reputation
ERC-8004 on-chain agent reputation management — submit and revoke feedback, append responses, approve clients, and query reputation summaries, feedback entries, and client lists.
What this skill does
# Reputation Skill
Provides ERC-8004 on-chain agent reputation operations using the reputation-registry contract. Read operations (get-summary, read-feedback, read-all-feedback, get-clients, get-feedback-count, get-approved-limit, get-last-index) work without a wallet. Write operations (give-feedback, revoke-feedback, append-response, approve-client) require an unlocked wallet.
## Usage
```
bun run reputation/reputation.ts <subcommand> [options]
```
## Subcommands
### give-feedback
Submit feedback for an agent in the ERC-8004 reputation registry. Requires an unlocked wallet.
```
bun run reputation/reputation.ts give-feedback --agent-id <id> --value <value> [--value-decimals <decimals>] [--tag1 <tag>] [--tag2 <tag>] [--endpoint <endpoint>] [--feedback-uri <uri>] [--feedback-hash <hex>] [--fee <fee>] [--sponsored]
```
Options:
- `--agent-id` (required) — Agent ID to give feedback for (non-negative integer)
- `--value` (required) — Feedback value (signed integer, e.g., 5 for positive, -2 for negative)
- `--value-decimals` (optional, default 0) — Decimal precision for the value (non-negative integer)
- `--tag1` (optional) — Primary classification tag (e.g., "helpful", "accuracy")
- `--tag2` (optional) — Secondary classification tag
- `--endpoint` (optional) — Endpoint or context identifier for the feedback
- `--feedback-uri` (optional) — URI pointing to detailed feedback data
- `--feedback-hash` (optional) — 32-byte SHA-256 hash of the feedback data as a hex string
- `--fee` (optional) — Fee preset (`low`, `medium`, `high`) or micro-STX amount
- `--sponsored` (flag) — Submit as a sponsored transaction
Output:
```json
{
"success": true,
"txid": "0xabc...",
"message": "Feedback submitted for agent 42.",
"agentId": 42,
"value": 5,
"valueDecimals": 0,
"network": "mainnet",
"explorerUrl": "https://explorer.hiro.so/txid/0xabc..."
}
```
### revoke-feedback
Revoke previously submitted feedback. Only the original feedback submitter (tx-sender) can revoke their own feedback. Requires an unlocked wallet.
```
bun run reputation/reputation.ts revoke-feedback --agent-id <id> --index <index> [--fee <fee>] [--sponsored]
```
Options:
- `--agent-id` (required) — Agent ID whose feedback you want to revoke (non-negative integer)
- `--index` (required) — Feedback index to revoke (non-negative integer)
- `--fee` (optional) — Fee preset (`low`, `medium`, `high`) or micro-STX amount
- `--sponsored` (flag) — Submit as a sponsored transaction
Output:
```json
{
"success": true,
"txid": "0xdef...",
"message": "Feedback index 0 revoked for agent 42.",
"agentId": 42,
"index": 0,
"network": "mainnet",
"explorerUrl": "https://explorer.hiro.so/txid/0xdef..."
}
```
### append-response
Append a response to a feedback entry. Any principal can append a response; the contract tracks unique responders per feedback entry. Requires an unlocked wallet.
```
bun run reputation/reputation.ts append-response --agent-id <id> --client <address> --index <index> --response-uri <uri> --response-hash <hex> [--fee <fee>] [--sponsored]
```
Options:
- `--agent-id` (required) — Agent ID associated with the feedback (non-negative integer)
- `--client` (required) — Stacks address of the original feedback submitter
- `--index` (required) — Feedback index to respond to (non-negative integer)
- `--response-uri` (required) — URI pointing to the response data
- `--response-hash` (required) — 32-byte SHA-256 hash of the response data as a hex string
- `--fee` (optional) — Fee preset (`low`, `medium`, `high`) or micro-STX amount
- `--sponsored` (flag) — Submit as a sponsored transaction
Output:
```json
{
"success": true,
"txid": "0xghi...",
"message": "Response appended to feedback index 0 for agent 42.",
"agentId": 42,
"client": "SP2...",
"index": 0,
"responseUri": "ipfs://response...",
"network": "mainnet",
"explorerUrl": "https://explorer.hiro.so/txid/0xghi..."
}
```
### approve-client
Approve a client address to submit feedback for an agent up to a specified index limit. Caller must be the agent owner or an approved operator. Requires an unlocked wallet.
```
bun run reputation/reputation.ts approve-client --agent-id <id> --client <address> --index-limit <limit> [--fee <fee>] [--sponsored]
```
Options:
- `--agent-id` (required) — Agent ID to configure approval for (non-negative integer)
- `--client` (required) — Stacks address of the client to approve
- `--index-limit` (required) — Maximum number of feedback entries the client may submit (non-negative integer)
- `--fee` (optional) — Fee preset (`low`, `medium`, `high`) or micro-STX amount
- `--sponsored` (flag) — Submit as a sponsored transaction
Output:
```json
{
"success": true,
"txid": "0xjkl...",
"message": "Client SP3... approved for agent 42 up to index limit 10.",
"agentId": 42,
"client": "SP3...",
"indexLimit": 10,
"network": "mainnet",
"explorerUrl": "https://explorer.hiro.so/txid/0xjkl..."
}
```
### get-summary
Get the aggregated reputation summary for an agent. Returns total feedback count and WAD-averaged summary value. Does not require a wallet.
```
bun run reputation/reputation.ts get-summary --agent-id <id>
```
Options:
- `--agent-id` (required) — Agent ID to query (non-negative integer)
Output:
```json
{
"success": true,
"agentId": 42,
"totalFeedback": 7,
"summaryValue": "5000000000000000000",
"summaryValueDecimals": 18,
"network": "mainnet"
}
```
### read-feedback
Read a specific feedback entry by agent ID, client address, and feedback index. Does not require a wallet.
```
bun run reputation/reputation.ts read-feedback --agent-id <id> --client <address> --index <index>
```
Options:
- `--agent-id` (required) — Agent ID to query (non-negative integer)
- `--client` (required) — Stacks address of the feedback submitter
- `--index` (required) — Feedback index to read (non-negative integer)
Output:
```json
{
"success": true,
"agentId": 42,
"client": "SP2...",
"index": 0,
"value": 5,
"valueDecimals": 0,
"wadValue": "5000000000000000000",
"tag1": "helpful",
"tag2": "",
"isRevoked": false,
"network": "mainnet"
}
```
### read-all-feedback
Get a paginated list of all feedback entries for an agent. Supports optional tag filtering and cursor-based pagination (page size: 14). Does not require a wallet.
```
bun run reputation/reputation.ts read-all-feedback --agent-id <id> [--tag1 <tag>] [--tag2 <tag>] [--include-revoked] [--cursor <cursor>]
```
Options:
- `--agent-id` (required) — Agent ID to query (non-negative integer)
- `--tag1` (optional) — Filter by primary tag
- `--tag2` (optional) — Filter by secondary tag
- `--include-revoked` (flag) — Include revoked feedback entries in results
- `--cursor` (optional) — Pagination cursor from a previous response
Output:
```json
{
"success": true,
"agentId": 42,
"items": [
{
"client": "SP2...",
"index": 0,
"value": 5,
"valueDecimals": 0,
"wadValue": "5000000000000000000",
"tag1": "helpful",
"tag2": "",
"isRevoked": false
}
],
"cursor": null,
"network": "mainnet"
}
```
### get-clients
Get a paginated list of client addresses that have given feedback for an agent. Cursor-based pagination with page size 14. Does not require a wallet.
```
bun run reputation/reputation.ts get-clients --agent-id <id> [--cursor <cursor>]
```
Options:
- `--agent-id` (required) — Agent ID to query (non-negative integer)
- `--cursor` (optional) — Pagination cursor from a previous response
Output:
```json
{
"success": true,
"agentId": 42,
"clients": ["SP2...", "SP3..."],
"cursor": null,
"network": "mainnet"
}
```
### get-feedback-count
Get the total feedback count for an agent. Does not require a wallet.
```
bun run reputation/reputation.ts get-feedback-count --agent-id <id>
```
Options:
- `--agent-id` (required) — Agent ID to query (non-negative integer)
Output:
```json
{
"success": true,
"agentId": 42,
"feedbackCountRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.