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-Role Spec and Task Breakdown

by mylukin in mylukin/agent-foreman

Runs a requirement through four research-backed specialist agents, a PM, a UX designer, a tech architect and QA, to produce implementable tasks.

No licenceAuto-check: notesAgent Workflows

Install Multi-Role Spec and Task Breakdown

skills CLI
$ npx skills add mylukin/agent-foreman --skill foreman-spec -a claude-code

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

GitHub CLI
$ gh skill install mylukin/agent-foreman foreman-spec --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/mylukin/agent-foreman.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/agent-foreman/skills/foreman-spec .claude/skills/foreman-spec && 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
foreman-spec
GitHub stars
250
Token cost
~5.1k tokens
SKILL.md length
1,662 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
None found

At a glance

Runs a requirement through four research-backed specialist agents, a PM, a UX designer, a tech architect and QA, to produce implementable tasks.

  • Works in 8 steps: Mode Selection → Codebase Scan → 5: Research Context (NEW) → …
  • Breaking a high-level feature request into implementable tasks
  • SKILL.md covers Overview, Phase 0: Mode Selection, Phase 1: Codebase Scan and Phase 1.5: Research Context…, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Each of the four agents does its own web research before analysis, so a product manager agent grounds what and why in market and industry context, a UX agent researches interaction patterns, a technical architect researches frameworks and security, and a QA agent researches testing strategies, rather than relying on built-in assumptions. Two modes trade speed for depth: a quick mode runs the four agents in parallel with one combined question session afterward, while a deep mode runs them one after another with a dedicated question session following each agent, so each answer can inform the next agent's analysis.

Before any analysis it scans the codebase to detect whether this is a new or existing project, counts the features mentioned and watches for uncertainty words to judge complexity, then recommends the deep mode for a new or complex project and asks the user to confirm or override that choice. A codebase scan phase follows, reading files like the README, package manifests and sample source files to understand existing patterns before the four agents begin their work.

When your agent uses it

  • Breaking a high-level feature request into implementable tasks
  • Getting research-backed UX, technical and QA perspectives on a requirement
  • Deciding between a quick or deep analysis mode for a new feature

Example prompts

  • “Spec out this new onboarding flow with foreman-spec.”
  • “Break down the requirement for a multi-tenant billing feature.”
  • “Run a deep-mode spec analysis on this complex integration request.”

Requirements

  • Web search access for each agent's research step
  • Pre-approved tools (allowed-tools): Read, Write, Glob, Grep, AskUserQuestion, Bash, Task

Workflow steps

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

  1. Mode Selection
  2. Codebase Scan
  3. 5: Research Context (NEW)
  4. Analysis (Mode-Dependent)
  5. 5: Question Collection & User Interaction
  6. Create Overview & Breakdown Tasks (DELEGATED)
  7. Module Breakdown (User-Driven)
  8. Validation

What it can do on your machine

Read from SKILL.md and the folder at commit 2763f83. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Glob
    • Grep
    • AskUserQuestion
    • Bash
    • Task

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown, json and bash).

    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-Role Spec and Task Breakdown loads about 5.1k tokens when it runs. Until then it costs about 122 tokens; SKILL.md has 1,662 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~122
When it runs · the whole SKILL.md, loaded when a task matches
~5.1k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Glob, Grep, AskUserQuestion, Bash, Task

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,662 words (~5,132 tokens).

“Multi-role requirement analysis using 4 specialized AI agents, each equipped with web research capabilities.”

— opening of SKILL.md by mylukin
name
foreman-spec
allowed-tools
Read, Write, Glob, Grep, AskUserQuestion, Bash, Task
user-invocable
true

Read the full SKILL.md on GitHub

Files

Just SKILL.md in plugins/agent-foreman/skills/foreman-spec of mylukin/agent-foreman.

Open the folder on GitHubat commit 2763f83

Compare with similar skills

Multi-Role Spec and Task Breakdown 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-Role Spec and Task Breakdown compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Multi-Role Spec and Task Breakdown this skillmylukin/agent-foreman250—~5.1kAutomated safety check: NotesNone
ULW Plan Workflowcode-yeongyu/oh-my-openagent70k—~3.9kAutomated safety check: PassCustom licence
Ask NavigatorYeachan-Heo/oh-my-claudecode40k—~4.1kAutomated safety check: PassMIT
Plannotator Goal Setupbacknotprop/plannotator9.2k—~2.4kAutomated safety check: PassApache-2.0
CE BrainstormEveryInc/compound-engineering-plugin25k—~1.9kAutomated safety check: PassMIT
Extracting Requirementsprime-radiant-inc/iterative-development181—~2.7kAutomated safety check: PassApache-2.0

Similar skills

  • ULW Plan Workflow

    code-yeongyu/oh-my-openagent

    Explore-first planning that turns a vague or large request into one decision-complete work plan, written only after your approval and executed by a separate worker.

    70k GitHub stars~3.9k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Ask Navigator

    Yeachan-Heo/oh-my-claudecode

    Charts a foggy effort into a map of decision tickets on the repo's issue tracker and works through them one per session, producing decisions rather than deliverables.

    40k GitHub stars~4.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Plannotator Goal Setup

    backnotprop/plannotator

    Guides the agent from a vague objective to a written goal package under goals/, using a confirmed restatement, a browser interview, a fact sheet and a codebase pass.

    9.2k GitHub stars~2.4k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • CE Brainstorm

    EveryInc/compound-engineering-plugin

    Turns a vague or ambitious feature idea into a requirements-only plan through dialogue with you, sized to the work, before any code is written.

    25k GitHub stars~1.9k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Extracting Requirements

    prime-radiant-inc/iterative-development

    Reads human-written spec documents and produces per-epic requirement files with proof obligations plus behavior scenarios with stable IDs, using parallel chunked extraction.

    181 GitHub stars~2.7k tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check passed

  • Feature Brainstorm

    VeryGoodOpenSource/vgv-wingspan

    Clarifies what to build before how, by asking one question at a time about a feature idea and then handing the result on to planning.

    109 GitHub stars~1.8k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

More from mylukin/agent-foreman

  • Feature Next Task Workflow

    mylukin/agent-foreman

    Enforces a strict next-implement-check-done cycle through the agent-foreman CLI so an agent works one backlog task at a time, with optional TDD gating.

    250 GitHub stars~927 tokensUpdated 8 mo ago
    Auto-check: notes

  • Agent-Foreman Feature Run

    mylukin/agent-foreman

    Runs the agent-foreman task loop for one task by ID or unattended across every pending task, following next, implement, check, done for each one.

    250 GitHub stars~1.6k tokensUpdated 8 mo ago
    Auto-check: notes

  • Agent Task Backlog Initializer

    mylukin/agent-foreman

    Builds a feature backlog, progress log, and optional strict test enforcement for agent-driven work with a single init command.

    250 GitHub stars~681 tokensUpdated 8 mo ago
    Auto-check: notes

  • Project Analyze

    mylukin/agent-foreman

    Scans codebases to generate architecture documentation (ARCHITECTURE.md). Use when joining an existing project, understanding codebase structure, exploring…

    250 GitHub stars~253 tokensUpdated 8 mo ago
    Auto-check: notes

Categories

Questions about Multi-Role Spec and Task Breakdown

What does Multi-Role Spec and Task Breakdown do?

Runs a requirement through four research-backed specialist agents, a PM, a UX designer, a tech architect and QA, to produce implementable tasks. Each of the four agents does its own web research before analysis, so a product manager agent grounds what and why in market and industry context, a UX agent researches interaction patterns, a technical architect researches frameworks and security, and a QA agent researches testing strategies, rather than relying on built-in assumptions. Two modes trade speed for depth: a quick mode runs the four agents in parallel with one combined question session afterward, while a deep mode runs them one after another with a dedicated question session following each agent, so each answer can inform the next agent's analysis.

When should I use Multi-Role Spec and Task Breakdown?

Multi-Role Spec and Task Breakdown fits situations like: breaking a high-level feature request into implementable tasks; getting research-backed UX, technical and QA perspectives on a requirement; deciding between a quick or deep analysis mode for a new feature.

How do I install Multi-Role Spec and Task Breakdown in Claude Code?

Run `npx skills add mylukin/agent-foreman --skill foreman-spec -a claude-code`. Or copy the skill folder (plugins/agent-foreman/skills/foreman-spec in mylukin/agent-foreman) into .claude/skills/foreman-spec in your project. Claude Code loads it when a task matches its description.

How do I install Multi-Role Spec and Task Breakdown in Codex?

Run `npx skills add mylukin/agent-foreman --skill foreman-spec -a codex`. Or copy the skill folder (plugins/agent-foreman/skills/foreman-spec in mylukin/agent-foreman) into .agents/skills/foreman-spec in your project. Codex loads it when a task matches its description.

Can I use Multi-Role Spec and Task Breakdown 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 mylukin/agent-foreman --skill foreman-spec -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/foreman-spec, .gemini/skills/foreman-spec, .github/skills/foreman-spec and .opencode/skills/foreman-spec in your project.

What does Multi-Role Spec and Task Breakdown need to run?

SKILL.md names no scripts, command-line tools or credentials: Multi-Role Spec and Task Breakdown is instructions for the agent only. Our summary lists: Web search access for each agent's research step. Its frontmatter pre-approves these tools: Read, Write, Glob, Grep, AskUserQuestion, Bash, Task.

Does Multi-Role Spec and Task Breakdown 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-Role Spec and Task Breakdown safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Multi-Role Spec and Task Breakdown use?

No licence was found for Multi-Role Spec and Task Breakdown or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Multi-Role Spec and Task Breakdown use?

About 5.1k tokens (SKILL.md is roughly 21k 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 Multi-Role Spec and Task Breakdown?

Skills that share tags, products or a category with Multi-Role Spec and Task Breakdown: ULW Plan Workflow (code-yeongyu/oh-my-openagent, 70k stars), Ask Navigator (Yeachan-Heo/oh-my-claudecode, 40k stars), Plannotator Goal Setup (backnotprop/plannotator, 9.2k stars) and CE Brainstorm (EveryInc/compound-engineering-plugin, 25k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Multi-Role Spec and Task Breakdown?

mylukin (a GitHub user) maintains it in mylukin/agent-foreman, which has 250 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on January 23, 2026.

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