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 TDD Implementation

by nwjs in nwjs/chromium.src

Multi-agent Test-Driven Development workflow. An agent skill from nwjs/chromium.src.

BSD-3-ClauseAuto-check passedTesting & QA

Install Multi Agent TDD Implementation

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

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

GitHub CLI
$ gh skill install nwjs/chromium.src multi-agent-tdd-implementation --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-tdd-implementation .claude/skills/multi-agent-tdd-implementation && 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-tdd-implementation
GitHub stars
160
Token cost
~1.4k tokens
SKILL.md length
613 words
Files
10 (incl. references)
Skills in repo
64
Repo updated
First seen
Licence
BSD-3-Clause

At a glance

Multi-agent Test-Driven Development workflow. An agent skill from nwjs/chromium.src.

  • Works in 5 steps: Environment Grounding & Safety… → API Scaffolding (Scaffold) → Test Bounds Definition (TDD Boundary) → …
  • Tasks that involve Test-driven development
  • SKILL.md covers Stages Overview, Stage 0: Environment Grounding…, Stage 1: API Scaffolding… and Stage 2: Test Bounds…, plus 5 more sections
  • Runs Python scripts from its folder

What it does

Multi Agent TDD Implementation is an agent skill from nwjs/chromium.src. Multi-agent Test-Driven Development workflow. Scaffolds APIs, writes failing tests, synthesizes implementation, and verifies compilation and test runs.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including reference files (for example `ROUTING.md`, `personas/core/gtest.json` and `personas/core/implementation.json`).

It sits in Testing & QA, covering Test-driven development, Project scaffolding and 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 Test-driven development
  • Tasks that involve Project scaffolding
  • Tasks that involve Multi-agent orchestration

Example prompts

  • “/multi-agent-tdd-implementation”

Requirements

  • Python 3

Workflow steps

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

  1. Environment Grounding & Safety Verification
  2. API Scaffolding (Scaffold)
  3. Test Bounds Definition (TDD Boundary)
  4. Parallel Implementation & Synthesis (Synthesis)
  5. Verification Build & Test (Verify)

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.

    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

Multi Agent TDD Implementation loads about 1.4k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 46 tokens; SKILL.md has 613 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~46
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.3k

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). 613 words, ~1,387 tokens.

Download SKILL.mdSave it as .claude/skills/multi-agent-tdd-implementation/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
multi-agent-tdd-implementation
description
Multi-agent Test-Driven Development workflow. Scaffolds APIs, writes failing tests, synthesizes implementation, and verifies compilation and test runs.

Multi-Agent TDD Implementation Protocol

This skill enforces Test-Driven Development (TDD) using specialized agents to scaffold APIs, write tests, implement code, and merge changes.

Stages Overview

  • Stage 0: Environment Grounding & Safety Verification
  • Stage 1: API Scaffolding (Scaffold)
  • Stage 2: Test Bounds definition (TDD Boundary)
  • Stage 3: Parallel Implementation & Synthesis (Synthesis)
  • Stage 4: Verification Build & Test (Verify)

Stage 0: Environment Grounding & Safety Verification

  1. Discover Environment: Read project.workflow.json to ground the VCS (GIT or JJ), repo type (CHROMIUM or GOOGLE_INTERNAL), and output directories.
  2. Initialize State: Create or read tdd_state.workflow.json. If creating, initialize state block fields (loop_counters set to {}, iteration set to 1, stage_attempts set to {}, next_stage set to "SCAFFOLDING", and verification_status set to "PENDING"). If reading, preserve or increment the existing counters.
  3. Transition: Move to Stage 1.

Stage 1: API Scaffolding (Scaffold)

  1. API Design: Invoke the Scoper sub-agent to read the goal from project.workflow.json.
  2. Create Scaffold: The Scoper must create or modify files to define class interfaces, method signatures, GN build rules, and Mojo pipes. Leaving implementations stubbed (e.g. NOTIMPLEMENTED()).
  3. Verification: The Scoper must verify that the scaffolded code compiles cleanly (even if stubs do nothing) before returning.
  4. Transition: Move to Stage 2.

Stage 2: Test Bounds Definition (TDD Boundary)

  1. Stub Tests: Invoke the Test Expert subagent. The Test Expert must create or update test files (*_unittest.cc), define fixtures, and write stubbed test cases covering the goal.
  2. Confirm Failure (TDD Mandate): To confirm TDD behavior, stubbed tests MUST fail by default. The Test Expert must insert ADD_FAILURE() << "NOT IMPLEMENTED"; into each test stub.
  3. Run Verification: Compile and run the tests. Verify that:
    • The scaffold compiles.
    • All newly added tests fail with the "NOT IMPLEMENTED" message.
  4. Snapshot: Save the current state (e.g., local commit or bookmark) as "Base Scaffold" so parallel writers share the same API boundary.
  5. Transition: Move to Stage 3.
Show full SKILL.md (303 more words)Show less

Stage 3: Parallel Implementation & Synthesis (Synthesis)

  1. Parallel Implement: Invoke Implementation subagents in parallel to implement the stubs from the Base Scaffold.
  2. Incorporate Constraints: If constraints.workflow.json is present (from a previous review cycle, conforming to schema.json#/definitions/Constraints), the implementation subagents must resolve the list of issues specified in the constraints array field of that object.
  3. 3-Way Merge: Invoke the Synthesis agent to merge the parallel drafts following synthesis_merge.md. Synthesis must use a surgical 3-way merge (Base Scaffold + Draft A + Draft B) to resolve conflicts.
  4. Compile Gate: Compile the merged draft. If compilation fails, loop back to the Implementation subagents to resolve syntax/link errors. Do not proceed to Stage 4 until the build is green.
  5. Transition: Move to Stage 4.

Stage 4: Verification Build & Test (Verify)

  1. Invoke Test Expert: Invoke the Test Expert subagent.
  2. Verification Task: The Test Expert must:
    • Replace test stubs with actual test assertions and logic.
    • Build and run the test suite.
    • Report the verification status (PASSED or FAILED) and build/test logs.
  3. Loop Check: The TDD skill orchestrator reads the verification status:
    • If tests pass, set verification_status: PASSED and next_stage: COMPLETED in tdd_state.workflow.json.
    • If tests fail due to implementation bugs, increment loop counters and loop back to Stage 3 for refinement.
    • If loop count exceeds the limit (default 3), abort and set next_stage: FAILED.

Stage Handoff & Loop Limits

  • Maximum Synthesis Loops: Limit the merge/compile cycle to 3 attempts.
  • Maximum Test Failure Loops: Limit the test-refinement loop to 3 attempts. If tests cannot pass after 3 loops, escalate to the user.

Reference Guides

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 9 other files (references) in agents/skills/multi-agent-tdd-implementation of nwjs/chromium.src.

  • SKILL.md
  • OWNERS
  • ROUTING.md
  • personas/core/gtest.json
  • personas/core/implementation.json
  • personas/core/scoper.json
  • references/synthesis_merge.md
  • references/tooling_guidance.md
  • run_presubmit.py
  • schema.json

Open the folder on GitHubat commit a9e8946

Compare with similar skills

Multi Agent TDD Implementation 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 TDD Implementation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Multi Agent TDD Implementation this skillnwjs/chromium.src160—~1.4kAutomated safety check: PassBSD-3-Clause
Bmad Testarch Atddbmad-code-org/bmad-method-test-architecture-enterprise1043 repos~1.2kAutomated safety check: PassCustom licence
Superpowers Test Driven Developmentchristopherarter/superpowers-reasonix102—~1.9kAutomated safety check: PassMIT
Openspec Plus TDDelastic/terraform-provider-elasticstack2101 repos~4.7kAutomated safety check: PassApache-2.0
Fix BugMelbourneDeveloper/dart_node1131 repos~709Automated safety check: NotesNone
Evanflow Debugevanklem/evanflow418—~760Automated safety check: PassCustom licence

Similar skills

  • Bmad Testarch Atdd

    bmad-code-org/bmad-method-test-architecture-enterprise

    Generate red-phase acceptance test scaffolds using the TDD cycle.

    104 GitHub starsUsed in 3 repos~1.2k tokens
    Testing & QAAuto-check passed

  • Superpowers Test Driven Development

    christopherarter/superpowers-reasonix

    Writing or fixing any code?. An agent skill from christopherarter/superpowers-reasonix.

    102 GitHub stars~1.9k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed

  • Openspec Plus TDD

    elastic/terraform-provider-elasticstack

    Official

    MANDATORY skill that activates whenever code is written to implement an OpenSpec change task.

    210 GitHub starsUsed in 1 repo~4.7k tokens
    Testing & QAAuto-check passed

  • Fix Bug

    MelbourneDeveloper/dart_node

    Fix a bug using test-driven development. An agent skill from MelbourneDeveloper/dart_node.

    113 GitHub starsUsed in 1 repo~709 tokens
    Testing & QAAuto-check: notes

  • Evanflow Debug

    evanklem/evanflow

    Root-cause discipline for bugs, test failures, and unexpected behavior.

    418 GitHub stars~760 tokensUpdated 4 mo ago
    Testing & QAAuto-check passed

  • TDD

    codeaholicguy/ai-devkit

    AI DevKit · Test-driven development — write a failing test before writing production code.

    1.6k GitHub stars~838 tokensUpdated today
    Testing & QAAuto-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 4 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 4 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 4 days ago
    Auto-check passed

  • Chrome Releases

    nwjs/chromium.src

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

    160 GitHub stars~1.3k tokensUpdated 4 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 4 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 4 days ago
    Auto-check passed

Categories

Questions about Multi Agent TDD Implementation

What does Multi Agent TDD Implementation do?

Multi-agent Test-Driven Development workflow. An agent skill from nwjs/chromium.src. src. Multi-agent Test-Driven Development workflow.

When should I use Multi Agent TDD Implementation?

Multi Agent TDD Implementation fits situations like: tasks that involve Test-driven development; tasks that involve Project scaffolding; tasks that involve Multi-agent orchestration.

How do I install Multi Agent TDD Implementation in Claude Code?

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

How do I install Multi Agent TDD Implementation in Codex?

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

Can I use Multi Agent TDD Implementation 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-tdd-implementation -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-tdd-implementation, .gemini/skills/multi-agent-tdd-implementation, .github/skills/multi-agent-tdd-implementation and .opencode/skills/multi-agent-tdd-implementation in your project.

What does Multi Agent TDD Implementation need to run?

Going by SKILL.md and its folder, Multi Agent TDD Implementation needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Multi Agent TDD Implementation 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 Multi Agent TDD Implementation 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 TDD Implementation use?

Multi Agent TDD Implementation 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 TDD Implementation use?

About 1.4k tokens (SKILL.md is roughly 5.5k 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 864 tokens, read only when the agent opens those files.

What are the alternatives to Multi Agent TDD Implementation?

Skills that share tags, products or a category with Multi Agent TDD Implementation: Bmad Testarch Atdd (bmad-code-org/bmad-method-test-architecture-enterprise, 104 stars), Superpowers Test Driven Development (christopherarter/superpowers-reasonix, 102 stars), Openspec Plus TDD (elastic/terraform-provider-elasticstack, 210 stars) and Fix Bug (MelbourneDeveloper/dart_node, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Multi Agent TDD Implementation?

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.