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/evolve/interfaces/improvement.md
View on GitHub# Improvement interface
Store each candidate under .harness/evolve/{timestamp}-{slug}/ with Report.md,
candidate/ content and Validation.md. These are working artifacts, not discoverable
active skills. Both providers use this shared artifact root; import legacy provider-local candidates explicitly, preserving originals.
Report.md owns:
- Identity, requested outcome, scope/non-goals, source reflection paths and evidence.
- Action (update/create/merge/retire), existing owner and affected callers.
- Acceptance criteria and proposed file mapping: source, destination, baseline hash,
candidate hash, and operation. Explicitly list removals and rollback material.
- Stage table: reflect, triage, validate, adopt; each pending, in_progress,
completed, blocked or not_applicable, with evidence and reasons for bypasses.
- Draft readiness is a Triage outcome, not an executable stage.
- Current stage, next action, unresolved decisions and candidate acceptance record.
- Validation path and verdict; adoption results and integration evidence.
Keep one authoritative state table. Update it on transitions; do not infer completion
from file existence. Split independent changes into separately validated candidates.
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 |