DataArt/artisyn-implementation-harness / skills/implementation-harness
implementation-harness
FlaggedInstall the portable AI-dev harness, rebuild its operational graph standalone, harvest project skill improvements into its canonical templates, package direct canonical edits into a portable bundle, or apply canonical updates to an existing project. Use /implementation-harness launch, /implementation-harness reindex-graph, or /implementation-harness patch harvest|prepare|apply.
canonical/skills/design/templates/report.md
View on GitHub---
name: Design Report Template
description: Template for design/Report.md — the living design report, idempotency anchor, and WAF findings store
type: reference
---
# Design Report — <TICKET>: <Short Title>
## Context
_Resolved once in Context Gathering. Every later phase reads these values instead of re-resolving them. Two-track deployments: see `patterns/context-resolution.md`. Single-track deployments: these are fixed values, filled in once._
## State
```yaml
current_stage: context-gathering
completed_stages: []
selected_artifacts: []
next_action: ''
context_fingerprint: ''
```
Update this block whenever a phase starts, completes, or is invalidated. The
`selected_artifacts` values are interface names (`architecture`, `design`, `stack`,
`efforts`) and are the source of truth for downstream review, publish, and resume.
## Evidence
| Source | Read at stage | Relevant decision or constraint | Reference/version |
| ------ | ------------- | ------------------------------- | ----------------- |
Record every required or relevant context source actually read. Add conflicts and
their resolution here; do not rely on conversation history for design provenance.
| Field | Value |
| ------------------- | ------------------------------------------------------------------------------------------------------ |
| Track | <Product / Project — Two-track only; omit this row for single-track deployments> |
| Source docs | <{{DESIGN_DOCS_ROOT}}> |
| Dest docs | <{{DESIGN_DOCS_ROOT}}{subfolder}> |
| Subfolder | <resolved subfolder/section> |
| Architect agent | <{{DESIGN_ARCHITECT_AGENT}}> |
| Implementation note | <resolved implementation note — where the resulting tickets are typically implemented; Two-track only> |
## Status
| Field | Value |
| ------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Ticket | <TICKET> |
| Branch | — _(set by Ceremony, e.g. `docs/{{PROJECT_KEY}}-XX-slug`)_ |
| Status | 🔄 In Progress |
| Phase | 🎯 Context Gathering 🔄 · 🚀 Ceremony ⏳ · 📋 Frame ⏳ · 🔍 Research ⏳ · 🏗 Evaluate ⏳ · 📦 Solution ⏳ · 🔎 Review ⏳ · 💬 Address Feedback ⏳ · 📤 Publish ⏳ · 🏁 Completion ⏳ |
---
## Stage Metrics
<!-- design-metrics:start -->
Source: [stat.json](stat.json). Generated by design-metrics. **Elapsed** = wall-clock
time from the stage's first start to its completion (includes any wait). **Work** =
summed observed work intervals (active effort) within that span. **Wait** = summed
observed wait intervals (blocked on developer input, approval, or an external
dependency) within that span. Durations are shown as `Xh Ym Zs`, rounded to the
nearest second; observed wall time is not human effort, and missing runtime token
usage remains unavailable, never zero.
<!-- design-metrics:end -->
## Assumptions
_Filled in during Research OQ triage. One row per open question answered or classified._
| # | Open question | V/E | Answer / status |
| --- | ------------- | --- | --------------- |
---
## WAF Assessment
_Filled in during the Evaluate phase closing step and updated by any `patterns/waf-review.md` invocation._
<!-- Append dated blocks here. Each block added by Evaluate or the waf-review pattern. -->
---
## Gate
- Approver: —
- Draft MR: —
- Approved: — _(a date once approved, or `declined`)_
- Decline reason: — _(filled in by Address Feedback only if declined)_
---
## Efforts
| Date | Phase | Notes |
| ---- | ----- | ----- |
---
## Implementation Tickets
_Filled in during Completion after implementation tickets are created._
| Ticket | Summary | Tracker |
| ------ | ------- | ------- |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |