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

Multi Agent Skill Trainer

by nwjs in nwjs/chromium.src

Updates checklists and personas for multi-agent skills. An agent skill from nwjs/chromium.src.

BSD-3-ClauseAuto-check passedAgent Workflows

Install Multi Agent Skill Trainer

skills CLI
$ npx skills add nwjs/chromium.src --skill multi-agent-skill-trainer -a claude-code

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

GitHub CLI
$ gh skill install nwjs/chromium.src multi-agent-skill-trainer --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/nwjs/chromium.src.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agents/skills/multi-agent-skill-trainer .claude/skills/multi-agent-skill-trainer && 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
multi-agent-skill-trainer
GitHub stars
160
Token cost
~1.6k tokens
SKILL.md length
692 words
Files
12 (incl. references)
Skills in repo
64
Repo updated
First seen
Licence
BSD-3-Clause

At a glance

Updates checklists and personas for multi-agent skills. An agent skill from nwjs/chromium.src.

  • Works in 5 steps: Grounding & Verification → History Mining & Extraction (Deep Path… → Parallel Component Research (Breadth… → …
  • Tasks that involve Multi-agent orchestration
  • SKILL.md covers The Three-Path Model, Stages Overview, Stage 0: Grounding &… and Stage 1: History Mining &…, plus 4 more sections
  • Runs Python scripts from its folder; calls git; reaches chromium-review.googlesource.com

What it does

Multi Agent Skill Trainer is an agent skill from nwjs/chromium.src. Updates checklists and personas for multi-agent skills.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including reference files (for example `ROUTING.md`, `personas/core/analyzer.json` and `personas/core/architect.json`).

It sits in Agent Workflows, covering Multi-agent orchestration. The repository describes itself as: Chromium codebase with NW.js modifications. Based on https://chromium.googlesource.com/chromium/src.git. The licence is BSD-3-Clause.

When your agent uses it

  • Tasks that involve Multi-agent orchestration

Example prompts

  • “Use the multi-agent-skill-trainer skill to update checklists and personas for multi-agent skills. An agent skill from nwjs/chromium.src”
  • “/multi-agent-skill-trainer”

Requirements

  • Python 3

Workflow steps

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

  1. Grounding & Verification
  2. History Mining & Extraction (Deep Path Only)
  3. Parallel Component Research (Breadth Path Only)
  4. Gap Analysis & Collation
  5. Ruleset Upgrade & Validation

What it can do on your machine

Read from SKILL.md and the folder at commit a9e8946. 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 script files (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • git

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • chromium-review.googlesource.com

    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

Multi Agent Skill Trainer loads about 1.6k tokens when it runs, and up to ~1.9k if it reads all its reference files. Until then it costs about 20 tokens; SKILL.md has 692 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~20
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.9k

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 nwjs/chromium.src at commit a9e8946, republished under its BSD-3-Clause licence (© nwjs). 692 words, ~1,621 tokens.

Download SKILL.mdSave it as .claude/skills/multi-agent-skill-trainer/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
multi-agent-skill-trainer
description
Updates checklists and personas for multi-agent skills.

Multi-Agent Skill Trainer Protocol

This skill is responsible for capturing knowledge gaps and updating the personas and checklists of other multi-agent skills (e.g., code review, TDD implementation) based on execution feedback, constraints, or historical code reviews.

The Three-Path Model

The Trainer MUST select an execution path based on the inputs provided in project.workflow.json:

  1. BASIC_PATH (Iterative Refinement): Used when a specific execution feedback file (feedback_file) is provided. Workflow: Stage 0 (Grounding) -> Stage 3 (Gap Analysis) -> Stage 4 (Upgrade).
  2. DEEP_PATH (Historical Learning): Used when targeting files (target_files_to_analyze) or a specific CL (cl_to_analyze) to extract historical human feedback. Workflow: Stage 0 (Grounding) -> Stage 1 (Mining) -> Stage 3 (Gap Analysis) -> Stage 4 (Upgrade).
  3. BREADTH_PATH (Component Bootstrapping): Used when targeting a whole component (target_component) to establish general rules. Workflow: Stage 0 (Grounding) -> Stage 2 (Parallel Research) -> Stage 3 (Gap Analysis) -> Stage 4 (Upgrade).

Stages Overview

  • Stage 0: Grounding & Verification
  • Stage 1: History Mining & Extraction (Deep Path Only)
  • Stage 2: Parallel Component Research (Breadth Path Only)
  • Stage 3: Gap Analysis & Collation
  • Stage 4: Ruleset Upgrade & Validation

Stage 0: Grounding & Verification

  1. Read Inputs: Read project.workflow.json (or standalone configuration) to discover target skill, temp_directory, and path-specific inputs.
  2. Verify Target: Confirm the target skill directory exists, contains a personas/ directory, and that each persona JSON file conforms to schema.json#/definitions/PersonaDef.
  3. Determine Path & Transition:
    • If feedback_file is provided, select BASIC_PATH and transition to Stage 3.
    • Else if target_files_to_analyze or cl_to_analyze is provided, select DEEP_PATH and transition to Stage 1.
    • Else if target_component is provided, select BREADTH_PATH and transition to Stage 2.

Stage 1: History Mining & Extraction (Deep Path Only)

  1. Mine CLs (if target_files_to_analyze provided):
    • For each file in the list, run git log --follow --format=%B <file> to fetch commit history.
    • Parse commit messages to extract Gerrit review links (e.g., Reviewed-on: https://chromium-review.googlesource.com/c/chromium/src/+/(\d+)).
    • Collect unique CL numbers.
  2. Fetch Comments:
    • For each mined CL number (or the specific cl_to_analyze if provided), run git cl comments <cl_number>.
    • Save the raw comments output to a temporary JSON file (e.g., gerrit_comments.workflow.json in the temp_directory).
  3. Transition: Set the feedback source to the temporary comments file and transition to Stage 3.
Show full SKILL.md (341 more words)Show less

Stage 2: Parallel Component Research (Breadth Path Only)

  1. Determine Strategies: Read project.workflow.json#breadth_strategies. If empty, auto-detect:
    • If README.md or g3doc/ exists in target_component -> enable STATIC_ARCH.
    • If git history exists for target_component -> enable CL_SAMPLING.
    • If public headers exist in target_component -> enable CONSUMER_USAGE.
  2. Execute Research in Parallel: Invoke the following subagents concurrently based on enabled strategies:
    • STATIC_ARCH: Invoke the Architect subagent (personas/core/architect.json) to scan docs, parse BUILD.gn, and write temp_arch_rules.json to the temp_directory.
    • CL_SAMPLING: Invoke the History Miner subagent (personas/core/history_miner.json) to sample the last 50 CLs for the component, fetch comments, and write temp_sampled_rules.json to the temp_directory.
    • CONSUMER_USAGE: Invoke the Usage Analyzer subagent (personas/core/usage_analyzer.json) to scan for external usage of the component's APIs and write temp_usage_rules.json to the temp_directory.
  3. Collate Research (Reduce Phase):
    • Once all parallel subagents complete, invoke the Consolidator subagent (personas/core/consolidator.json).
    • The Consolidator must read all temp_*.json files, perform semantic de-duplication, and merge them into a single breadth_gap_report.json in the temp_directory.
  4. Transition: Set the feedback source to breadth_gap_report.json and transition to Stage 3.

Stage 3: Gap Analysis & Collation

  1. Invoke Analyzer: Invoke the Analyzer subagent (conforming to personas/core/analyzer.json).
  2. Analysis Task: The Analyzer must:
    • Read the feedback source (either feedback_file, gerrit_comments.workflow.json, or breadth_gap_report.json).
    • Filter out noise if reading raw Gerrit comments.
    • Identify the responsible persona in the target skill.
    • Formulate new, generalized boolean checklist items.
    • Output the target persona name and the proposed checklist updates.
  3. Transition: Move to Stage 4.

Stage 4: Ruleset Upgrade & Validation

  1. Invoke Upgrader: Invoke the Upgrader subagent (conforming to personas/core/upgrader.json).
  2. Upgrade Task: The Upgrader must:
    • Read the target persona JSON file from the target skill's directory.
    • Append the new checklist items to its checklist.
    • Validate that the updated persona file conforms to the PersonaDef schema.
    • Consult segmentation.md to check if the ruleset checklist exceeds 10 items. If it does, split the ruleset and update the target skill's ROUTING.md.
  3. Complete: Confirm that the files are saved and exit.

Evaluation & Testing

When modifying this skill's workflow, routing, or schemas, ensure that the corresponding Promptfoo evaluation test suite is updated and passing:

© nwjs, BSD-3-Clause. 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 11 other files (references) in agents/skills/multi-agent-skill-trainer of nwjs/chromium.src.

  • SKILL.md
  • OWNERS
  • ROUTING.md
  • personas/core/analyzer.json
  • personas/core/architect.json
  • personas/core/consolidator.json
  • personas/core/history_miner.json
  • personas/core/upgrader.json
  • personas/core/usage_analyzer.json
  • references/segmentation.md
  • run_presubmit.py
  • schema.json

Open the folder on GitHubat commit a9e8946

Compare with similar skills

Multi Agent Skill Trainer 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.

Multi Agent Skill Trainer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Multi Agent Skill Trainer this skillnwjs/chromium.src160—~1.6kAutomated safety check: PassBSD-3-Clause
Orca CLIstablyai/orca88k2 repos~593Automated safety check: PassMIT
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
O2 Review Loopopenobserve/openobserve22k—~3.7kAutomated safety check: PassAGPL-3.0
Paseo Committeegetpaseo/paseo20k1 repos~496Automated safety check: PassCustom licence
Mission Control Agent APIbuilderz-labs/mission-control6.3k—~2.1kAutomated safety check: PassMIT

Similar skills

  • Orca CLI

    stablyai/orca

    Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…

    88k GitHub starsUsed in 2 repos~593 tokens
    Agent WorkflowsAuto-check passed

  • 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.

    20k GitHub starsUsed in 1 repo~756 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

  • 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.

    20k GitHub starsUsed in 1 repo~496 tokens
    Agent WorkflowsAuto-check passed

  • 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.

    6.3k GitHub stars~2.1k tokensUpdated 11 days ago
    Agent WorkflowsAuto-check passed

  • 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.

    20k GitHub starsUsed in 1 repo~606 tokens
    Agent WorkflowsAuto-check passed

More from nwjs/chromium.src

All 64 skills in this repo

  • Analyzing SQL Traces

    nwjs/chromium.src

    Extracts raw trace data from Perfetto traces, runs arbitrary SQL queries for custom follow-up analysis, and applies expert cognitive principles (Tiered Flow Analysis, Semantic Mismatch, Redundancy)…

    160 GitHub stars~2.9k tokensUpdated 5 days ago
    Auto-check passed

  • Chrome Performance Optimizer

    nwjs/chromium.src

    Autonomous multi-agent performance optimization loop for Chromium and V8.

    160 GitHub stars~4.2k tokensUpdated 5 days ago
    Auto-check passed

  • Automated Tracing

    nwjs/chromium.src

    Automated Tracing & Performance Telemetry in Chromium using Perfetto and Telemetry benchmarks.

    160 GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check passed

  • Chrome Releases

    nwjs/chromium.src

    Queries Chrome commit, version, release, and milestone metadata.

    160 GitHub stars~1.3k tokensUpdated 5 days ago
    Auto-check passed

  • Chromium Docs

    nwjs/chromium.src

    Search and reference Chromium documentation from the local docs index, including design docs, APIs, and development guides.

    160 GitHub stars~1.2k tokensUpdated 5 days ago
    Auto-check passed

  • Gn Deps Debugging

    nwjs/chromium.src

    Diagnose Chromium GN dependency and include-visibility failures, including BUILD.gn deps/publicdeps, DEPS include rules, private headers, and circular dependencies.

    160 GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check passed

Categories

Questions about Multi Agent Skill Trainer

What does Multi Agent Skill Trainer do?

Updates checklists and personas for multi-agent skills. An agent skill from nwjs/chromium.src. src. Updates checklists and personas for multi-agent skills.

When should I use Multi Agent Skill Trainer?

Multi Agent Skill Trainer fits situations like: tasks that involve Multi-agent orchestration.

How do I install Multi Agent Skill Trainer in Claude Code?

Run `npx skills add nwjs/chromium.src --skill multi-agent-skill-trainer -a claude-code`. Or copy the skill folder (agents/skills/multi-agent-skill-trainer in nwjs/chromium.src) into .claude/skills/multi-agent-skill-trainer in your project. Claude Code loads it when a task matches its description.

How do I install Multi Agent Skill Trainer in Codex?

Run `npx skills add nwjs/chromium.src --skill multi-agent-skill-trainer -a codex`. Or copy the skill folder (agents/skills/multi-agent-skill-trainer in nwjs/chromium.src) into .agents/skills/multi-agent-skill-trainer in your project. Codex loads it when a task matches its description.

Can I use Multi Agent Skill Trainer 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 nwjs/chromium.src --skill multi-agent-skill-trainer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/multi-agent-skill-trainer, .gemini/skills/multi-agent-skill-trainer, .github/skills/multi-agent-skill-trainer and .opencode/skills/multi-agent-skill-trainer in your project.

What does Multi Agent Skill Trainer need to run?

Going by SKILL.md and its folder, Multi Agent Skill Trainer needs Python for the scripts in its folder and the command-line tools its instructions call (git). Our summary lists: Python 3.

Does Multi Agent Skill Trainer access the network?

SKILL.md names 1 domain. In commands or code: chromium-review.googlesource.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Multi Agent Skill Trainer 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 Multi Agent Skill Trainer use?

Multi Agent Skill Trainer is published under the BSD-3-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Multi Agent Skill Trainer 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. Its references folder adds about 239 tokens, read only when the agent opens those files.

What are the alternatives to Multi Agent Skill Trainer?

Skills that share tags, products or a category with Multi Agent Skill Trainer: 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 Multi Agent Skill Trainer?

nwjs (a GitHub organization) maintains it in nwjs/chromium.src, which has 160 GitHub stars. The repository holds 64 skills in this directory. The repository was last updated on October 3, 2026.

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