erc8004
ERC-8004 identity, reputation, and validation — register identities, retrieve identity info by agent ID, query reputation scores, submit peer feedback, and request or check third-party validation status.
What this skill does
# ERC-8004 Skill
Unified ERC-8004 on-chain agent identity skill — register agent identities, retrieve identity info, query reputation scores, submit feedback, and request or check third-party validations. Read operations work without a wallet. Write operations require an unlocked wallet.
## Usage
```
bun run erc8004/erc8004.ts <subcommand> [options]
```
## Subcommands
### register
Register a new agent identity on-chain using the ERC-8004 identity registry. Returns a transaction ID. Check the transaction result to get the assigned agent ID. Requires an unlocked wallet.
```
bun run erc8004/erc8004.ts register [--uri <uri>] [--metadata <json>] [--fee <fee>] [--sponsored]
```
Options:
- `--uri` (optional) — URI pointing to agent metadata (IPFS, HTTP, etc.)
- `--metadata` (optional) — JSON array of `{"key": "...", "value": "<hex>"}` pairs (values are hex-encoded buffers)
- `--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": "Identity registration transaction submitted. Check transaction result to get your agent ID.",
"network": "mainnet",
"explorerUrl": "https://explorer.hiro.so/txid/0xabc..."
}
```
### get-identity
Get agent identity information from the ERC-8004 identity registry. Returns owner address, URI, and wallet if set. Does not require a wallet.
```
bun run erc8004/erc8004.ts get-identity <address>
```
Arguments:
- `<address>` (required) — Agent ID (non-negative integer) to look up
Output:
```json
{
"success": true,
"agentId": 42,
"owner": "SP1...",
"uri": "ipfs://...",
"wallet": "SP2...",
"network": "mainnet"
}
```
### get-reputation
Get the aggregated reputation score for an agent. Returns total feedback count and WAD-averaged summary value. Does not require a wallet.
```
bun run erc8004/erc8004.ts get-reputation <address>
```
Arguments:
- `<address>` (required) — Agent ID (non-negative integer) to query
Output:
```json
{
"success": true,
"agentId": 42,
"totalFeedback": 10,
"summaryValue": 85,
"summaryValueDecimals": 0,
"network": "mainnet"
}
```
### give-feedback
Submit feedback for an agent in the ERC-8004 reputation registry. Value is a signed integer. Requires an unlocked wallet.
```
bun run erc8004/erc8004.ts give-feedback <address> <score> <comment> [--fee <fee>] [--sponsored]
```
Arguments:
- `<address>` (required) — Agent ID (non-negative integer) to give feedback for
- `<score>` (required) — Feedback value (signed integer, e.g., 5 for positive, -2 for negative)
- `<comment>` (required) — Comment or tag for the feedback (used as tag1)
Options:
- `--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 submitted for agent 42.",
"agentId": 42,
"value": 5,
"network": "mainnet",
"explorerUrl": "https://explorer.hiro.so/txid/0xdef..."
}
```
### request-validation
Request third-party validation for an agent from a validator. Requires an unlocked wallet.
```
bun run erc8004/erc8004.ts request-validation <address> --validator <validator-address> --request-uri <uri> --request-hash <hex> [--fee <fee>] [--sponsored]
```
Arguments:
- `<address>` (required) — Agent ID (non-negative integer) to request validation for
Options:
- `--validator` (required) — Stacks address of the validator
- `--request-uri` (required) — URI pointing to the validation request data
- `--request-hash` (required) — 32-byte SHA-256 hash of the request 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": "Validation requested from SP3... for agent 42.",
"validator": "SP3...",
"agentId": 42,
"network": "mainnet",
"explorerUrl": "https://explorer.hiro.so/txid/0xghi..."
}
```
### validation-status
Check the status of a validation request by its 32-byte request hash. Does not require a wallet.
```
bun run erc8004/erc8004.ts validation-status <request-id>
```
Arguments:
- `<request-id>` (required) — 32-byte SHA-256 hash of the validation request as a hex string
Output:
```json
{
"success": true,
"requestHash": "abc123...",
"validator": "SP3...",
"agentId": 42,
"response": 90,
"hasResponse": true,
"tag": "trusted",
"lastUpdate": 12345,
"network": "mainnet"
}
```
## Notes
- Read operations (`get-identity`, `get-reputation`, `validation-status`) work without a wallet
- Write operations (`register`, `give-feedback`, `request-validation`) require an unlocked wallet (`bun run wallet/wallet.ts unlock`)
- Agent IDs are assigned by the contract upon registration — check the transaction result to find your assigned ID
- Feedback values are signed integers; positive values improve reputation, negative values lower it
- Validation responses are scores between 0 and 100 submitted by the designated validator
Related 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.