do
Skill3 starsChanged 7 months agoMITView on GitHub
Dispatch the implementation supervisor for a bead task. Resolves the correct supervisor from the assignee field, checks branch state, and dispatches with full context.
In this repository21 other files it gives its agents.
- skills/setup/templates/AGENTS.mdAGENTS.md
- skills/setup/templates/CLAUDE.mdCLAUDE.md
- add-supervisorSkill
- architectureSkill
- core-loopSkill
- implementationSkill
- investigateSkill
- manifestoSkill
- planSkill
- productSkill
- qualitySkill
- requirementsSkill
- researchSkill
- reviewSkill
- setupSkill
- specificationSkill
- specSkill
- subagents-disciplineSkill
- tasksSkill
- updateSkill
- workflowSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
19 rules. About 0 are common, 10 are distinctive, and 9 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
If the user provides $ARGUMENTS, check if it contains a bead ID (e.g., bd-a3f, bd-001.2).
- Distinctive: line 16
If bead ID provided: use it directly.
- Very specific: line 19
Run bd ready --json to get unblocked tasks
- Very specific: line 26
Investigation should exist: Read bead comments: bd comments {BEAD_ID}.
- Distinctive: line 34
No investigation found for this bead.
- Very specific: line 37
Ask: "Do you want to run /investigate {BEAD_ID} first, or proceed without investigation?"
- Very specific: line 38
If user wants investigation → stop and recommend /investigate
- Distinctive: line 39
If user proceeds → continue to dispatch </on-check-fail>
- Distinctive: line 49
Read the design doc content — this is the implementation contract
- Very specific: line 54
Read the assignee field from the bead JSON — this contains the supervisor name (e.g., rust-supervisor)
- Very specific: line 56
Verify the agent file exists: .claude/agents/{assignee}.md
- Distinctive: line 57
If found → supervisor resolved
- Distinctive: line 58
If NOT found → warn user, fall through to manual selection
- Distinctive: line 63
Ask: "Which supervisor should handle this task?"
- Very specific: line 64
If user wants to create → stop and suggest /add-supervisor, then re-run /do
- Distinctive: line 74
Ask: "Continue on the existing branch, or create a fresh branch?"
- Distinctive: line 78
Ask: "Which branch should I base from?
- Distinctive: line 107
Decisions/Deviations: if the supervisor logged DECISION or DEVIATION comments, explain each in plain language — what choice was made, why, …
- Very specific: line 113
After the supervisor completes, recommend /review {BEAD_ID} for code review.
≈ “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
Do
Dispatch the implementation supervisor for a bead task. Handles supervisor resolution, branch management, and dispatch with full investigation context.
<on-init>
If the user provides $ARGUMENTS, check if it contains a bead ID (e.g., `bd-a3f`, `bd-001.2`).If bead ID provided: use it directly.
If no bead ID provided:
- Run
bd ready --jsonto get unblocked tasks - Present the list showing: ID, title, priority, and labels
- Pick by order and priority; if unclear, ask the user
</on-init>
<on-check>
1. **Bead must exist.** Validate with `bd show {BEAD_ID} --json`.
2. **Investigation should exist.** Read bead comments: `bd comments {BEAD_ID}`. Search for `INVESTIGATION:`.
</on-check><on-check-fail if="bead">
Bead does not exist. Inform the user and stop.
</on-check-fail><on-check-fail if="investigation">
No investigation found for this bead. Warn:
"No investigation found. The supervisor will implement without codebase analysis. This can lead to missed edge cases."Ask: "Do you want to run /investigate {BEAD_ID} first, or proceed without investigation?"
- If user wants investigation → stop and recommend
/investigate - If user proceeds → continue to dispatch
</on-check-fail>
<on-execute>Step 1: Read Full Bead Context
- Parse bead JSON. Extract:
description,acceptance,design,notes,status,parent,labels - If bead is an epic child (BEAD_ID contains a dot):
- Extract EPIC_ID, read the epic, extract design doc path
- Read the design doc content — this is the implementation contract
- Store all context for the dispatch prompt
Step 2: Resolve Supervisor
- Read the
assigneefield from the bead JSON — this contains the supervisor name (e.g.,rust-supervisor) - If
assigneeis set and non-empty:- Verify the agent file exists:
.claude/agents/{assignee}.md - If found → supervisor resolved
- If NOT found → warn user, fall through to manual selection
- Verify the agent file exists:
- If
assigneeis empty or unset:- List available supervisors: find all
*-supervisor.mdin.claude/agents/ - Present the list
- Inform: "If the supervisor you need is not listed, create one with
/add-supervisor {technology}." - Ask: "Which supervisor should handle this task?"
- If user wants to create → stop and suggest
/add-supervisor, then re-run/do
- List available supervisors: find all
Step 3: Check Branch State
git branch -a | grep {BEAD_ID}If branch exists:
- Inform user: "A branch already exists:
{branch-name}. This may be from a previous implementation attempt." - Ask: "Continue on the existing branch, or create a fresh branch?"
- Include context in dispatch prompt
If no branch exists:
- Ask: "Which branch should I base from? (default:
main)" - Store as
{BASE_BRANCH}
Step 4: Dispatch Implementation Supervisor
- Announce before dispatching:
Dispatching {resolved-supervisor} for {BEAD_ID}: "{bead title}" - Dispatch using exactly these parameters — no more, no less:
Do NOT add extra parameters unless the user explicitly requests it.Agent( subagent_type="{resolved-supervisor}", prompt="Implement BEAD {BEAD_ID}. [Include EPIC_ID if epic child]. Base branch: {BASE_BRANCH} — run `git checkout {BASE_BRANCH}` before creating your feature branch. Read the bead (bd show {BEAD_ID}) and comments (bd comments {BEAD_ID}) for full context — description, acceptance criteria, design notes, and investigation findings." ) - The
PreToolUsehook automatically injects the discipline reminder because the agent name ends in-supervisor.
</on-execute><on-complete>
Present the result following the **Presenting to the User** guidelines:- Headline: "{bead title} — implementation complete" in plain language
- What was done: 1-2 sentences summarizing what the supervisor built — translate the COMPLETED bead comment into natural language, don't paste raw
- Branch and PR: show branch name and PR URL (look for
PR:in the completion report or bead comments) - Decisions/Deviations: if the supervisor logged DECISION or DEVIATION comments, explain each in plain language — what choice was made, why, and what the alternative was
- Next step: recommend
/review {BEAD_ID} - Technical details: raw COMPLETED comment and file list in a
<details>block</on-complete>
<on-next>
After the supervisor completes, recommend `/review {BEAD_ID}` for code review.
</on-next>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.

