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/satellite-review.md
View on GitHub# Pattern: Satellite Review (Design)
Apply `{{provider:skills_root}}/design/runtime/delegation.md` for invocation and unavailable-review handling.
After completing a design artifact or applying architecture doc changes, invoke `{{DESIGN_ARCHITECT_AGENT}}` as a read-only reviewer before presenting the result to the developer.
## When to trigger
- After `solution/Architecture.md` is confirmed — before beginning `solution/Design.md` (see `design-architect-review.md` for the Architecture.md-specific prompt and scope rules)
- After `{{DESIGN_DOCS_ROOT}}` docs are updated in Publish — before archiving
Skip for non-structural artifacts: `solution/Stack.md`, `solution/Efforts.md`, Efforts table updates.
## Review protocol
1. Complete the artifact or apply the changes
2. Invoke `{{DESIGN_ARCHITECT_AGENT}}` with a read-only prompt scoped to the artifact — **"Do not write or edit any files — return output only"**
3. If **OK / no issues**: present result to the developer and continue
4. If **corrections needed**: apply corrections, then re-invoke once more
5. **Maximum 2 iterations.** If still unresolved after 2, report the stalemate to the developer and stop
## Why
Design artifacts drive `{{DESIGN_DOCS_ROOT}}` updates (Publish) and implementation plans (Dev). A structural gap found after Design.md and Stack.md are written cascades corrections across multiple files. An earlier satellite review catches issues at the cheapest point — before downstream artifacts are locked in.
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 |