Skip to content

davepoon/buildwithclaude / plugins/all-skills/skills/feedback

feedback

Verified

Turn post-task feedback—even blunt or angry feedback—into an evidence-based, approval-gated improvement plan for the agent/user workflow. Use after agent work goes wrong, misses expectations, creates friction, or should improve in future. Never mutate during the feedback turn.

FileKindSize
LICENSEother1.0 KB
SKILL.mdskill md8.0 KB
references/approval-protocol.mdmarkdown1.4 KB
references/hosts/claude-code.mdmarkdown1.2 KB
references/hosts/codex.mdmarkdown1.2 KB
references/hosts/generic.mdmarkdown616 B
references/hosts/hermes.mdmarkdown1015 B
references/hosts/pi.mdmarkdown1.1 KB
references/privacy.mdmarkdown1.1 KB
references/routing.mdmarkdown2.3 KB

references/hosts/codex.md

View on GitHub
# OpenAI Codex adapter

## Invocation
Use `$feedback` explicitly. `/skills` can inspect available skills in Codex clients that expose it.

## Surfaces
Potential skills include repository `.agents/skills/feedback/SKILL.md`, user `~/.agents/skills/feedback/SKILL.md`, and configured roots. Repository guidance belongs in `AGENTS.md`; Codex builds an instruction chain from Codex home through the project, with more specific files closer to the working directory taking precedence.

Local memories under `~/.codex/memories/` are generated state used to improve later work, not the primary surface for mandatory human-authored policy.

## Routing
- Reusable workflow → Agent Skill.
- Mandatory repository behavior → narrowest applicable `AGENTS.md`.
- Architecture/decision/runbook → checked-in docs.
- Stable user guidance → user-level `AGENTS.md` or explicit configuration.
- Generated-memory issue → supported lifecycle/configuration or move mandatory guidance to `AGENTS.md`; do not casually hand-edit generated memory files.

## Guardrails
No feedback-turn edits. Preserve `AGENTS.md` scope/precedence. Do not claim Codex remembered because the current session acknowledged something. Treat generated memory as implementation state, not a public incident log.
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: 471kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall