Skip to content
Agentmart
Submit a tool

zf-channel-research-synthesizer

Use when synthesizing a ZaoFu research-review Channel.

Skill by uisee-ai

IndexedApache-2.0★ 34
Write a review

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-channel-research-synthesizer

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

Use when synthesizing a ZaoFu research-review Channel. Produces an evidence-bound research synthesis and optional workflow recommendation without starting a workflow or creating a refactor task map.

Use cases: research, productivity

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-channel-research-synthesizer

What's inside

Skill name
zf-channel-research-synthesizer
Description
Use when synthesizing a ZaoFu research-review Channel. Produces an evidence-bound research synthesis and optional workflow recommendation without starting a workflow or creating a refactor task map.
License
Apache-2.0
Instructions
41 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Channel Research Review Synthesizer

## Purpose

Converge participant findings into one research decision draft while preserving
contradictions, uncertainty, source provenance, and owner decision items.

## Synthesis Rules

1. Deduplicate equivalent findings without dropping distinct evidence.
2. Separate confirmed facts, inferences, assumptions, and unresolved questions.
3. Preserve material dissent; do not average conflicting sources into false
   consensus.
4. For every scope or recommendation narrowing, show the original intent,
   proposed interpretation, reason, and owner decision needed. Use the common
   synthesizer's atomic question and frontier protocol.
5. Recommend ResearchFlow only when the current evidence is insufficient for a
   consequential decision.

## Output

End with one `channel_synthesis` JSON object using the runtime-provided
contract. Populate:

- `title`, `decision`, and `summary`;
- `decisions`, `assumptions`, `open_questions`, and `risks`;
- `source_refs` containing the evidence actually used;
- `recommended_workflow` only as a recommendation;
- `confidence` tied to evidence quality.

Use `acceptance_criteria` only for observable evidence needed to accept the
research conclusion. Do not turn it into an implementation backlog.

## Boundary

- Do not create a Task, invoke a Workflow, or emit workflow lifecycle events.
- Do not generate `task_map.json`, `refactor-plan.md`, or implementation slices.
- Runtime owns `channel.synthesis.proposed`, artifact persistence, consensus,
  and any later controlled workflow proposal.

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

More from uisee-ai

Cite this page

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