Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Project Orchestrator

ASecurity

This is the **project-scoped invocation of `catalyst-dev:steward`**, which is the canonical implementation of this role (its `SKILL.md` is CTL-1974's spec). The role is named `steward` in code and docs because this repo reserves the word *orchestrator* for the pipeline MACHINERY, never for an agent — so **run `catalyst-dev:steward` with scope = your project** and follow its loop. This file codifies the shape ORCH ran by hand on 2026-08-18 and points at the steward mechanics.

20 stars
0 votes
0 copies
3 views
Added 9/3/2026
ai-agentsgoreactapi

Works with

api

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add coalesce-labs/catalyst --skill project-orchestrator --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Project Orchestrator?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Project Orchestrator
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/coalesce-labs-project-orchestrator/badge)](https://www.skillsdirectory.com/skills/coalesce-labs-project-orchestrator)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: project-orchestrator
description:
  Run the project orchestrator — the long-lived, single-threaded owner of ONE project that moves
  ready backlog tickets to Todo, lets the fleet scheduler dispatch them, watches the work, and
  communicates in threaded Linear comments. Use when asked to run/own/coordinate a project or its
  backlog. It never dispatches a worker; Todo is its only dispatch verb.
user-invocable: true
---

# Project orchestrator — move ready tickets to Todo, watch, and speak in threads

This is the **project-scoped invocation of `catalyst-dev:steward`**, which is the canonical implementation of this role (its `SKILL.md` is CTL-1974's spec). The role is named `steward` in code and docs because this repo reserves the word *orchestrator* for the pipeline MACHINERY, never for an agent — so **run `catalyst-dev:steward` with scope = your project** and follow its loop. This file codifies the shape ORCH ran by hand on 2026-08-18 and points at the steward mechanics.

## The shape you run (from CTL-1974; steward implements each step)

1. **CLAIM** — assignee on the tracking ticket + 👀 the human's latest comment (`linear-ack.mjs`).
2. **SCOPE** — read the project + its tickets from the **replica** (freshness-gate the `-wal`).
3. **SELECT** — keep the READY tickets: four readiness tests → the `steward` skill's `references/readiness.md`.
4. **PLAN** — ONE top-level `Project orchestrator — <date>` comment; everything threads under it.
5. **DISPATCH** — move ready tickets to **Todo**, priority order, capped at the fleet's free slots →
   the `steward` skill's `references/dispatch.md`.
6. **WATCH** — bounded replica poll ≤ 5 min: state changes, comments, PRs on your scope.
7. **SPEAK** — reply in the thread the message arrived in; a human decision → an **ask**, then
   proceed on the default → the `steward` skill's `references/threads.md`, the `ask` skill's `references/threading.md`.
8. **CLOSE** — a merged PR's ticket goes to **Done**, stated in the project thread.

(Steward adds STATUS DOC and HAND OFF — the `steward` skill's `references/status-doc.md` and `references/resume.md`. A stalled ticket gets a nudge in its own thread — the `steward` skill's `references/stalls.md`.)

## Invariants (must survive codification)

- **Todo is your only dispatch verb** — never a worker, worktree, `claude -p`, or phase agent, and
  you write **no product code**: you change ticket state and post comments.
- **Never dispatch a worker directly** — you change state; the *existing* pull-based fleet scheduler
  dispatches. That is the architectural point.
- **A cap is never silent** — every ready ticket you did not dispatch is named, with why.
- **Reads → the replica** (freshness-gate the `-wal`, not the `.db`); **writes → the cloud proxy**
  (comment/state/label/reaction routes), not `api.linear.app` (CTL-1961 v1 gate).
- **Comment threads are ONE level deep** — a `parentId` must be a top-level comment.
- **Never reply as the human** — anything needing them is an ask (Options + Default if silent).

## Pointers

`catalyst-dev:steward` (canonical engine) · `catalyst-dev:ask` · `catalyst-dev:linearis` · `catalyst-dev:gherkin-ticket`.

Attribution

coalesce-labscoalesce-labs
View sourceMore from coalesce-labs →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →