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/patterns/waf-review.md
View on GitHub# Pattern: WAF Review
A parameterized WAF assessment, callable against any design artifact at any point
in the lifecycle. Findings always append to `design/Report.md`'s `## WAF Assessment`
section — this pattern never produces a standalone review file.
Call with a `target` and, optionally, a `--pillars=` filter (default: all pillars).
## Target → artifact mapping
| Target | Artifact(s) read | Default review lens |
| ---------- | -------------------------------------------------- | ----------------------------------------------------------------------------- |
| `frame` | `design/00 Frame.md` | Completeness, risk, missing ECs |
| `research` | `design/01 Research*.md` | Coverage, credibility, option gaps |
| `evaluate` | `design/02 Evaluate*.md` | Full WAF on recommended option |
| `solution` | `solution/Architecture.md` + `solution/Design*.md` | Full WAF on the chosen approach; Architecture.md is the integrated E2E record |
If the target artifact does not exist, tell the developer which phase to complete
first and stop. Also read `design/Report.md` for existing WAF findings, to avoid
duplicating already-recorded items.
## Step 1 — Read architecture context
Read relevant docs under `{{DESIGN_DOCS_ROOT}}` (across its subfolders) for the
areas the design touches.
## Step 2 — Run the assessment
### Pillar definitions
{{WAF_PILLARS_TABLE}}
### RAG rating
| Rating | Meaning |
| -------- | ---------------------------------- |
| 🟢 Green | Addressed adequately |
| 🟡 Amber | Partially addressed — bounded risk |
| 🔴 Red | Not addressed — material gap |
### Output per pillar
```
### {Pillar} — {RAG}
**Strengths:** ...
**Gaps:** ...
**Recommendations:** P1 (block implementation) / P2 (address in impl) / P3 (backlog)
```
Assess only the pillars specified in `--pillars` (or all if not specified).
**For `frame` target:** focus on completeness (missing ECs, unstated constraints,
scope creep risk) and operational risk.
**For `research` target:** focus on option coverage (obvious alternatives missing?),
credibility of sources, and whether open questions would block evaluation.
**For `evaluate` target:** standard WAF assessment of the recommended option.
**For `solution` target:** standard WAF assessment of the chosen approach as
specified in `solution/Architecture.md`/`solution/Design.md` — this is the last WAF pass before the
human-approval gate, so treat any P1 here as blocking.
## Step 3 — Present findings
Present the full assessment in the console.
**Default (no caller instruction says otherwise):** this is a sign-off gate
(`patterns/approval-sign-off.md`). Say:
> "Review complete. Any corrections before I append to `design/Report.md`? (**yes** to save / **no** to discuss)"
**Stop and wait.** Apply corrections if requested.
**When the calling stage reference explicitly says not to stop here** (it
folds P1/failing findings into its own phase sign-off instead) — continue
straight to Step 4 without presenting or asking. The findings and any P1
items are the calling reference's responsibility to carry forward and name as
a decision at its own sign-off; this pattern never silently drops them.
## Step 4 — Append to Report.md
Apply the docs-writer authoring pattern (`{{provider:skills_root}}/design/patterns/docs-writer-authoring.md`):
delegate appending the dated block below to the `## WAF Assessment` section of
`design/Report.md` to `@docs-writer` rather than editing it directly.
```markdown
### Review — {target} — {YYYY-MM-DD} [pillars: {list}]
| Pillar | Rating | Headline |
| ------ | ------ | -------- |
| ... | ... | ... |
**P1 items:**
- <list or "none">
```
If the `## WAF Assessment` section does not exist in `design/Report.md`, create it.
## Step 5 — Report back
> "WAF review ({target}) complete. Findings appended to `design/Report.md`.
>
> P1 items: <list or 'none'>"
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 |