Agent skill

Fund Orchestration

by SilvioBaratto in SilvioBaratto/optimizer

Sequence the fund pipeline and delegate to the four subagents (economist, allocator, risk, executor).

Custom licenceAuto-check passedAgent Workflows

Install Fund Orchestration

skills CLI
$ npx skills add SilvioBaratto/optimizer --skill fund-orchestration -a claude-code

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

GitHub CLI
$ gh skill install SilvioBaratto/optimizer fund-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/SilvioBaratto/optimizer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/fund/src/fund/skills/fund-orchestration .claude/skills/fund-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
fund-orchestration
GitHub stars
176
Token cost
~635 tokens
SKILL.md length
289 words
Files
2
Skills in repo
10
Repo updated
First seen
Licence
Custom licence

At a glance

Sequence the fund pipeline and delegate to the four subagents (economist, allocator, risk, executor).

  • Works in 5 steps: Confirm an active ConstraintSet exists… → Delegate each step with the task tool,… → Enforce the round cap: stop at… → …
  • The PM/orchestrator must plan a run
  • SKILL.md covers When to use, Load-bearing rule, Pipeline order (detail in… and Procedure, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Fund Orchestration is an agent skill from SilvioBaratto/optimizer. Sequence the fund pipeline and delegate to the four subagents (economist, allocator, risk, executor). Use when the PM/orchestrator must plan a run, hand a step to a subagent via the task tool, collect its structured report, and decide whether to proceed, re-run, or stop. Does NOT read the DB, call optimizer tools, or emit weights — it coordinates; the subagents and their tools do the work.

Its SKILL.md is about 640 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `reference.md`).

It sits in Agent Workflows, covering Subagents. The repository describes itself as: Quantitative portfolio construction and optimization platform built on skfolio and scikit-learn.

When your agent uses it

  • The PM/orchestrator must plan a run
  • Hand a step to a subagent via the task tool
  • Collect its structured report
  • Decide whether to proceed

Example prompts

  • “/fund-orchestration”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Confirm an active ConstraintSet exists for the portfolio (else route to the
  2. Delegate each step with the task tool, passing the ConstraintSet + the prior
  3. Enforce the round cap: stop at max_pm_rounds / recursion_limit; if hit, mark
  4. On a risk-gate BLOCK, return to the allocator with the violations — never override.
  5. Gate place_orders behind HITL; record every decision in the audit trail.

What it can do on your machine

Read from SKILL.md and the folder at commit 63e897b. 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

Fund Orchestration loads about 635 tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 289 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~103
When it runs · the whole SKILL.md, loaded when a task matches
~635

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 289 words (~635 tokens).

“The main agent (PM) runs the fund as a deterministic pipeline, not a free chat. It delegates each step to a stateless subagent with complete instructions, collects the typed report, and moves on. Subagents never chatter freely; the PM owns…”

— opening of SKILL.md by SilvioBaratto, Custom licence
name
fund-orchestration

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in fund/src/fund/skills/fund-orchestration of SilvioBaratto/optimizer.

  • SKILL.md
  • reference.md

Open the folder on GitHubat commit 63e897b

Compare with similar skills

Fund 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.

Fund Orchestration compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fund Orchestration this skillSilvioBaratto/optimizer176—~635Automated safety check: PassCustom licence
Claude Code Agent Developmentanthropics/claude-plugins-official38k7 repos~2.8kAutomated safety check: PassApache-2.0
Subagent Driven DevelopmentAsvarox/allkaraoke26137 repos~1.2kAutomated safety check: PassNone
Dispatching Parallel Agentsultralisp/ultralisp25840 repos~1.5kAutomated safety check: PassNone
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~11kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 7 repos~2.8k tokens
    Agent WorkflowsAuto-check passed
  • Subagent Driven Development

    Asvarox/allkaraoke

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    261 GitHub starsUsed in 37 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Dispatching Parallel Agents

    ultralisp/ultralisp

    A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    258 GitHub starsUsed in 40 repos~1.5k tokens
    Agent WorkflowsAuto-check passed
  • 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.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed
  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~11k tokens
    Agent WorkflowsAuto-check passed
  • 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.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from SilvioBaratto/optimizer

All 10 skills in this repo
  • Yfinance

    SilvioBaratto/optimizer

    Load proactively whenever the user works with yfinance or Yahoo Finance data — pulling price history, fetching financials or analyst data, screening stocks / funds / ETFs, streaming real-time…

    176 GitHub stars~4k tokensUpdated 3 days ago
    Auto-check: notes
  • DB Context

    SilvioBaratto/optimizer

    Complete knowledge of the optimizer PostgreSQL database: 57 ingestion tables, schema, relationships, live row counts, query patterns, and conventions.

    176 GitHub stars~6.4k tokensUpdated 3 days ago
    Auto-check: notes
  • Optimization Objective Map

    SilvioBaratto/optimizer

    Map a chosen ConstraintSet.objective to the correct optimizer cone / risk-measure and factory config.

    176 GitHub stars~510 tokensUpdated 3 days ago
    Auto-check passed
  • Macro Regime Read

    SilvioBaratto/optimizer

    Read macro/FRED series from the DB and label the current market regime for the economist.

    176 GitHub stars~403 tokensUpdated 3 days ago
    Auto-check passed
  • Rebalancing Execution

    SilvioBaratto/optimizer

    Translate approved target weights into paper orders under a no-trade band and an L1 turnover penalty, then place them behind human approval.

    176 GitHub stars~425 tokensUpdated 3 days ago
    Auto-check passed
  • Risk Limits Check

    SilvioBaratto/optimizer

    Validate a proposed weight vector against the ConstraintSet — drawdown ceilings nu1/nu2/nu3, ESG hard gate, robust uncertainty, and a walk-forward backtest — and BLOCK on any breach.

    176 GitHub stars~468 tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Fund Orchestration

What does Fund Orchestration do?

Sequence the fund pipeline and delegate to the four subagents (economist, allocator, risk, executor). Fund Orchestration is an agent skill from SilvioBaratto/optimizer. Sequence the fund pipeline and delegate to the four subagents (economist, allocator, risk, executor).

When should I use Fund Orchestration?

Fund Orchestration fits situations like: the PM/orchestrator must plan a run; hand a step to a subagent via the task tool; collect its structured report; decide whether to proceed.

How do I install Fund Orchestration in Claude Code?

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

How do I install Fund Orchestration in Codex?

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

Can I use Fund 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 SilvioBaratto/optimizer --skill fund-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/fund-orchestration, .gemini/skills/fund-orchestration, .github/skills/fund-orchestration and .opencode/skills/fund-orchestration in your project.

What does Fund Orchestration need to run?

SKILL.md names no scripts, command-line tools or credentials: Fund Orchestration is instructions for the agent only.

Does Fund 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 Fund 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 Fund Orchestration use?

Fund Orchestration has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Fund Orchestration use?

About 635 tokens (SKILL.md is roughly 2.5k 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 Fund Orchestration?

Skills that share tags, products or a category with Fund Orchestration: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (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 Fund Orchestration?

SilvioBaratto (a GitHub user) maintains it in SilvioBaratto/optimizer, which has 176 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.

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