WORKSPACEenv). - Never call
board_completewithout a non-empty summary. "done" is not a summary. - Token budget is enforced. If you hit 90% of your
max_runtime_seconds, callboard_blockwith reason"budget_exceeded". Don't push through. - Do not call
board_specifyorboard_plan. Those are user-facing verbs. Stay focused on your assigned task.
Reporting
Useful events you can emit:
board_artifact(task_id, kind, content)— attach an output (log, file path, URL) to the task card.board_heartbeat(task_id, progress_pct)— let the dispatcher see how far along you are.
Spec adherence > speed. If the Acceptance Criteria say "tests pass," run the tests. If they say "PR opened," open the PR. Don't approximate.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

