zf-channel-discussion-synthesizer
Use for the designated synthesizer in a ZaoFu fanout-then-synthesis Channel.
Skill by uisee-ai
Chalk Labs
Need help deploying zf-channel-discussion-synthesizer?
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.
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-discussion-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.
About
Reviews
Write a reviewNo 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-discussion-synthesizer
What's inside
- Skill name
zf-channel-discussion-synthesizer- Description
- Use for the designated synthesizer in a ZaoFu fanout-then-synthesis Channel. Defines typed question-graph normalization, targeted cross-review, owner frontier, evidence-bound synthesis, dissent preservation, and all-role sign-off.
- License
- Apache-2.0
- Instructions
- 164 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Channel 需求澄清讨论 — Synthesizer 协议
你除了按 participant 协议独立发言,还负责问题图规范化、定向交叉质询、owner
questionnaire 和最终综合。你做语义判断;runtime 只验证图、身份、digest 和路由。
## Phase 2 开场:台账去重
盲答后的问题可能重叠。收到去重请求后,读取 context pack 中完整问题台账,
保留每组里更锋利、边界更清楚的问题,并在回复末尾返回
`channel_question_dedup` JSON:
```json
{
"channel_question_dedup": {
"ledger_digest": "<context 中的精确 digest>",
"groups": [
{
"canonical_question_id": "q-keep",
"merge_question_ids": ["q-duplicate"],
"reason": "asks for the same owner decision"
}
],
"question_updates": [
{
"question_id": "q-canonical",
"kind": "fact",
"depends_on": [],
"priority": "p0",
"why_it_matters": "决定后续设计是否成立",
"recommended_answer": "先核实仓库事实",
"target_member_id": "arch"
}
],
"cross_review_requests": [
{
"question_id": "q-canonical",
"target_member_ids": ["arch", "critic"],
"prompt": "分别核实证据并指出最强反例",
"reason": "两份 contribution 对同一事实冲突",
"source_refs": ["event:..."]
}
]
}
}
```
Runtime 校验 digest、thread、question identity、环和 stale input 后原子应用
merge,并只向指定成员派发 cross review。相同事实冲突才发定向质询;不要把整个
讨论重新 `@all`。对每个 owner-facing 问题给 priority、why、推荐答案,确保
question frontier 是可逐项回答的,而不是一份混杂问卷。
每个保留的 `fact` 必须定向给真实 channel member,并至少有一个
`cross_review_requests` 取得 evidence。`owner` / `operator` 只承接 owner decision;
如果问题要求尚未生成的 canonical PRD/artifact/version/digest,应将其判定为过早的
未来输出依赖,以当前 requirement/context digest 完成核验,不得让它循环阻塞首次
synthesis。若请求携带上一次 rejection reason,必须基于最新 ledger 修正该错误,
不得原样重放。
## 收到 synthesis 请求时(channel.synthesis.requested 指向你)
问题依赖已满足、定向质询完成且 owner frontier 已清零后,产出综合 artifact:
1. 在结构化回复中提供完整 PRD 字段。Runtime 会原子写入
`<project.state_dir>/channel-artifacts/<channel>/<synthesis-request>.md` 并绑定 sha256:
```markdown
# 澄清需求:<标题>
## Decisions(逐条:问题 → owner 的回答)
## Assumptions(显式假设 + 风险)
## Out of Scope(明确不做)
## Acceptance Criteria(EARS 句式:When <触发>, the <系统> shall <行为>)
```
保留有来源的原文规则;**新增 Owner 裁定必须对应一个 resolved question**,
不把原文事实冒充新裁定,也不发明 Owner 没说过的决定。
2. 在 channel 回复末尾输出 `channel_synthesis` JSON,包含 `title`、
`decision`、`summary`、`decisions`、`assumptions`、`out_of_scope`、
`acceptance_criteria`、`open_questions`、`risks`、
`recommended_workflow`、`source_refs`、`dissent` 和 `confidence`。Runtime 负责
`channel.synthesis.proposed`、artifact 写入和唯一 consensus proposal;
不要自行写 canonical event 或 state。
`verification_commands` 必须覆盖每条 mandatory acceptance 的真实证据方法,
每条 acceptance 使用稳定 `id`;每条 command 使用稳定 `id`、与 acceptance
对齐的 canonical `acceptance_ids` 和 `producer_paths`,不要把
`acceptance_ids` 改名为 `covers`;同时显式声明 `owner`、`tier`、
`deterministic`、`reusable` 和 `timeout_seconds`,不依赖下游默认值。
`summary` 只描述长期有效的产品行为,签收、
Owner 确认和执行授权等瞬时状态只写入 `readiness`,避免 immutable PRD 在签收后
生成自相矛盾的 Task behavior。
这些 command 不能只给 build/unit 命令却把 viewport、pointer、network、storage、refresh、
screenshot 等浏览器行为留给下游猜测。浏览器场景加载
`zf-browser-e2e-contract`,写入可从 repo root 原样执行的 Docker Playwright
命令;对应 runner/config/test/evidence 路径须在后续 Task handoff 的 scope 中
可写。实施前截图/trace 尚不存在不构成 readiness blocker;缺少可执行 runner
方法才是 blocker。
3. 保留 material dissent:记录异议角色、异议内容、采用/不采用理由和能改变结论
的证据。不要用多数意见覆盖少数但高风险的反例。
4. 出现 `blocked` → 讨论自动重开,blocker 进台账 → owner 答完后重新综合。
Runtime 只把你的结构化综合绑定为你自己的 proposer 签名,并向当前 roster 其余
角色派发 artifact-bound review。所有角色签收且 Owner 确认后 kernel 才关闭讨论。
Task 创建和 Workflow 点火仍需 owner 单独发起。
## 完整 PRD 与可追溯评估
`summary` 是摘要,完整产品说明必须写入 `prd_markdown`,两者不能互相替代。
长篇既有 PRD 可以改用 `prd_composition`:绑定当前完整来源的 message id/digest,
以唯一的起止原文锚点选取完整正文,以互不重叠、唯一精确匹配的 `old`/`new` 修改
条款,在 `appendix_markdown` 补入决策、测试假设、异议处理和验收。Runtime 展开为
完整 Markdown 后沿同一合同落盘和复审,不把来源路径当作正文。两种输入只能选一种。
这次 synthesis 就须交付完整 PRD;不能只给摘要并建议后续 Workflow 再编制。
先从实际源文档生成需求清单,保留范围、主流程、异常流程、权限、数据约束、状态变化、
非功能要求和可执行验收;按项目取舍,不套用固定条数或固定产品功能表。
`requirement_coverage` 每项包含唯一 `id`、`source_refs`、正文 `section`、
`acceptance_ids` 和 `status: covered|deferred|gap`;covered 必须指向声明过的验收 ID,From uisee-ai/zaofu, Apache-2.0.
More from uisee-ai/zaofu
- 0.653score
zf-browser-e2e-contract
uisee-ai
ZaoFu browser/E2E (Docker Playwright) command-shape and clean-checkout environment checklist for writer, review, verify, and operator roles.
SkillAFreshness: A★ 34Claude Code +9 - 0.650score
zf-channel-discussion-participant
uisee-ai
Use for every active lens in a ZaoFu fanout-then-synthesis Channel.
SkillAFreshness: A★ 34Claude Code +9 - 0.615score
zf-record-browser-demo
uisee-ai
Use on demand to record a short, truthful browser workflow as deterministic frames plus an optimized GIF and provenance artifact.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-refactor-generalization-audit
uisee-ai
ZaoFu refactor portability audit for Claude or Codex.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-channel-research-synthesizer
uisee-ai
Use when synthesizing a ZaoFu research-review Channel.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-research-fanout-trigger
uisee-ai
ZaoFu project-level trigger for starting the fixed-role research fanout workflow from a channel or Kanban Agent request.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-backlog-batch-closeout
uisee-ai
ZaoFu backlog/task batch closeout workflow for Codex or Claude.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-workflow-start-planner
uisee-ai
Use when a ZaoFu operator, Kanban Agent, Channel member, or Coding Agent must classify a tracked Task, clarify missing workflow inputs, recommend one active…
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-find-simplifications
uisee-ai
Use on demand to find evidence-backed simplifications in ZaoFu itself, in applications developed with ZaoFu, or in an Autoresearch simplify audit.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-cr
uisee-ai
Read-only architecture review of the ZaoFu repository before development.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-dynamic-artifact-gate
uisee-ai
Use in ZaoFu issue, PRD, or refactor workflows when plan, verify, judge, or replan stages must generate run-specific fact artifacts and artifact/matrix gate…
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-harness-design-handoff
uisee-ai
Use when you are arch about to emit arch.proposal.done OR critic about to emit design.critique.done.
SkillBFreshness: B★ 34Claude Code +9
Signals
- Stars
- 34
- Forks
- 4
- Open issues
- 0
- Last commit (this folder)
- Oct 11, 2026 (20 days ago)
- Last release
- Aug 21, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/uisee-ai/zaofu
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from uisee-ai
- 0.653score
zf-browser-e2e-contract
uisee-ai
ZaoFu browser/E2E (Docker Playwright) command-shape and clean-checkout environment checklist for writer, review, verify, and operator roles.
SkillAFreshness: A★ 34Claude Code +9 - 0.650score
zf-channel-discussion-participant
uisee-ai
Use for every active lens in a ZaoFu fanout-then-synthesis Channel.
SkillAFreshness: A★ 34Claude Code +9 - 0.615score
zf-record-browser-demo
uisee-ai
Use on demand to record a short, truthful browser workflow as deterministic frames plus an optimized GIF and provenance artifact.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-refactor-generalization-audit
uisee-ai
ZaoFu refactor portability audit for Claude or Codex.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-find-simplifications
uisee-ai
Use on demand to find evidence-backed simplifications in ZaoFu itself, in applications developed with ZaoFu, or in an Autoresearch simplify audit.
SkillBFreshness: B★ 34Claude Code +9 - 0.613score
zf-cr
uisee-ai
Read-only architecture review of the ZaoFu repository before development.
SkillBFreshness: B★ 34Claude Code +9
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-channel-discussion-synthesizer 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.
Cite this page
zf-channel-discussion-synthesizer skill. Agent Mart. https://agentmart.dev/skills/uisee-ai-zf-channel-discussion-synthesizer (last updated 2026-10-24)