New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Init Project Orchestration

by flonat in flonat/flonat-research

Create or migrate project-level agents, repeatable project workflows, and planning state from one client-neutral contract, then render repository-scoped adapters for both Claude Code and Codex.

MITAuto-check passedDevelopment

Install Init Project Orchestration

skills CLI
$ npx skills add flonat/flonat-research --skill init-project-orchestration -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install flonat/flonat-research init-project-orchestration --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/flonat/flonat-research.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/init-project-orchestration .claude/skills/init-project-orchestration && rm -rf skills-src

Use ~/.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/

Facts

Skill name
init-project-orchestration
GitHub stars
146
Token cost
~1.6k tokens
SKILL.md length
667 words
Files
11 (incl. scripts)
Skills in repo
83
Repo updated
First seen
Licence
MIT

At a glance

Create or migrate project-level agents, repeatable project workflows, and planning state from one client-neutral contract, then render repository-scoped adapters for both Claude Code and Codex.

  • Works in 6 steps: Assess → Confirm the design → Author neutral sources → …
  • A research project needs role separation
  • SKILL.md covers Resulting structure, Phase 1: Assess, Phase 2: Confirm the design and Phase 3: Author neutral sources, plus 4 more sections
  • Runs Python scripts from its folder; calls uv

What it does

Init Project Orchestration is an agent skill from flonat/flonat-research. Create or migrate project-level agents, repeatable project workflows, and planning state from one client-neutral contract, then render repository-scoped adapters for both Claude Code and Codex. Use when a research project needs role separation, project commands, formal phase tracking, or conversion from an existing Claude-only .claude/agents and .claude/commands setup.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts (for example `scripts/project-orchestration.py`, `templates/agent-template.md` and `templates/command-template.md`).

It sits in Development, covering Project scaffolding. The repository describes itself as: Shareable Claude Code + Codex infrastructure for PhD researchers — skills, agents, hooks, and rules for academic workflows. The licence is MIT.

When your agent uses it

  • A research project needs role separation
  • Project commands
  • Formal phase tracking
  • Conversion from an existing Claude-only .claude/agents and .claude/commands setup

Example prompts

  • “/init-project-orchestration”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Assess
  2. Confirm the design
  3. Author neutral sources
  4. Reconcile an existing Claude project
  5. Render and verify
  6. Planning and guidance pointers

What it can do on your machine

Read from SKILL.md and the folder at commit da27600. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    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

Init Project Orchestration loads about 1.6k tokens when it runs. Until then it costs about 100 tokens; SKILL.md has 667 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~100
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from flonat/flonat-research at commit da27600, republished under its MIT licence (© flonat). 667 words, ~1,613 tokens.

Download SKILL.mdSave it as .claude/skills/init-project-orchestration/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
init-project-orchestration
description
Create or migrate project-level agents, repeatable project workflows, and planning state from one client-neutral contract, then render repository-scoped adapters for both Claude Code and Codex. Use when a research project needs role separation, project commands, formal phase tracking, or conversion from an existing Claude-only .claude/agents and .claude/commands setup.

Initialize project orchestration

Create the project source once under .ai/orchestration/. Treat Claude Code and Codex files as generated adapters, never as parallel authoring surfaces.

Resulting structure

text
.ai/orchestration/                 # canonical, client-neutral source
├── manifest.yaml
├── agents/<role>.md
└── commands/<workflow>.md

.claude/agents/project-<role>.md   # generated Claude agent
.claude/commands/project/<workflow>.md
.codex/agents/project-<role>.toml  # generated Codex agent
.agents/skills/project-<workflow>/SKILL.md
.planning/roadmap.md               # shared project state
.planning/state.md

Claude exposes a workflow as /project:<workflow>. Codex exposes the same workflow as $project-<workflow>. Both adapters derive from the same neutral command body. The namespace prevents collisions with global skills.

Phase 1: Assess

  1. Resolve the project root from the argument or current directory. Confirm it is the intended research project before searching elsewhere.
  2. Read the active client's project guidance. Read neutral project facts from AI.md, README.md, docs/, and .context/; do not treat the sibling client's guidance file as an additional instruction set.
  3. Read .context/field-calibration.md, project memory, and .planning/ when present.
  4. Classify the project:
    • experimental: data preparation and empirical estimation;
    • computational: software, algorithms, simulations, or experiments;
    • theoretical: formal models and proofs;
    • mixed: select roles and workflows from more than one preset.
  5. Inventory existing neutral sources and generated adapters. Also inventory legacy non-generated .claude/agents/ and .claude/commands/ files.

Do not overwrite anything during assessment.

Phase 2: Confirm the design

Read the applicable preset under templates/presets/ and present:

  • proposed project agents and their exact read/write boundaries;
  • proposed project workflows and expected arguments;
  • the initial .planning/ phases;
  • any legacy single-client Claude files that need reconciliation.

Ask for one confirmation covering additions, removals, names, and project-specific standards. Agents implement; independent global agents review.

Phase 3: Author neutral sources

  1. Create .ai/orchestration/manifest.yaml from templates/manifest-template.yaml. Keep namespace: project unless an existing checked-in namespace would collide.
  2. Create one neutral agent source per confirmed role using templates/agent-template.md.
  3. Create one neutral command source per confirmed workflow using templates/command-template.md.
  4. Always include commands/update-state.md, starting from templates/update-state-command.md.
  5. Populate real project paths, standards, and ownership boundaries. Do not leave placeholders.

Canonical sources must not contain client-home paths, machine-absolute paths, Claude/Codex adapter directories, or client-specific invocation syntax. Refer to reusable global capabilities as “the latex skill”, for example.

Agent policy
  • Use artifact_contract.mode: response-only plus write_policy.project: read-only for an advisory agent.
  • Use artifact_contract.mode: project-write plus write_policy.project: scoped-write for an implementation agent.
  • Keep write_policy.git: forbidden unless the user explicitly authorizes Git mutation as part of that role.
  • Declare behavioral capabilities and the minimum Claude adapter tools. Codex derives a read-only or workspace-write sandbox from the neutral write policy.
  • Treat every data/raw/ path as read-only.
Show full SKILL.md (287 more words)Show less

Phase 4: Reconcile an existing Claude project

If legacy project agents or commands exist:

  1. Read every non-generated legacy file.
  2. Convert its substantive behavior into the matching neutral source.
  3. Replace client-bound guidance-file reads with “active client guidance” plus the relevant neutral project files.
  4. Convert slash-skill calls to semantic skill references.
  5. Preserve tool and write restrictions in neutral policy fields.
  6. Compare the neutral source against the legacy file before rendering.

The renderer refuses to overwrite a non-generated target. Keep unmatched legacy files in place and report them; never select one side silently.

Phase 5: Render and verify

Resolve scripts/project-orchestration.py relative to this skill directory, then run it through uv:

bash
uv run <skill-root>/scripts/project-orchestration.py render --project <project-root>
uv run <skill-root>/scripts/project-orchestration.py check --project <project-root>

The renderer:

  • validates the neutral schemas and portability constraints;
  • writes both clients' adapters atomically;
  • refuses symlinked parents and non-generated collisions;
  • removes only stale files carrying its own generated marker;
  • exits non-zero when check detects drift.

Never edit a generated adapter. Change .ai/orchestration/ and render again.

Phase 6: Planning and guidance pointers

Create .planning/roadmap.md and .planning/state.md from the bundled templates only when they are absent. When they exist, merge deliberately and preserve current decisions and progress.

Add a short pointer to each existing client guidance file without duplicating the orchestration body:

  • canonical project roles/workflows: .ai/orchestration/;
  • shared phase state: .planning/roadmap.md and .planning/state.md;
  • generated adapters for that client;
  • rerender command.

Do not create or overwrite a large CLAUDE.md or AGENTS.md merely to install orchestration. Shared project facts belong in neutral project documentation.

Completion report

Report:

  • neutral agent and workflow sources created or migrated;
  • generated Claude and Codex adapter counts;
  • planning files created, merged, or preserved;
  • any legacy file still awaiting reconciliation;
  • the exact renderer check result.

Do not commit or push unless the user separately requests it.

© flonat, 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 10 other files (scripts) in skills/init-project-orchestration of flonat/flonat-research.

  • SKILL.md
  • scripts/project-orchestration.py
  • templates/agent-template.md
  • templates/command-template.md
  • templates/manifest-template.yaml
  • templates/presets/computational.md
  • templates/presets/experimental.md
  • templates/presets/theoretical.md
  • templates/roadmap-template.md
  • templates/state-template.md
  • templates/update-state-command.md

Open the folder on GitHubat commit da27600

Compare with similar skills

Init Project 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.

Init Project Orchestration compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Init Project Orchestration this skillflonat/flonat-research146—~1.6kAutomated safety check: PassMIT
Nx Generatenomcopter/react-mosaic4.8k7 repos~1.9kAutomated safety check: PassCustom licence
PonytailDavidObando/gsharp5648 repos~1.7kAutomated safety check: PassMIT
Run Nx Generatornrwl/nx29k2 repos~592Automated safety check: NotesMIT
Conductor Setupgemini-cli-extensions/conductor3.8k—~4.2kAutomated safety check: PassApache-2.0
Mirage VFS Adapter Authoringstrukto-ai/mirage3.7k—~2.5kAutomated safety check: PassApache-2.0

Similar skills

  • Nx Generate

    nomcopter/react-mosaic

    Generate code using nx generators. An agent skill from nomcopter/react-mosaic.

    4.8k GitHub starsUsed in 7 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Ponytail

    DavidObando/gsharp

    Forces the laziest solution that actually works, simplest, shortest, most minimal.

    564 GitHub starsUsed in 8 repos~1.7k tokens
    DevelopmentAuto-check passed

  • Run Nx Generator

    nrwl/nx

    Run Nx generators with prioritization for workspace-plugin generators.

    29k GitHub starsUsed in 2 repos~592 tokens
    DevelopmentAuto-check: notes

  • Conductor Setup

    gemini-cli-extensions/conductor

    Scaffolds the project and sets up the Conductor environment.

    3.8k GitHub stars~4.2k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Mirage VFS Adapter Authoring

    strukto-ai/mirage

    Builds or extends a custom Mirage virtual filesystem adapter for an API, database, object store or app data, with a working mount configuration and filesystem tests.

    3.7k GitHub stars~2.5k tokensUpdated today
    DevelopmentAuto-check passed

  • Siteboon Backend Module Standards

    siteboon/claudecodeui

    Enforces this repository's TypeScript backend module architecture under server/: feature folders, barrel exports, and where shared types and utilities belong.

    14k GitHub stars~1.2k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from flonat/flonat-research

All 83 skills in this repo

  • Latex Posters

    flonat/flonat-research

    Create a large-format academic poster in LaTeX using beamerposter, tikzposter, or baposter.

    146 GitHub stars~1.5k tokensUpdated 9 days ago
    Auto-check: notes

  • Skill Creator

    flonat/flonat-research

    Create, revise, and evaluate reusable AI workflow skills, including trigger-quality tests.

    146 GitHub stars~4.4k tokensUpdated 9 days ago
    Auto-check passed

  • DOCX

    flonat/flonat-research

    Create, read, edit, or convert Microsoft Word documents while preserving professional document structure.

    146 GitHub stars~1.2k tokensUpdated 9 days ago
    Auto-check passed

  • PDF

    flonat/flonat-research

    Read, create, combine, split, rotate, OCR, watermark, secure, or extract content from PDF files.

    146 GitHub stars~488 tokensUpdated 9 days ago
    Auto-check passed

  • Pre Commit Audit

    flonat/flonat-research

    Deliver a fast pre-commit safety scan: file size, anonymity (author / affiliation strings in tex/bib), hardcoded secrets, and invisible-Unicode carriers.

    146 GitHub stars~2.8k tokensUpdated 9 days ago
    Auto-check: notes

  • Skill Extract

    flonat/flonat-research

    Extract reusable knowledge from the current session into a persistent skill.

    146 GitHub stars~2.4k tokensUpdated 9 days ago
    Auto-check passed

Categories

Questions about Init Project Orchestration

What does Init Project Orchestration do?

Create or migrate project-level agents, repeatable project workflows, and planning state from one client-neutral contract, then render repository-scoped adapters for both Claude Code and Codex. Init Project Orchestration is an agent skill from flonat/flonat-research. Create or migrate project-level agents, repeatable project workflows, and planning state from one client-neutral contract, then render repository-scoped adapters for both Claude Code and Codex.

When should I use Init Project Orchestration?

Init Project Orchestration fits situations like: A research project needs role separation; project commands; formal phase tracking; conversion from an existing Claude-only .claude/agents and .claude/commands setup.

How do I install Init Project Orchestration in Claude Code?

Run `npx skills add flonat/flonat-research --skill init-project-orchestration -a claude-code`. Or copy the skill folder (skills/init-project-orchestration in flonat/flonat-research) into .claude/skills/init-project-orchestration in your project. Claude Code loads it when a task matches its description.

How do I install Init Project Orchestration in Codex?

Run `npx skills add flonat/flonat-research --skill init-project-orchestration -a codex`. Or copy the skill folder (skills/init-project-orchestration in flonat/flonat-research) into .agents/skills/init-project-orchestration in your project. Codex loads it when a task matches its description.

Can I use Init Project 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 flonat/flonat-research --skill init-project-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/init-project-orchestration, .gemini/skills/init-project-orchestration, .github/skills/init-project-orchestration and .opencode/skills/init-project-orchestration in your project.

What does Init Project Orchestration need to run?

Going by SKILL.md and its folder, Init Project Orchestration needs Python for the scripts in its folder and the command-line tools its instructions call (uv). Our summary lists: Python 3.

Does Init Project Orchestration access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Init Project 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Init Project Orchestration use?

Init Project 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 Init Project Orchestration use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Init Project Orchestration?

Skills that share tags, products or a category with Init Project Orchestration: Nx Generate (nomcopter/react-mosaic, 4.8k stars), Ponytail (DavidObando/gsharp, 564 stars), Run Nx Generator (nrwl/nx, 29k stars) and Conductor Setup (gemini-cli-extensions/conductor, 3.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Init Project Orchestration?

flonat (a GitHub user) maintains it in flonat/flonat-research, which has 146 GitHub stars. The repository holds 83 skills in this directory. The repository was last updated on September 29, 2026.

Source: flonat/flonat-research on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.