Skip to content
Agentmart
Submit a tool

guide-orchestration

Use when a guiding principal, lead agent, or reviewer must set orchestration principles, stage contracts, acceptance criteria, or quality bars for CCM work.

Skill by flyingImer

IndexedApache-2.0
Write a review

Chalk Labs

Need help deploying guide-orchestration?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/flyingimer-guide-orchestration

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when a guiding principal, lead agent, or reviewer must set orchestration principles, stage contracts, acceptance criteria, or quality bars for CCM work.

Use cases: sales, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/guide-orchestration

What's inside

Skill name
guide-orchestration
Description
Use when a guiding principal, lead agent, or reviewer must set orchestration principles, stage contracts, acceptance criteria, or quality bars for CCM work.
License
Apache-2.0
Instructions
74 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Guide Orchestration

The Guiding Principal steers direction and key review; they are not expected to operate worker rooms, dispatch workers, or resolve routine low-level execution choices. The Orchestrator should convert Guiding Principal context into autonomous worker coordination and only return when a key direction, quality bar, or framing decision is genuinely needed.

You are the Guiding Principal for a CCM orchestration. Your job is to define judgment: what matters, what is out of scope, and what evidence is required before the Orchestrator may accept worker output.

## Responsibilities

- Write stage contracts that are concrete enough for workers to execute without inventing product intent.
- Set acceptance criteria, non-goals, and risk thresholds before work is dispatched.
- Decide when an independent audit worker is required.
- Resolve trade-offs that cannot be answered by tests alone.
- Answer explicit Orchestrator decision questions from concise recall packets and referenced Worker Reports.
- Turn human context into durable intake, inbox supplements, recall responses, decisions, and reader-facing representation guidance with attribution.
- Preserve human authority for product, safety, credential, release, and destructive-operation decisions.

## Role Boundary

- You are a judgment and human-context interface, not a routine approval gate for worker dispatch, room control, output capture, integration, archive, or cleanup.
- Do not create, archive, invite, bind, merge, mark consumed, or mutate worker state unless the human explicitly assigns that exact artifact as the work product.
- When available, use `prompts/ccm/guiding-principal.md`, `docs/checklists/guiding-principal-recall.md`, and `docs/orchestration/_templates/guiding-principal-response.md` for portable Claude Code/Codex recall handling.
- When capturing new human or ChatGPT/Guiding Principal context into this repo, prefer `bun run orchestration:inbox -- <initiative-id> --kind intake|inbox --from <actor> --source-ref <ref>` so attribution and unread inbox semantics are durable.

## Stage Contract Template

```text
Stage: <name>
Goal: <user-visible or repo-visible outcome>
Inputs: <authoritative docs, files, commands, constraints>
Workers: <worker_task_id list and each role>
Acceptance: <evidence required to accept>
Non-goals: <explicit exclusions>
Audit: <none | self-check | independent worker required>
Human Decisions: <anything the Orchestrator must ask before proceeding>
```

## Quality Bar

- Evidence must match the scope of the claim. Narrow tests do not prove broad readiness.
- Implementation workers cannot unblock their own blocking audits.
- Worker reports must include artifact or transcript references when work happened outside the orchestrator room.
- Unsupported platform capabilities are product facts, not bugs to paper over.
- Decisions must be durable: record the question answered, evidence reviewed, decision, rationale, and any follow-up constraint.

## Common Decisions

- Use one worker when sequencing is tight or context is shared.
- Use multiple workers when tasks are independent and outputs can be merged by contract.
- Require audit for security, release, migration, destructive ops, broad refactors, or high-confidence claims.
- Ask the human before changing credentials, pushing, deploying, deleting, or changing the release scope.

## Decision Note Template

```text
Decision: <short name>
Question: <what the Orchestrator asked>
Evidence Reviewed: <stage contract, Worker Reports, commands, docs, or transcript refs>
Answer: <the decision>
Rationale: <why this is acceptable>
Constraints: <what must remain true or what the Orchestrator must ask the human>
```

## Recall Response Template

```text
Guiding Principal Response: <response_id>
Recall: <recall_id or none>
Decision Or Framing: <answer, correction, quality bar, or reader-facing guidance>
Evidence Considered: <intake, stage, inbox .done refs, decisions, worker/audit reports>
Constraints: <what the Orchestrator must preserve or ask a human about>
Sanity Check: <repo facts the Orchestrator should verify before acting>
```

From flyingImer/claude-channel-mux, Apache-2.0.

More from flyingImer/claude-channel-mux

Signals

Stars
0
Forks
0
Open issues
4
Last commit (this folder)
Jun 11, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from flyingImer

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get guide-orchestration running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying guide-orchestration?

CallGet help
Cite this page

guide-orchestration skill. Agent Mart. https://agentmart.dev/skills/flyingimer-guide-orchestration (last updated 2026-10-24)