Orca CLI
stablyai/orca
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…
This skill should be used when orchestrating complex writing workflows with multiple phases.
Install Writing Orchestration
$ npx skills add robertguss/claude-code-toolkit --skill writing-orchestration -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install robertguss/claude-code-toolkit writing-orchestration --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/robertguss/claude-code-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/compound-writing/skills/writing-orchestration .claude/skills/writing-orchestration && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "writing-orchestration" agent skill from https://github.com/robertguss/claude-code-toolkit/tree/main/plugins/compound-writing/skills/writing-orchestration into .claude/skills/writing-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-orchestration", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/robertguss/claude-code-toolkit/tree/main/plugins/compound-writing/skills/writing-orchestrationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add robertguss/claude-code-toolkit --skill writing-orchestration -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install robertguss/claude-code-toolkit writing-orchestration --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/robertguss/claude-code-toolkit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/compound-writing/skills/writing-orchestration .agents/skills/writing-orchestration && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "writing-orchestration" agent skill from https://github.com/robertguss/claude-code-toolkit/tree/main/plugins/compound-writing/skills/writing-orchestration into .agents/skills/writing-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-orchestration", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add robertguss/claude-code-toolkit --skill writing-orchestration -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install robertguss/claude-code-toolkit writing-orchestration --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/robertguss/claude-code-toolkit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/compound-writing/skills/writing-orchestration .cursor/skills/writing-orchestration && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "writing-orchestration" agent skill from https://github.com/robertguss/claude-code-toolkit/tree/main/plugins/compound-writing/skills/writing-orchestration into .cursor/skills/writing-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-orchestration", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/robertguss/claude-code-toolkit.git --path plugins/compound-writing/skills/writing-orchestration--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add robertguss/claude-code-toolkit --skill writing-orchestration -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install robertguss/claude-code-toolkit writing-orchestration --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/robertguss/claude-code-toolkit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/compound-writing/skills/writing-orchestration .gemini/skills/writing-orchestration && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "writing-orchestration" agent skill from https://github.com/robertguss/claude-code-toolkit/tree/main/plugins/compound-writing/skills/writing-orchestration into .gemini/skills/writing-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-orchestration", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install robertguss/claude-code-toolkit writing-orchestrationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add robertguss/claude-code-toolkit --skill writing-orchestration -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/robertguss/claude-code-toolkit.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/compound-writing/skills/writing-orchestration .github/skills/writing-orchestration && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "writing-orchestration" agent skill from https://github.com/robertguss/claude-code-toolkit/tree/main/plugins/compound-writing/skills/writing-orchestration into .github/skills/writing-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-orchestration", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add robertguss/claude-code-toolkit --skill writing-orchestration -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install robertguss/claude-code-toolkit writing-orchestration --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/robertguss/claude-code-toolkit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/compound-writing/skills/writing-orchestration .opencode/skills/writing-orchestration && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "writing-orchestration" agent skill from https://github.com/robertguss/claude-code-toolkit/tree/main/plugins/compound-writing/skills/writing-orchestration into .opencode/skills/writing-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-orchestration", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
writing-orchestration- GitHub stars
- 123
- Token cost
- ~1.9k tokens
- SKILL.md length
- 705 words
- Files
- 4 (incl. references)
- Skills in repo
- 16
- Repo updated
- First seen
- Licence
- MIT
At a glance
This skill should be used when orchestrating complex writing workflows with multiple phases.
- Works in 4 steps: Generate 3 different drafts → Vary angle, not just words → Apply all strategies to each → …
- Tasks that involve Audit readiness
- SKILL.md covers When to Use This Skill, Two-Agent Architecture, Two-Gate Content Readiness… and 10 Baseline Strategies (ALWAYS…, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Writing Orchestration is an agent skill from robertguss/claude-code-toolkit. This skill should be used when orchestrating complex writing workflows with multiple phases. It provides two-agent orchestration patterns, the two-gate content readiness assessment, 10 baseline writing strategies, 20+ situational strategies, and quality checkpoints. Inspired by the Spiral Writing System.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/baseline-strategies.md`, `references/quality-checkpoints.md` and `references/situational-strategies.md`).
It sits in Agent Workflows, covering Audit readiness and Multi-agent orchestration. The repository describes itself as: A collection of custom skills that extend Claude's capabilities with specialized workflows, methods, and domain knowledge. The licence is MIT.
When your agent uses it
- Tasks that involve Audit readiness
- Tasks that involve Multi-agent orchestration
Example prompts
- “/writing-orchestration”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Generate 3 different drafts
- Vary angle, not just words
- Apply all strategies to each
- Let user choose direction
What it can do on your machine
Read from SKILL.md and the folder at commit f7fd35e. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Writing Orchestration loads about 1.9k tokens when it runs, and up to ~6.1k if it reads all its reference files. Until then it costs about 82 tokens; SKILL.md has 705 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from robertguss/claude-code-toolkit at commit f7fd35e, republished under its MIT licence (© robertguss). 705 words, ~1,912 tokens.
Download SKILL.mdSave it as
.claude/skills/writing-orchestration/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- writing-orchestration
- description
- This skill should be used when orchestrating complex writing workflows with multiple phases. It provides two-agent orchestration patterns, the two-gate content readiness assessment, 10 baseline writing strategies, 20+ situational strategies, and quality checkpoints. Inspired by the Spiral Writing System.
Writing Orchestration Skill
A complete orchestration system for complex writing workflows. This skill provides the strategic layer that coordinates agents, applies writing strategies, and ensures content quality.
When to Use This Skill
This skill applies when:
- Coordinating multiple writing agents
- Applying strategic writing decisions
- Assessing content readiness before drafting
- Selecting and applying writing strategies
- Running quality checkpoints on drafts
Two-Agent Architecture
Complex writing benefits from separation of concerns:
Orchestrator Role
- Classifies requests (information vs. content)
- Applies two-gate assessment
- Gathers research and context
- Hands off to writer when ready
- Never creates content directly
Writer Role
- Creates drafts using strategies
- Applies style guides
- Produces variations (EXPLORATION mode)
- Refines based on feedback (REFINEMENT mode)
- Uses tools for all content (never in chat)
User Request
↓
[Orchestrator] → Classify → Research → Two-Gate Assessment
↓
├── Not Ready → Gather more material/clarity
↓
└── Ready → Handoff to Writer
↓
[Writer] → Apply Strategies → Create Drafts
↓
Quality Checkpoints → OutputTwo-Gate Content Readiness Assessment
Before any content creation, apply this assessment:
Gate 1: Material Sufficiency
Question: "Could the writer create this without inventing facts?"
| Outcome | Action |
|---|---|
| ✓ Pass | Have concrete examples, data, quotes available |
| ✗ Fail | Need to research/gather material first |
Pass signals:
- Specific examples available
- Data points confirmed
- Expert quotes accessible
- No major claims need fabrication
Gate 2: Message Clarity
Question: "Do we know EXACTLY what message to convey?"
| Outcome | Action |
|---|---|
| ✓ Pass | Clear, specific communication goal |
| ✗ Fail | Need to interview for clarity |
Pass signals:
- Can state thesis in one sentence
- Know the audience specifically
- Know the desired action
- Angle is differentiated
Decision Matrix
| Material | Message | Action |
|---|---|---|
| ✓ | ✓ | Handoff to writer immediately |
| ✓ | ✗ | Interview for message clarity |
| ✗ | ✓ | Research/gather material |
| ✗ | ✗ | Interview for both |
10 Baseline Strategies (ALWAYS Apply)
These strategies apply to ALL content. Reference baseline-strategies.md for full details.
| Strategy | Rule | Transform |
|---|---|---|
| reader-zero-context | Add 3-6 word orienting phrases | "Stripe handles billing" → "Stripe, the payments platform, handles billing" |
| subject-verb | Subject + verb in first 5 words | "There were students who..." → "Students completed..." |
| activate-verbs | Precise verbs over is/was | "Markets were down" → "Markets plunged" |
| watch-adverbs | Let strong verbs carry load | "whispered quietly" → "whispered" |
| limit-ings | Simple tense over continuous | "are running tests" → "run tests" |
| prefer-simple | Everyday language unless technical | "utilizes stochastic gradient" → "learns by trial and error" |
| cut-big-small | Edit hierarchically | Paragraphs → Sentences → Words |
| ban-empty-hypophora | No self-answered questions | "The payoff? Our app..." → "Our app..." |
| present-active-tense | Direct, immediate language | "debuts today" → "is out now" |
| one-idea-per-sentence | Single clear point | Split compound thoughts |
20+ Situational Strategies (Select 3-4)
Choose based on content type and goals. Reference situational-strategies.md for full list.
Hook & Opening
- hook-effectiveness - Counterintuitive or surprising openings
- tension-builder - Create and resolve tension
- pattern-twist - Set expectations, then break them
Structure & Flow
- order-words-emphasis - Important words at sentence ends
- sentence-length - Vary for rhythm (short for impact, long for flow)
- paragraph-length - Mix for visual rhythm
- ladder-abstraction - Alternate concrete ↔ abstract
Show full SKILL.md (285 more words)Show less
Style & Voice
- elegant-variation - Avoid word repetition
- passive-aggressive - Strategic passive for emphasis
- punctuation-pace - Use punctuation for rhythm
- key-words-space - Give important terms breathing room
Persuasion & Engagement
- essential-name-filter - Only names that add value
- name-of-dog - Specific details for authenticity
- original-images - Fresh metaphors, avoid clichés
- show-and-tell - Balance showing with telling
Narrative & Story
- narrate-scenes - Immersive scene-setting
- cinematic-angles - Camera-like perspective shifts
- dialogue-compression - Tight, purposeful dialogue
- reveal-traits - Character through action
Quality Checkpoints
Before finalizing content, verify:
Opening Quality
- Opening is counterintuitive or surprising
- Leads with most compelling insight/moment/problem
- No chronology/setup/version numbers in opening
- Hook earns the next sentence
Body Quality
- Body delivers on opening's promise
- Concrete sensory details present
- Each paragraph has clear purpose
- Transitions are smooth
Strategy Compliance
- All 10 baseline strategies applied
- 3-4 situational strategies visible
- Each sentence expresses one clear idea
- Technical terminology oriented with context
Style Guide Compliance
- Voice matches profile/guide
- No prohibited words/patterns
- Formatting rules followed
Content Modes
EXPLORATION Mode (New Content)
When creating new content:
- Generate 3 different drafts
- Vary angle, not just words
- Apply all strategies to each
- Let user choose direction
REFINEMENT Mode (Editing)
When user provides feedback:
- Work with existing draft
- Preserve voice and structure
- Apply specific changes requested
- Keep what works
Handoff Protocol
Orchestrator → Writer
[Research summary if applicable - 2-3 sentences]
[Material gathered: list key assets]
[Message clarity: thesis statement]
[Style guide: name if applicable]
[Mode: EXPLORATION or REFINEMENT]Writer → Orchestrator (Rare)
Only when:
- User explicitly requests brainstorming
- New research topic needed
- Web search required
- Significant scope change
Integration with Commands
/writing:plan
Uses Orchestrator patterns:
- Request classification
- Research phase
- Two-gate assessment
- Material gathering
/writing:draft
Uses Writer patterns:
- Strategy application
- Mode selection
- Draft creation
- Quality checkpoints
/writing:review
Uses both:
- Orchestrator: coordinate review agents
- Writer: apply fixes
/writing:compound
Captures patterns that worked for future orchestration.
References
- baseline-strategies.md - Full 10 baseline strategies with examples
- situational-strategies.md - 20+ situational strategies
- quality-checkpoints.md - Detailed checkpoint criteria
© robertguss, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (references) in plugins/compound-writing/skills/writing-orchestration of robertguss/claude-code-toolkit.
- SKILL.md
- references/baseline-strategies.md
- references/quality-checkpoints.md
- references/situational-strategies.md
Open the folder on GitHubat commit f7fd35e
Compare with similar skills
Writing Orchestration next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Writing Orchestration this skillrobertguss/claude-code-toolkit | 123 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Orca CLIstablyai/orca | 88k | 2 repos | ~593 | Automated safety check: Pass | MIT | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| O2 Review Loopopenobserve/openobserve | 22k | — | ~3.7k | Automated safety check: Pass | AGPL-3.0 | |
| Paseo Committeegetpaseo/paseo | 20k | 1 repos | ~496 | Automated safety check: Pass | Custom licence | |
| Mission Control Agent APIbuilderz-labs/mission-control | 6.3k | — | ~2.1k | Automated safety check: Pass | MIT |
Similar skills
Paseo Advisor Second Opinion
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
Paseo Committee
getpaseo/paseo
Forms a two-agent committee with contrasting profiles to analyze a stuck problem in parallel, reconcile their views and return a consensus plan without editing files.
Mission Control Agent API
builderz-labs/mission-control
Teaches an agent to use the Mission Control dashboard API: register, send heartbeats, fetch assigned tasks, report progress and disconnect, with API key auth.
Paseo Agent Handoff
getpaseo/paseo
Hands off the current task, including context, decisions and failed attempts, to a fresh agent through Paseo by writing a self-contained briefing prompt and launching that agent.
More from robertguss/claude-code-toolkit
All 16 skills in this repoBrainstorm
robertguss/claude-code-toolkit
Collaborative brainstorming partner for multi-session ideation projects.
Voice Capture
robertguss/claude-code-toolkit
This skill should be used when extracting voice profiles from sample text, creating voice documentation, or matching a specific writing style.
Dhh Writing
robertguss/claude-code-toolkit
This skill should be used when writing in the distinctive style of David Heinemeier Hansson (DHH).
Pragmatic Writing
robertguss/claude-code-toolkit
This skill should be used when writing technical content in the style of Hunt/Thomas (The Pragmatic Programmer) and Joel Spolsky (Joel on Software).
App Store Opportunity Research
robertguss/claude-code-toolkit
Full-pipeline iOS App Store opportunity research. An agent skill from robertguss/claude-code-toolkit.
Book Architect
robertguss/claude-code-toolkit
Design the structural and emotional architecture for nonfiction books.
Related
Categories
Questions about Writing Orchestration
What does Writing Orchestration do?
This skill should be used when orchestrating complex writing workflows with multiple phases. Writing Orchestration is an agent skill from robertguss/claude-code-toolkit. This skill should be used when orchestrating complex writing workflows with multiple phases.
When should I use Writing Orchestration?
Writing Orchestration fits situations like: tasks that involve Audit readiness; tasks that involve Multi-agent orchestration.
How do I install Writing Orchestration in Claude Code?
Run `npx skills add robertguss/claude-code-toolkit --skill writing-orchestration -a claude-code`. Or copy the skill folder (plugins/compound-writing/skills/writing-orchestration in robertguss/claude-code-toolkit) into .claude/skills/writing-orchestration in your project. Claude Code loads it when a task matches its description.
How do I install Writing Orchestration in Codex?
Run `npx skills add robertguss/claude-code-toolkit --skill writing-orchestration -a codex`. Or copy the skill folder (plugins/compound-writing/skills/writing-orchestration in robertguss/claude-code-toolkit) into .agents/skills/writing-orchestration in your project. Codex loads it when a task matches its description.
Can I use Writing Orchestration in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add robertguss/claude-code-toolkit --skill writing-orchestration -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writing-orchestration, .gemini/skills/writing-orchestration, .github/skills/writing-orchestration and .opencode/skills/writing-orchestration in your project.
What does Writing Orchestration need to run?
SKILL.md names no scripts, command-line tools or credentials: Writing Orchestration is instructions for the agent only.
Does Writing Orchestration access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Writing Orchestration safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Writing Orchestration use?
Writing Orchestration is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Writing Orchestration use?
About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.1k tokens, read only when the agent opens those files.
What are the alternatives to Writing Orchestration?
Skills that share tags, products or a category with Writing Orchestration: Orca CLI (stablyai/orca, 88k stars), Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars), O2 Review Loop (openobserve/openobserve, 22k stars) and Paseo Committee (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Writing Orchestration?
robertguss (a GitHub user) maintains it in robertguss/claude-code-toolkit, which has 123 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on September 16, 2026.
Source: robertguss/claude-code-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.