agentleFS
sreejithramansreejithraman/SreeStack/skills/orchestration/SKILL.md

orchestration

Skill1 starsChanged 16 days agoMITView on GitHub

Resolve working-model defaults and coordinate agents in T3 Code. Use before implementation, diagnosis, research, or verification, or when assigning agents and integrating their results.

47 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use orca-cli, orca-per-workspace-env and 6 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.
  • HK-hubSkill

    orca-cli

    Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", "orca artifacts", "share HTML/Markdown", "public artifact link", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.

    Also in 5 projects that use this

  • stablyaiSkill

    orca-per-workspace-env

    Set up, review, debug, or validate an Orca per-workspace environment recipe: the on-demand, disposable runtime (cloud sandbox, VM, SSH host, or local container) Orca creates fresh for each workspace. Use to stand up a new recipe end to end, fix an `environmentRecipes` entry in `orca.yaml`, scaffold provider lifecycle scripts, or resolve an `orca vm recipe doctor` failure. Use `orca-cli` for ordinary worktree and workspace creation with no recipe involved.

    Also in 3 projects that use this

  • HK-hubSkill

    computer-use

    Use Orca's computer-use CLI to inspect and operate local desktop app windows through accessibility trees, screenshots, and safe UI actions. Use for desktop app interaction: list apps/windows, get app state, read visible UI, click controls, type, press keys, scroll, drag, set values, or perform accessibility actions. Also use for browser windows, webviews, Orca app UI, or other desktop UI. Triggers include "computer use", "orca computer", "read Spotify", "read Slack", "control/click/read in a desktop app", and "get app state".

    Also in 6 projects that use this

  • kongyo2Skill

    prompt-engineering

    Comprehensive prompt engineering framework for designing, optimizing, and iterating LLM prompts. This skill should be used when users request prompt creation, optimization, or improvement for any LLM task, or when users need help translating vague requirements into effective prompts through collaborative dialogue and iterative refinement.

    Also in 3 projects that use this

  • AnthropicSkill

    wrap-up

    Close out (or revisit) a Claude Managed Agent build — refresh the overview page, recap every primitive the founder now owns, show the run log and live status, suggest 1–2 tailored next upgrades, and sweep hygiene (sessions archived, key only in .env, no literal dates in deployment kickoffs). Use when the founder says "/wrap-up", "wrap up", "close it out", "where do things stand with my agent", or at the end of a /launch-your-agent build.

    Also in 3 projects that use this

  • MicrosoftSkill

    pr-review

    Verify the technical accuracy of a vscode-docs pull request against the VS Code source code in microsoft/vscode. Use when reviewing a docs PR for factual correctness: setting names, command IDs, default values, API shapes, keybindings, versioned availability, and described behavior.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify the integrated result against the original requirements.

    line 48
  2. Distinctive:

    Use review-fix-loop for behavior and agent-procedure changes.

    line 50
  3. Distinctive:

    Use showroom before handoff when the integrated result is something the user can inspect or try.

    line 54

“Common” is measured: kept by at least 6 in 10 of the 42 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

Orchestration

The parent owns the outcome. Give independent, ready work to children when it improves speed or coverage; keep cohesive work with one owner. Use the applicable selection in agent routing, including when working directly. The working selection applies unless a task-specific selection or explicit user override covers the assignment.

Resolve that selection before doing the work. Continue directly only when this agent's effective model and effort match it or an explicit user override. Otherwise delegate the task with that selection, preserving the parent's configuration. Use the steps below for delegation, including a single cohesive task that needs the working model.

Assign

For design and implementation decisions, use Engineering Principles where its guidance helps the task. Include applicable references in implementation briefs.

Resolve the required outcome and proof before splitting it. Each child owns one result and a checkable completion condition. Separate writable paths and shared resources; serialize work that would collide. For competing approaches, choose the comparison criteria before dispatch. For tickets with blocking relationships, use task graphs.

Give each child a self-contained brief: requirements and accepted decisions, source paths and artifacts, owned output, permitted actions, shared files to preserve, checks, and return format. For verification or measurement, include exact revisions and the method. Assign further delegation explicitly when needed.

Finish assignment when every required slice has an owner, usable inputs, compatible ownership, and a completion check. Then follow agent routing to resolve the model and start ready work within the concurrency ceiling.

Accept

Inspect each result and its evidence. Account for every required slice as accepted, needing repair, rejected with a reason, or blocked. A completed child turn, a missing slice, or a mismatched verification revision/method is not proof of the parent outcome. Repair through the working model selection.

Verify the integrated result against the original requirements. Reuse checks while their revision and scope remain valid; rerun those affected by integration. Use review-fix-loop for behavior and agent-procedure changes. When pr will review the same complete scope before publication, let it own that loop once.

Use showroom before handoff when the integrated result is something the user can inspect or try. It chooses demonstrations and access; reuse applicable verification evidence.

Finish when every required result is integrated and its checks pass, or report the precise remaining gap. Return child task IDs and dispositions, artifacts, checks, requested/confirmed model settings, and blockers. Goal state, recurring work, and ordinary top-level threads use their explicitly requested host workflows; ordinary delegation creates none of them.

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.

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.