Skip to content

Adonis0123/adonis-skills / skills/agentic-review-handoff

agentic-review-handoff

Verified

Validate pasted review findings before fixes; run same-session automatic Git review-fix-re-review with a headless Reviewer and no redundant confirmation; start fresh-eyes Git diff Review Intake; resume review-loop sessions or packets; get a DecisionConsult from another AI; or run first-principles/DDD/high-cohesion review. Requires Git and review/consult intent; ordinary implementation or commit-only requests do not start a review loop.

references/environment-recovery.md

View on GitHub
# Reviewer Startup Failures

Keep review work separate from host maintenance. Capture the launcher error and
report the unavailable reviewer once. Do not move/delete Docker sockets, start
services, change account configuration, or ask the user to do those things as a
routine review step. Host repair is a separate task.

For a failure explicitly diagnosed before model submission, correct only an
invocation-local mistake within existing authorization, then retry once. Preserve
the selected account, scope, controls, and budget. Do not infer non-delivery from
silence, a quick exit, or model-generated text. Never resubmit an ambiguous
submission or timeout to the same product. Only the run/consult script may
advance to the next configured fallback product after `timedOut: true`, recording
each switch. This does not prove non-delivery of the timed-out invocation.
Non-timeout failures and timeouts without a remaining fallback stay
`DELIVERY_UNKNOWN`; inspect the existing session. Respect STOP cancellation.

Optional advisory consult: continue independent work and report the missing peer
opinion. Required review: report blocked/UNVERIFIED. Never invent a verdict or
silently substitute an account/product. Report configured fallback switches.
Failure after fallback is unavailable or exhausted ends the attempt.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 323kUpdated Claude CodeCodexVerifiedInstall