DataArt/artisyn-implementation-harness / .claude/skills/evolve
evolve
VerifiedImprove harness skills, agents, workflows, and conventions from observed friction or a concrete improvement request. Supports reflect, triage, validate, and adopt; use for harness improvements rather than ordinary product changes.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.3 KB |
| interfaces/improvement.md | markdown | 1.2 KB |
| interfaces/reflection.md | markdown | 353 B |
| interfaces/validation.md | markdown | 653 B |
| patterns/task-tracking.md | markdown | 777 B |
| references/00-router.md | markdown | 1007 B |
| references/01-reflect.md | markdown | 805 B |
| references/02-triage.md | markdown | 2.6 KB |
| references/03-draft.md | markdown | 1.2 KB |
| references/04-validate.md | markdown | 1.5 KB |
| references/05-adopt.md | markdown | 1.5 KB |
| runtime/browser.md | markdown | 2.5 KB |
| runtime/context.md | markdown | 517 B |
| runtime/credentials.md | markdown | 512 B |
| runtime/delegation.md | markdown | 910 B |
| runtime/interaction.md | markdown | 359 B |
| runtime/planning.md | markdown | 745 B |
| runtime/review.md | markdown | 1.0 KB |
| runtime/task-tracking.md | markdown | 897 B |
references/02-triage.md
View on GitHub# Triage
## Responsibility and completion
Determine the underlying concern, scope, existing owner and affected callers, then
prepare actionable changes as inactive drafts. Finish with candidate paths and
acceptance criteria or explicit defer/archive decisions. Drafting belongs to this
stage; Triage does not publish or automatically invoke validation.
| Action | Required result |
| ------- | ------------------------------------------------------------------ |
| Update | Proposed revision to the existing owner |
| Create | New candidate and evidence that no suitable owner already exists |
| Merge | Consolidated candidate, superseded paths and caller migration plan |
| Retire | Explicit removals, caller handling and rollback information |
| Defer | Missing evidence and a condition for reconsideration |
| Archive | Reason no change is warranted |
## Procedure
Accept a concrete request directly, or inventory pending reflections by metadata; read those relevant to the requested
scope. Use local task records first and consult the configured tracker only if
needed. Do not load every skill or fetch every linked ticket by default.
Cluster evidence by underlying failure or useful practice. A single strong case can
justify action. Inspect likely existing owners and callers before choosing update,
create, merge, retire, defer, or archive. Prefer an existing skill, agent, convention doc,
or script when it already owns the concern. Avoid turning one-off preferences into
universal rules. Broader harness audits run only when relevant or requested.
For each actionable cluster create a candidate report using
[the improvement interface](../interfaces/improvement.md), including scope, owner,
sources, proposed action and acceptance criteria. Apply [Draft](03-draft.md) within
Triage to prepare the candidate content and validation plan. New skills and agents
stay inactive drafts until validated and published through Adopt.
Deferred observations retain their source and receive status: deferred, a reason and
reconsideration condition; revisit them only when requested or relevant new evidence
is supplied. Archive no-action observations with their reason. Mark actionable reflections triaged only after
the candidate report and draft content are saved and link them to its path. Preserve source history;
move processed files to reflections/triaged or archive using Git moves for tracked
files and ordinary moves for untracked files. Present the decisions and draft paths,
then stop. Do not automatically validate or publish the drafts.
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 |