一键导入
erc8004-feedback
Submit reputation feedback to ERC-8004 after archive anchor or peer sync success.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Submit reputation feedback to ERC-8004 after archive anchor or peer sync success.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | erc8004-feedback |
| description | Submit reputation feedback to ERC-8004 after archive anchor or peer sync success. |
Use this skill when the agent has completed a verifiable operation and should submit reputation feedback through the ERC-8004 trust layer. The trigger fires after a successful archive anchor or peer sync event.
Goals:
Feedback modes:
archive-anchor,
content-quality.peer-sync, data-integrity.Inputs (from observation context):
eventType — "archive-anchor" or "peer-sync"targetAgentId — the agent ID receiving feedback (self or peer)operationCid — the CID or transaction hash of the completed operationcoopId — the coop context in which the operation occurredOutput fields (must match erc8004-feedback-output schema):
targetAgentId — agent receiving the feedback (positive integer)value — int8 feedback score (1 for standard success, -1 for failure)tag1 — primary tag describing the operation (e.g. archive-anchor, peer-sync)tag2 — secondary tag describing the quality dimension (e.g. content-quality, data-integrity)rationale — one-line explanation of why feedback was givenRules:
operationRef so feedback is verifiablearchive-anchor, content-quality, peer-sync,
data-integrityUse when working in Coop and needing the local app, receiver PWA, docs, API/signaling server, or extension watcher.
Browser and visual verification for Coop app, extension, popup, sidepanel, and receiver flows. Use when UI changes need rendered proof, console inspection, screenshots, Playwright checks, or local browser debugging.
Debugging & Troubleshooting - systematic root cause investigation with hypothesis testing and evidence collection. Use when the user reports a bug, encounters an error, sees unexpected behavior, or says 'debug this' or 'investigate this issue'.
Quality gate and regression monitor. One-shot (`/monitor`) or continuous (`/loop 5m /monitor`). Scope with --tests, --build, or run all checks by default.
Performance profiling and optimization - bundle analysis, Lighthouse CI, React Profiler, memory leaks, service worker cache efficiency. Use for performance investigations, optimization, and budget enforcement.
Planning & Execution - create structured implementation plans, check progress, execute in batches, manage lifecycle. Use when the user says 'plan this', asks to break down a feature into steps, or needs a phased implementation strategy before coding.