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/architecture.md
View on GitHub# Architecture interface
`Architecture.md` is the authoritative, integrated end-to-end solution record for
the story. Use it when the solution changes system, container, component ownership,
deployment topology or a cross-boundary contract. It must capture the complete
chosen solution and every settled decision made during Frame, Research, Evaluate,
Solution drafting, review and feedback. State the affected boundary and the
intended responsibility distribution. Show the relevant C4 level or supporting
view: system context, containers, deployment, dynamic flow or another justified
diagram.
Describe relationships, communication purpose, data/control crossings, technology
constraints and confirmed architectural decisions. For each material decision,
record the chosen outcome, scope and ownership, affected interfaces or contracts,
failure/recovery and operational or security consequences, and how it will be
verified. Trace representative user and system flows end to end, including normal,
failure and recovery paths where they affect the design. Reference existing
HLD/LLD/NFR documents and describe the solution delta rather than copying them.
Do not invent containers for folders, teams or tools. Do not put implementation
classes or unconfirmed target requirements in this artifact. Supporting artifacts
(`Design.md`, `Stack.md` and `Efforts.md`) may add detail, but may not introduce a
material decision absent from or conflicting with `Architecture.md`; add a concise
decision and consequence there first. Record affected architecture documents and
verification obligations for the publish phase.
## Ways to express this design
- A container or boundary diagram plus a short responsibility table can explain
ownership, communication purpose and what changes. Label the abstraction level;
link component internals to the implementation design rather than mixing levels.
- A sequence diagram can trace a business transaction or data flow across those
boundaries, including a consequential failure or recovery path.
- A deployment or trust-boundary view can clarify placement, identity, network
access or fault isolation when these determine the architecture.
## What good looks like
A reader can locate every changed responsibility, trace each representative scenario
through named boundaries, and understand the contracts, decisions and failure
consequences without reopening research or evaluation files.
Accompanying descriptions explain responsibilities and constraints the diagram
cannot express clearly; they do not merely narrate its arrows.
For example, an integration change might combine a container delta, an ownership
table and a cross-system sequence. A hosting change might instead use deployment
placement and failover flow. These are optional compositions, not mandatory headings.
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 |