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/claude-code.md

View on GitHub
# Claude Code adapter

## Invocation
Standalone skill: `/feedback`.

This repository loaded as a Claude Code plugin: `/feedback-loop:feedback`. Plugin skill commands are namespaced.

Claude Code exposes installed skills as slash commands.

## Surfaces
Potential skills: `.claude/skills/feedback/SKILL.md`, `~/.claude/skills/feedback/SKILL.md`, or plugin `skills/feedback/SKILL.md`.

Potential durable guidance: managed organization policy, project `CLAUDE.md` or `.claude/CLAUDE.md`, `.claude/rules/`, user `~/.claude/CLAUDE.md`, local `CLAUDE.local.md`, and Claude Code auto memory. Use only verified active surfaces and respect instruction precedence/project trust.

## Routing
- Reusable workflow → skill.
- Repository-wide mandatory behavior → narrowest project `CLAUDE.md` or rule.
- User-wide authored preference → user `CLAUDE.md` when explicitly wanted.
- Agent-discovered local learning → auto memory only when it is the right owner.
- Architecture/decision/runbook → project docs, not auto memory.

## Guardrails
No feedback-turn edits. Do not write the same rule to every surface. Auto memory does not replace mandatory human-authored policy. Scope path rules narrowly. Report command/name conflicts instead of claiming `/feedback` is active.
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