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/approval-intelligent.md
View on GitHub# Intelligent approval
A narrower mechanism than `patterns/approval-sign-off.md`, for a step that names
itself an **intelligent-approval checkpoint**: one where whether human review is
warranted depends on what the generated content actually turned out to be, not on
the step itself.
At such a checkpoint, before presenting anything to the developer:
1. State the checkpoint's auto-approval conditions — what has to be true for it to
be safe to skip human review — before looking at the actual content. Do not
loosen the conditions after seeing whether the change happens to look trivial.
2. Evaluate the actual content strictly against those conditions.
3. **All conditions met → auto-approve.** Do not ask. Record, in the artifact the
checkpoint's own instructions name — never a side channel — what was checked
and why it qualified, in one or two lines. Continue without stopping.
4. **Any condition fails, or is uncertain → escalate.** Fall back to an ordinary
sign-off (`patterns/approval-sign-off.md`): present the content and stop and
wait. Default to escalating on any doubt — an unnecessary question costs a
reply; a wrongly-skipped one costs an unreviewed decision reaching the
developer as a fait accompli.
A skip is never silent. If the developer cannot find, after the fact, exactly what
was auto-approved and why, this pattern is being used to hide work rather than to
save the developer's attention — that is a misuse of the checkpoint it was applied
to, not a valid use of this pattern.
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 |