Skip to content
Agentmart
Submit a tool

zf-research-fanout-trigger

ZaoFu project-level trigger for starting the fixed-role research fanout workflow from a channel or Kanban Agent request.

Skill by uisee-ai

IndexedApache-2.0★ 34
Write a review

Chalk Labs

Need help deploying zf-research-fanout-trigger?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/uisee-ai-zf-research-fanout-trigger

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

ZaoFu project-level trigger for starting the fixed-role research fanout workflow from a channel or Kanban Agent request. Use when the user explicitly invokes this skill, asks to trigger/start/run research fanout, wants a channel/Kanban Agent research request turned into a fixed multi-role fanout, or wants research results prepared for PRD/refactor prompt generation. Do not use for generic web searching or ordinary channel discussion that has not requested research fanout.

Use cases: research, productivity, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/zf-research-fanout-trigger

What's inside

Skill name
zf-research-fanout-trigger
Description
ZaoFu project-level trigger for starting the fixed-role research fanout workflow from a channel or Kanban Agent request. Use when the user explicitly invokes this skill, asks to trigger/start/run research fanout, wants a channel/Kanban Agent research request turned into a fixed multi-role fanout, or wants research results prepared for PRD/refactor prompt generation. Do not use for generic web searching or ordinary channel discussion that has not requested research fanout.
License
Apache-2.0
Instructions
199 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# ZaoFu Research Fanout Trigger

## Objective

Turn an explicit channel or Kanban Agent research request into a ZaoFu
controlled workflow trigger for the fixed-role research fanout template.

This skill is the entrypoint. The runtime fanout and subagents do the research.

## Ground Rules

- Treat this as a ZaoFu project skill, not a user-global research helper.
- Read `AGENTS.md` if you need repository rules or are about to run commands.
- Use `zf.yaml` as the only control-plane config. Do not hard-code `.zf`.
- Do not write `events.jsonl`, `kanban.json`, `session.yaml`, or other runtime
  truth files directly.
- Use `zf-workflow-start-planner` and the shared `zf workflow start` CLI.
- Do not silently run research from ordinary channel text. Require explicit
  skill invocation or an explicit user request for research fanout.
- Preparatory Research is Request-first. Create or reuse the exact Workflow
  Request revision before creating its workflow-managed Research Task.
- Treat the Workflow Request origin binding as the return authority. Channel
  ids and source refs are provenance and must not override that binding.
- If a required field, token, task, or workflow stage is missing, produce a
  preview payload and the exact blocker instead of bypassing the gate.

## Fixed Template

Use this template unless the user explicitly names another ZaoFu research
template:

```yaml
template_id: research-fanout.fixed.v1
pattern_id: research-fanout
roles:
  - source_researcher
  - product_analyst
  - technical_analyst
  - risk_critic
  - synthesizer
outputs:
  - research_summary
  - evidence_refs
  - open_questions
  - prd_prompt_input
  - refactor_prompt_input
```

Role intent:

- `source_researcher`: gather and cite primary or direct evidence.
- `product_analyst`: convert findings into user needs, scope, and PRD inputs.
- `technical_analyst`: identify architecture, implementation, and integration
  implications.
- `risk_critic`: challenge assumptions, missing evidence, rollout risk, and
  failure modes.
- `synthesizer`: produce the final research synthesis and PRD/refactor prompt
  inputs.

Runtime mapping: the first four roles run as `fanout.children`; `synthesizer`
runs as `aggregate.synth_role` after the child reports complete.

## Adaptive Pilot

Use `route_id=research:adaptive-pilot` only when the operator explicitly asks
for adaptive/provider-native Research and the active route catalog exposes it.
The route runs one ZaoFu `research_root`; that root may use bounded read-only
Provider children under `zf-research-adaptive-root`. It is an opt-in pilot, not
a declaration that Provider child telemetry or credential isolation is
production-qualified. If preflight rejects it, report the reason and offer
`research:fixed`; never silently relabel a fixed run as adaptive.

## Trigger Workflow

1. Classify and extract the request:
   - `topic`: the concrete thing to research.
   - `scope`: bounded aspects to investigate.
   - `expected_output`: default to
     `research synthesis plus PRD/refactor prompt inputs`.
   - `channel_id` and `thread_id`: identify the originating conversation when
     available.
   - classify it as preparatory when the result will update a later
     PRD/refactor/delivery request; otherwise it is standalone knowledge
     delivery.

2. For preparatory Research, create or reuse the Workflow Request through the
   controlled `workflow-request` action. Record its exact `request_id`,
   `request_revision`, and `origin_binding`. Do not start Research while the
   Request is missing or stale.

3. Create the Research Task through controlled `create-task` with:

```json
{
  "title": "<bounded research topic>",
  "execution_mode": "workflow",
  "request_id": "REQ-ID",
  "request_revision": 1
}
```

   A current workflow-managed Task may be reused only when its Request binding
   matches exactly. A standalone Research Task does not carry a Request and its
   result cannot be adopted into a later requirement.

4. Read and validate the active route:

   ```bash
   zf workflow routes --task TASK-ID --format json
   ```

   Select `route_id=research:fixed` for the stable audit path. Select
   `route_id=research:adaptive-pilot` only for an explicit adaptive pilot.
   The catalog owns the internal pattern, topology, roles, and rollout label.

5. Build the controlled action payload:

```json
{

From uisee-ai/zaofu, Apache-2.0.

More from uisee-ai/zaofu

Signals

Stars
34
Forks
4
Open issues
0
Last commit (this folder)
Jul 30, 2026 (3 months ago)
Last release
Aug 21, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from uisee-ai

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get zf-research-fanout-trigger running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying zf-research-fanout-trigger?

CallGet help
Cite this page

zf-research-fanout-trigger skill. Agent Mart. https://agentmart.dev/skills/uisee-ai-zf-research-fanout-trigger (last updated 2026-10-24)