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/interfaces/stack.md
View on GitHub# Technology decision interface
Use only when technology selection, replacement, versioning or compatibility is part
of the solution. State the decision scope, constraints, selected technology and the
capability it provides. Record relevant alternatives and trade-offs in the evaluation
record; publish only the confirmed choice and its consequences.
Cover compatibility with existing interfaces, runtime/build/deployment constraints,
operational ownership, licensing or cost obligations, migration and rollback needs,
and verification of the selected technology. Do not generate a generic full-stack
diagram or inventory unchanged technologies. Link existing HLD/LLD/NFR decisions.
## Ways to express this design
- A technology-to-responsibility table can relate each changed dependency to its
capability, owning component, relevant version and configuration constraints.
- A compatibility or dependency diagram can expose runtime/build relationships
that affect installation, deployment or interoperability.
- A small configuration or integration example can clarify how a selected tool
connects to the existing environment, using confirmed values and no credentials.
## What good looks like
A reader knows where each selected technology is used, what compatibility must
hold, and how to verify the integration. Version specificity reflects the decision;
it does not invent unsupported pins. Selection rationale stays in Evaluate.
A library replacement may need only a compatibility table and migration notes.
A runtime upgrade may benefit from a dependency view and a build/deploy check list.
Neither implies documenting the project's entire stack.
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: 471k | 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 |