zf-harness-design-handoff
Use when you are arch about to emit arch.proposal.done OR critic about to emit design.critique.done.
Skill by uisee-ai
Chalk Labs
Need help deploying zf-harness-design-handoff?
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-harness-design-handoff
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
Use cases: design
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-harness-design-handoff
What's inside
- Skill name
zf-harness-design-handoff- Description
- Use when you are arch about to emit arch.proposal.done OR critic about to emit design.critique.done. Defines the shared schema both sides agree on so orchestrator can synthesize the backlog (6 refs) at stage ④ without ambiguity.
- License
- Apache-2.0
- Instructions
- 221 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# ZaoFu Design Handoff (arch ↔ critic ↔ orchestrator)
## Why this skill exists
Stage ② design (arch) and stage ③ design_critique (critic) feed stage ④
backlog (orchestrator). Arch may create rich **candidate** plan/backlog
artifacts, but only orchestrator accepts/merges them into final task
contracts. If arch and critic don't agree on the event payload shape,
orchestrator can't deterministically synthesize the 6
`required_backlog_refs` (`docs/impl/22-zaofu-canonical-dag.md` §4.2.1)
and `task.contract.invalid` blocks dev dispatch.
This skill is the contract between three roles.
## Ref channels (do not mix)
ZaoFu accepts planning output from any content skill pack, but lifecycle event
payloads use a stable adapter contract:
- `artifact.manifest.published.artifact_refs` is the **structured manifest**
channel: object refs with `kind/path/sha256/summary/status`.
- `arch.proposal.done` / `design.critique.done` / terminal gate events use
`artifact_refs` as a **string path list** only. If you need structured
metadata, publish a manifest first and reference its event id.
- `artifact_manifest_event_id` links the lifecycle event back to the structured
manifest. This keeps ZaoFu independent from whether the content came from
`agent-skills`, yoke, a project-local skill pack, or a different provider.
## Schema arch MUST emit (arch.proposal.done)
```json
{
"summary": "<one-sentence behavior statement; goes into contract.behavior verbatim>",
"file_plan": [
"packages/foo/src/bar.ts",
"test/unit/foo/bar.test.ts",
"packages/foo/package.json"
],
"test_plan": {
"framework": "vitest" or "pytest" or "...",
"location": "test/unit/foo/bar.test.ts",
"cases": [
"happy_path",
"boundary_zero",
"boundary_max",
"invalid_input_throws"
],
"min_required": 4
},
"verification_command": "PATH=... pnpm install --frozen-lockfile && pnpm exec vitest run test/unit/foo/bar.test.ts",
"scope_compliance": {
"respects_exclusions": true,
"touches_only_listed_files": true
},
"risks_and_clarifications": [
"RISK-1: <thing reviewer should check>",
"..."
],
"evidence_refs": [
"packages/foo/package.json",
"docs/specs/phase-1/...",
"CLAUDE.md §6"
],
"artifact_manifest_event_id": "evt-<artifact.manifest.published id>",
"artifact_refs": [
"docs/plans/foo-implementation-plan.md",
"docs/plans/foo-backlog.md"
],
"dispatch_id": "<from briefing>"
}
```
**Required fields**: `summary`, `file_plan`, `test_plan` (or `verification_command`), `dispatch_id`.
**Optional but strongly recommended**: `risks_and_clarifications`, `scope_compliance`,
`evidence_refs`, `artifact_manifest_event_id`, `artifact_refs`. These reduce
critic's auditing effort and let orchestrator pre-populate
`contract.exclusions` and `contract.evidence_contract`.
If arch created rich artifact metadata, it MUST be published in
`artifact.manifest.published` before `arch.proposal.done`. Do not paste object
refs into `arch.proposal.done.artifact_refs`; that field is a replayable string
path list for evidence gates.
Arch-authored planning artifacts are normally `status=draft` or
`status=proposed`. That status means "candidate input for critic and
orchestrator", not accepted runtime truth. Orchestrator may accept the candidate
as-is, merge several candidate artifacts into a new final artifact, or reject
the package and re-dispatch arch.
## Schema critic MUST emit (design.critique.done OR gate.failed)
### Success path (critic approves arch's plan)
```json
{
"verdict": "approve",
"summary": "<one-line: what was reviewed and what conclusion>",
"risks": [], // empty or low-severity informational risks
"fix_items": [], // empty — nothing to fix
"evidence_refs": [
"arch event evt-...",
"packages/foo/package.json",
"docs/specs/..."
],
"dispatch_id": "<from briefing>"
}
```
### Reject path — TWO event-type options (same semantic after P1/K2):
**Option A — `design.critique.done verdict=reject`** (preferred default):
```json
{
"verdict": "reject",
"summary": "<reason in one sentence>",
"risks": [
"BLOCKER-1: <hard issue arch must fix>",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-synthesizer
uisee-ai
Use for the designated synthesizer in a ZaoFu fanout-then-synthesis Channel.
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-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-channel-research-synthesizer
uisee-ai
Use when synthesizing a ZaoFu research-review Channel.
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-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-backlog-batch-closeout
uisee-ai
ZaoFu backlog/task batch closeout workflow for Codex or Claude.
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
Signals
- Stars
- 34
- Forks
- 4
- Open issues
- 0
- Last commit (this folder)
- Aug 14, 2026 (2 months 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 - 0.650score
zf-channel-discussion-synthesizer
uisee-ai
Use for the designated synthesizer 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
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-harness-design-handoff 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-harness-design-handoff skill. Agent Mart. https://agentmart.dev/skills/uisee-ai-zf-harness-design-handoff (last updated 2026-10-24)