agentleFS
Sign inStart free
daiduo2daiduo2/local-proof-loop/skills/orchestrator/SKILL.md

orchestrator

Skill0 starsChanged 7 months agoMITView on GitHub

Use this skill when acting as the host-side orchestrator in the local proof loop. This is the host-side control plane. It is responsible for publishing runs, processing solver submissions, invoking reviewer behavior when needed, and returning either a terminal result or the next solver round packet. You are not the solver. You do not write theorem bodies. You do not replace deterministic Lean execution. Prefer the local HTTP facade: Typical local base URL: Reviewer behavior is host-side only. If the…

80 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use worker, planner and 9 more.

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.
  • stotihvSkill

    worker

    Execute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools from AGENTS.md, and reports progress to orchestrator.

    Also in 3 projects that use this

  • am-willSkill

    planner

    Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: "make a plan", "create a plan", "plan this out", "plan the implementation", "help me plan", "design a plan", "draft a plan", "write a plan", "outline the steps", "break this down into tasks", "what's the plan for", or any similar planning request. Also triggers on explicit "/planner" or "/plan" commands.

    Also in 4 projects that use this

  • yakatotechSkill

    advisor

    Provide improvement suggestions and advice on work content. Use for document review, efficiency suggestions, and best practices

    Also in 3 projects that use this

  • AWSSkill

    planning

    Discovers user intent and generates a structured, step-by-step plan for model customization workflows. This skill must always be activated alongside any other skill when the user's request relates to model customization — including fine-tuning, training, building, customizing, reviewing data, or getting advice on approach, regardless of domain. Do not skip this skill even if the immediate ask is narrow (e.g., reviewing data format or a single workflow step), because planning discovers the full scope of work needed. Also activate when the user wants to resume, continue, or modify an existing plan.

    Also in 3 projects that use this

  • OpenAISkill

    observability

    Vercel Observability expert guidance — Drains (logs, traces, speed insights, web analytics), Web Analytics, Speed Insights, runtime logs, custom events, OpenTelemetry integration, and monitoring dashboards. Use when instrumenting, debugging, or optimizing application performance and user experience on Vercel.

    Also in 3 projects that use this

  • scott2bSkill

    obsidian

    PROACTIVELY use for Obsidian vault operations. Fast search using ripgrep, direct file operations (read/write/delete). Works with slipbox in _Slipbox directory. 4-7x faster than API. Use obsidian-api skill ONLY for Dataview queries, periodic notes, or patch operations.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 66 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when acting as the host-side orchestrator in the local proof loop.

    line 3
  2. Distinctive:

    call the host-side external protocol

    line 15
  3. Distinctive:

    keep Hermes on the solver side only

    line 16
  4. Distinctive:

    Prefer the local HTTP facade:

    line 21
  5. Distinctive:

    if the host needs no work, report current status

    line 56
  6. Very specific:

    if the host needs reviewer work, read the returned exec_result, produce a reviewer result, and send it back

    line 57
  7. Very specific:

    If the host responds with needs_reviewer, produce a review_result grounded in the returned exec_result, then call the host-side review …

    line 67
  8. Distinctive:

    Do not send reviewer work through Hermes.

    line 72

“Common” is measured: kept by at least 6 in 10 of the 66 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.

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

Orchestrator Skill

Use this skill when acting as the host-side orchestrator in the local proof loop.

This is the host-side control plane. It is responsible for publishing runs, processing solver submissions, invoking reviewer behavior when needed, and returning either a terminal result or the next solver round packet.

Core Role

You are not the solver. You do not write theorem bodies. You do not replace deterministic Lean execution.

You do:

  • call the host-side external protocol
  • keep Hermes on the solver side only
  • move runs from publish to complete/stop or back to awaiting_solver

Preferred Surface

Prefer the local HTTP facade:

  • POST /publish
  • POST /submit
  • POST /process
  • POST /review
  • GET /status

Typical local base URL:

  • http://127.0.0.1:8788

Modes

Publish Mode

Input:

  • a packaged problem.json
  • or a problem_id when the host service already knows the packaged problem

Output:

  • run_id
  • status: awaiting_solver
  • round-1 solver_round_input

Process Mode

Input:

  • an existing run_id

Behavior:

  • if the host needs no work, report current status
  • if the host needs reviewer work, read the returned exec_result, produce a reviewer result, and send it back
  • continue until the run either:
    • returns awaiting_solver
    • returns complete
    • returns stop

Reviewer Boundary

Reviewer behavior is host-side only.

If the host responds with needs_reviewer, produce a review_result grounded in the returned exec_result, then call the host-side review operation.

Solver-facing theorem-query tools do not change this boundary. They may assist the solver, but they must not expose reviewer artifacts or replace internal host-side review.

Do not send reviewer work through Hermes.

Minimal Invocation Convention

Examples:

  • Use the orchestrator skill with http://127.0.0.1:8788 on problem minif2f_mathd_algebra_478 and publish a new run.
  • Use the orchestrator skill with http://127.0.0.1:8788 on run minif2f_mathd_algebra_478/run_005 and process the host side until Hermes is needed again or the run terminates.

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