Skip to content
Back to search

aelf-skills

Unified aelf skills hub for discovery, routing, bootstrap, and health checks across OpenClaw, Codex, Cursor, and Claude Code.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/aelfproject--aelf-skills/badge.svg)](/listings/aelfproject--aelf-skills)

HTML

<a href="/listings/aelfproject--aelf-skills"><img src="/api/listings/aelfproject--aelf-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

npm install @blockchain-forever/aelf-skills
# or
bun add @blockchain-forever/aelf-skills

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

SKILL.md · Manifest · 82 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. ---
  2. name: aelf-skills-hub
  3. description: >
  4. Discovery, download, and configuration hub for the entire aelf agent skill ecosystem.
  5. Use when the user wants to: (1) explore or list available aelf skills,
  6. (2) install/bootstrap aelf skills into Cursor, Claude Desktop, OpenClaw, Codex, or Claude Code,
  7. (3) route an aelf-related intent to the correct skill,
  8. (4) check health or audit installed skills,
  9. (5) onboard a new skill into the aelf ecosystem.
  10. Covers domains: Portkey CA wallet, Portkey EOA wallet, Awaken DEX, eForest NFT marketplace,
  11. AelfScan explorer, TomorrowDAO governance, aelf node interaction.
  12. ---
  13. # aelf Skills Hub
  14. One-stop meta-skill for discovering, downloading, configuring, and routing all aelf ecosystem skills.
  15. ## Available Skills
  16. Read `skills-catalog.json` for the full machine-readable registry. Current skills:
  17. | ID | Domain |
  18. |---|---|
  19. | `portkey-ca-agent-skills` | CA wallet: registration, auth, guardian, transfer |
  20. | `portkey-eoa-agent-skills` | EOA wallet: create, import, assets, transfer |
  21. | `aelf-node-skill` | Node: chain status, block, tx, contract view/send |
  22. | `aelfscan-skill` | Explorer: address, token, NFT, statistics analytics |
  23. | `awaken-agent-skills` | DEX: quote, swap, liquidity, K-line |
  24. | `eforest-agent-skills` | NFT marketplace: symbol, collection, listing, trade |
  25. | `tomorrowdao-agent-skills` | Governance: DAO, proposals, BP election, resources |
  26. ## Workflow
  27. ### 1. Route user intent
  28. Read [docs/SKILL_ROUTING_MATRIX.md](docs/SKILL_ROUTING_MATRIX.md) to map intent → skill.
  29. Key rules:
  30. - Wallet: default EOA; switch to CA on guardian/register/recover/CA-hash signals.
  31. - Chain data: `aelf-node-skill` for raw node interaction; `aelfscan-skill` for aggregated analytics.
  32. - DEX/NFT: domain skill handles logic; wallet skill provides signing identity.
  33. - Ambiguous: return Recommended / Alternative / Reason.
  34. ### 2. Bootstrap the skill
  35. ```bash
  36. ./bootstrap.sh --only <skill-id>
  37. ```
  38. Options: `--source auto|npm|github|local`, `--skip-install`, `--skip-health`, `--dest <dir>`.
  39. ### 3. Configure for client
  40. After bootstrap, run setup inside the downloaded skill directory:
  41. ```bash
  42. cd downloaded-skills/<skill-id>
  43. bun run setup openclaw # for OpenClaw
  44. bun run setup cursor # for Cursor
  45. bun run setup claude # for Claude Desktop
  46. ```
  47. ### 4. Health check
  48. ```bash
  49. bun run health:check -- --skills-root ./downloaded-skills
  50. ```
  51. ## Recovery
  52. | Problem | Action |
  53. |---|---|
  54. | Dependency download failed | `./bootstrap.sh --source github --only <skill-id>` |
  55. | skill-id not found | `bun run catalog:generate`, then retry |
  56. | Health check failed | Follow `health:check` output, add missing artifacts |
  57. ## References
  58. - Catalog field semantics: [docs/CATALOG_SCHEMA.md](docs/CATALOG_SCHEMA.md)
  59. - Intent routing matrix: [docs/SKILL_ROUTING_MATRIX.md](docs/SKILL_ROUTING_MATRIX.md)
  60. - E2E scenarios with recovery: [docs/AI_E2E_SCENARIOS.md](docs/AI_E2E_SCENARIOS.md)
  61. - Security audit: `bun run security:audit`
README.md · README · 210 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. [中文](README.zh-CN.md) | English
  2. # aelf Skills
  3. A single discovery and bootstrap entry for the aelf skill ecosystem.
  4. [![npm](https://img.shields.io/npm/v/@blockchain-forever/aelf-skills)](https://www.npmjs.com/package/@blockchain-forever/aelf-skills)
  5. This repository provides:
  6. 1. Bilingual entry docs for humans and AI agents.
  7. 2. A machine-readable catalog: `skills-catalog.json`.
  8. 3. One-click bootstrap: `bootstrap.sh`.
  9. ## AI Quick Prompt (OpenClaw / Codex / Cursor / Claude Code)
  10. ```text
  11. Repository: https://github.com/AElfProject/aelf-skills
  12. This is a client-agnostic prompt for OpenClaw, Codex, Cursor, and Claude Code.
  13. Read first: skills-catalog.json, docs/SKILL_ROUTING_MATRIX.md, docs/AI_E2E_SCENARIOS.md.
  14. Then run:
  15. 1) ./bootstrap.sh --source github --dest ./downloaded-skills
  16. 2) bun run health:check -- --skills-root ./downloaded-skills
  17. 3) read `clientInstall.openclaw` / `clientInstall.ironclaw` from `skills-catalog.json`; if `installCommand` exists, execute it locally instead of treating a GitHub tree URL as the final install input
  18. Routing rule: follow SKILL_ROUTING_MATRIX; if ambiguous, output Recommended/Alternative/Reason.
  19. Failure rule: use Common Recovery Template in docs/AI_E2E_SCENARIOS.md.
  20. ```
  21. ## Scope
  22. This hub focuses on **discovery, download, install, and capability indexing**.
  23. It does **not** replace each skill repository's own client integration logic.
  24. Client-specific setup (`OpenClaw`, `Cursor`, `Claude Desktop`, `IronClaw`, `Codex`, `Claude Code`) remains inside each skill repo.
  25. AI agents: jump to [AI Navigation](#ai-navigation) for routing and execution guides.
  26. ## Discovery vs Activation
  27. Treat skill distribution in two stages:
  28. 1. `discovery`: GitHub repo URL / npm package / ClawHub slug help the host find the skill.
  29. 2. `activation`: the host or agent executes the machine-readable install contract from `skills-catalog.json`.
  30. Rules:
  31. 1. GitHub tree/repo URLs are discovery sources only. Do not treat them as the final IronClaw install artifact.
  32. 2. For IronClaw, prefer `clientInstall.ironclaw.installCommand` and expect a trusted local install step.
  33. 3. For OpenClaw, prefer `ClawHub` / managed install when `distributionSources.clawhubId` exists; otherwise use `clientInstall.openclaw.installCommand`.
  34. ## Prerequisites
  35. - `bun >= 1.1.0` (hard requirement)
  36. - `npm >= 10`
  37. - `git >= 2.39`
  38. - `tar` (GNU tar / bsdtar)
  39. ## Local Environment Setup
  40. `workspace.json` paths use `${SKILLS_BASE}` placeholders for portability.
  41. `workspace.json` is Codex-local workspace config; external consumers should use `skills-catalog.json` as the data source.
  42. ```bash
  43. export SKILLS_BASE=/path/to/your/workspace
  44. ```
  45. Example:
  46. - `${SKILLS_BASE}/AElf/aelf-node-skill`
  47. - `${SKILLS_BASE}/awaken/awaken-agent-skills`
  48. ## Install
  49. ```bash
  50. npm install @blockchain-forever/aelf-skills
  51. # or
  52. bun add @blockchain-forever/aelf-skills
  53. ```
  54. ## Quick Start
  55. ```bash
  56. # 1) Generate public catalog and sync README tables
  57. bun run catalog:generate
  58. # 2) Generate local catalog with sourcePath (for local bootstrap/health)
  59. bun run catalog:generate:local
  60. # 3) Run baseline gates
  61. bun run health:check
  62. bun run readme:check
  63. bun run security:audit
  64. # 4) Bootstrap selected skills
  65. ./bootstrap.sh --only aelf-node-skill --skip-install
  66. # 5) Check hub/catalog update drift (non-blocking)
  67. bun run update:check
  68. ```
  69. ## Bootstrap CLI
  70. ```bash
  71. ./bootstrap.sh [--catalog <path>] [--dest <dir>] [--source auto|npm|github|local] [--skip-install] [--skip-health] [--only <csv>]
  72. ```
  73. Defaults:
  74. 1. `--source auto` (npm first, fallback to github)
  75. 2. install enabled
  76. 3. health check enabled
  77. 4. `skills-catalog.json` as catalog source
  78. ## Update Self-Check
  79. `aelf-skills` includes built-in update reminders for `bootstrap`, `health:check`, and `catalog:generate`.
  80. Checks are non-blocking and cache-backed (default TTL 24h).
  81. Reminder output is throttled to once per TTL window by `lastNotifiedAt`.
  82. Commands:
  83. 1. `bun run update:check`
  84. 2. `bun run update:check -- --force`
  85. 3. `bun run update:check:json`
  86. Environment variables:
  87. 1. `AELF_SKILLS_UPDATE_CHECK=0|1` (default `1`)
  88. 2. `AELF_SKILLS_UPDATE_TTL_HOURS=24` (default `24`)
  89. 3. `AELF_SKILLS_UPDATE_CACHE_PATH=<path>` (default `~/.aelf-skills/update-check-cache.json`)
  90. ## Generated Catalog
  91. `skills-catalog.json` is the stable machine interface.
  92. Main fields per skill:
  93. 1. `id`, `displayName`
  94. 2. `npm` (`name`, `version`)
  95. 3. `repository.https`
  96. 4. `distributionSources` (`githubRepo`, `npmPackage`, optional `clawhubId`)
  97. 5. `description`, `capabilities`
  98. 6. `artifacts` (`skillMd`, `mcpServer`, `openclaw`)
  99. 7. `setupCommands` (compatibility display commands such as `claudeDesktop`, `cursor`, `openclaw`, `ironclaw`)
  100. 8. `clientSupport` (support matrix such as `claude_desktop`, `cursor`, `ironclaw`, `codex`)
  101. 9. `clientInstall` (machine-executable activation contract for `openclaw` / `ironclaw`)
  102. 10. `dependsOn` (optional, schema `1.3.0`)
  103. Schema references:
  104. 1. `docs/schemas/workspace.schema.json`
  105. 2. `docs/schemas/skill-frontmatter.schema.json`
  106. 3. `docs/schemas/openclaw.schema.json`
  107. 4. `docs/schemas/skills-catalog.schema.json`
  108. Schema evolution policy:
  109. 1. `patch` (`1.3.x`): wording/docs fixes, no field semantics change.
  110. 2. `minor` (`1.x.0`): backward-compatible field additions.
  111. 3. `major` (`x.0.0`): breaking changes only.
  112. ## AI Navigation
  113. 1. Catalog field semantics: [docs/CATALOG_SCHEMA.md](docs/CATALOG_SCHEMA.md) | [docs/CATALOG_SCHEMA.zh-CN.md](docs/CATALOG_SCHEMA.zh-CN.md)
  114. 2. Intent routing matrix: [docs/SKILL_ROUTING_MATRIX.md](docs/SKILL_ROUTING_MATRIX.md) | [docs/SKILL_ROUTING_MATRIX.zh-CN.md](docs/SKILL_ROUTING_MATRIX.zh-CN.md)
  115. 3. End-to-end execution scenarios (with recovery): [docs/AI_E2E_SCENARIOS.md](docs/AI_E2E_SCENARIOS.md) | [docs/AI_E2E_SCENARIOS.zh-CN.md](docs/AI_E2E_SCENARIOS.zh-CN.md)
  116. 4. Type safety baseline and rollout status: [docs/TYPE_SAFETY_MATRIX.md](docs/TYPE_SAFETY_MATRIX.md) | [docs/TYPE_SAFETY_MATRIX.zh-CN.md](docs/TYPE_SAFETY_MATRIX.zh-CN.md)
  117. ## Current Skill Snapshot
  118. This section is auto-synced by `bun run catalog:generate`.
  119. <!-- SKILL_TABLE_START -->
  120. | ID | npm Package | Version | OpenClaw Tools | Description |
  121. |---|---|---:|---:|---|
  122. | aelf-node-skill | @blockchain-forever/aelf-node-skill | 0.1.3 | 11 | AElf node querying and contract execution skill for agents. |
  123. | aelfscan-skill | @aelfscan/agent-skills | 0.2.2 | 61 | AelfScan explorer data retrieval and analytics skill for agents. |
  124. | awaken-agent-skills | @awaken-finance/agent-kit | 1.2.4 | 11 | Awaken DEX trading and market data operations for agents. |
  125. | eforest-agent-skills | @eforest-finance/agent-skills | 0.4.3 | 48 | eForest symbol and forest NFT operations for agent workflows. |
  126. | portkey-ca-agent-skills | @portkey/ca-agent-skills | 2.3.0 | 32 | Portkey CA wallet registration/auth/guardian/transfer operations for agents. |
  127. | portkey-eoa-agent-skills | @portkey/eoa-agent-skills | 1.2.6 | 21 | Portkey EOA wallet and asset operations for aelf agents. |
  128. | tomorrowdao-agent-skills | @tomorrowdao/agent-skills | 0.2.0 | 44 | TomorrowDAO governance, BP, and resource operations for agents. |
  129. <!-- SKILL_TABLE_END -->
  130. ## Health Check
  131. If a check fails, use the [Common Recovery Template](docs/AI_E2E_SCENARIOS.md#common-recovery-template).
  132. ```bash
  133. # Check local source repositories from workspace.json
  134. bun run health:check
  135. # Check downloaded skills under specific root
  136. bun run health:check -- --skills-root ./downloaded-skills
  137. ```
  138. ## Security Boundary
  139. 1. `bootstrap` does not execute setup commands.
  140. 2. `bootstrap` only downloads, optionally installs dependencies, and runs health checks.
  141. 3. Use `bun run security:audit` to detect risky setup command patterns.
  142. ## CI Gates
  143. CI workflow: `.github/workflows/gates.yml`
  144. Fixture-based gate set:
  145. 1. `catalog:generate` with `testdata/workspace.ci.json`
  146. 2. `health:check` against fixture catalog
  147. 3. `readme:check`
  148. 4. `security:audit`
  149. 5. `bootstrap --only fixture-node-skill --source local --skip-install`
  150. ## Contributing
  151. 1. Contribution guide: [CONTRIBUTING.zh-CN.md](CONTRIBUTING.zh-CN.md) | [CONTRIBUTING.md](CONTRIBUTING.md)
  152. 2. AI execution contract: [docs/AI_SKILL_CONTRACT.zh-CN.md](docs/AI_SKILL_CONTRACT.zh-CN.md) | [docs/AI_SKILL_CONTRACT.md](docs/AI_SKILL_CONTRACT.md)
  153. 3. AI prompt template: [docs/templates/AI_NEW_SKILL_PROMPT.zh-CN.md](docs/templates/AI_NEW_SKILL_PROMPT.zh-CN.md) | [docs/templates/AI_NEW_SKILL_PROMPT.md](docs/templates/AI_NEW_SKILL_PROMPT.md)
  154. 4. PR checklist: [docs/templates/NEW_SKILL_CHECKLIST.zh-CN.md](docs/templates/NEW_SKILL_CHECKLIST.zh-CN.md) | [docs/templates/NEW_SKILL_CHECKLIST.md](docs/templates/NEW_SKILL_CHECKLIST.md)
  155. 5. Skill markdown template: [docs/templates/SKILL_TEMPLATE.zh-CN.md](docs/templates/SKILL_TEMPLATE.zh-CN.md) | [docs/templates/SKILL_TEMPLATE.md](docs/templates/SKILL_TEMPLATE.md)
  156. 6. Golden path example: [docs/examples/EXAMPLE_NEW_SKILL_DIFF.zh-CN.md](docs/examples/EXAMPLE_NEW_SKILL_DIFF.zh-CN.md) | [docs/examples/EXAMPLE_NEW_SKILL_DIFF.md](docs/examples/EXAMPLE_NEW_SKILL_DIFF.md)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.