websublimewebsublime/mister-anderson/skills/add-supervisor/SKILL.md

add-supervisor

Skill3 starsChanged 7 months agoMITView on GitHub

Create a new implementation supervisor for a specific technology. Invokes the Discovery agent in on-demand mode to fetch, filter, and inject the beads workflow into a specialist agent. Use when adding a new tech stack to the project (e.g., new package in monorepo).

In this repository21 other files it gives its agents.
- skills/setup/templates/AGENTS.mdAGENTS.md
- skills/setup/templates/CLAUDE.mdCLAUDE.md
- architectureSkill
- core-loopSkill
- doSkill
- implementationSkill
- investigateSkill
- manifestoSkill
- planSkill
- productSkill
- qualitySkill
- requirementsSkill
- researchSkill
- reviewSkill
- setupSkill
- specificationSkill
- specSkill
- subagents-disciplineSkill
- tasksSkill
- updateSkill
- workflowSkill

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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

Distinctive:
Create an implementation supervisor for a technology that doesn't have one yet.
line 9
Very specific:
If the user provides $ARGUMENTS, extract the technology name (e.g., rust, react, python, go, flutter).
line 14
Distinctive:
If technology provided: use it directly.
line 16
Distinctive:
Ask the user: "Which technology do you need a supervisor for?" </on-init>
line 21
Very specific:
Check if supervisor already exists: Search .claude/agents/ for files that match the technology name (e.g., rust → rust-supervisor.md, …
line 26
Distinctive:
No technology specified. Ask the user which technology they need a supervisor for.
line 30
Distinctive:
Ask: "Do you want to recreate it from scratch, or keep the existing one?"
line 36
Distinctive:
If recreate → proceed (Discovery will overwrite) </on-check-fail>
line 38
Very specific:
Verify the new supervisor file exists in .claude/agents/
line 61

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Add Supervisor

Create an implementation supervisor for a technology that doesn't have one yet.

<on-init>
If the user provides $ARGUMENTS, extract the technology name (e.g., `rust`, `react`, `python`, `go`, `flutter`).

If technology provided: use it directly.

If no technology provided:

List existing supervisors in .claude/agents/ matching *-supervisor.md
Present what's already covered
Ask the user: "Which technology do you need a supervisor for?"</on-init>

<on-check>
1. **Technology must be resolved.** Either from arguments or user input.
2. **Check if supervisor already exists.** Search `.claude/agents/` for files that match the technology name (e.g., `rust` → `rust-supervisor.md`, `python` → `python-backend-supervisor.md`).
</on-check>

<on-check-fail if="technology">
No technology specified. Ask the user which technology they need a supervisor for.
</on-check-fail>

<on-check-fail if="supervisor_exists">
A supervisor already exists for this technology: `{name}-supervisor.md`.

Ask: "Do you want to recreate it from scratch, or keep the existing one?"

If keep → stop
If recreate → proceed (Discovery will overwrite)</on-check-fail>

<on-execute>

Step 1: Dispatch Discovery

Dispatch the Discovery agent in on-demand mode to create a single supervisor:

Dispatch using exactly these parameters — no more, no less:

Agent(
    subagent_type="discovery",
    prompt="Create a supervisor for {technology}. This is on-demand mode — do NOT scan the full codebase. Create only the {technology} supervisor by fetching the specialist from the external directory, filtering the content, injecting the beads workflow, and writing to .claude/agents/. Also update the Supervisors section in CLAUDE.md."
)

Do NOT add extra parameters (e.g., isolation, run_in_background, etc.) unless the user explicitly requests it.

</on-execute>

<on-complete>
1. Verify the new supervisor file exists in `.claude/agents/`
2. Inform user: "Created `{name}-supervisor.md`. You can now use it in beads tasks by setting `--assignee {name}-supervisor` when creating the issue."
</on-complete>

<on-next>
Supervisor created. You can now assign tasks to this supervisor with `/tasks` (set `--assignee {name}-supervisor`) or start implementing with `/do`.
</on-next>

Download now (ZIP)

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free