{"id":"aelfproject-aelf-skills","name":"aelf-skills","homepage":null,"repo_url":"https://github.com/AElfProject/aelf-skills","category":"devtools","subcategories":[],"tags":["aelf","agent-skills","skill-registry","bootstrap","catalog","mcp","openclaw","cursor","claude-code","codex","ironclaw"],"what_it_does":"aelf-skills is a client-agnostic hub for discovering, downloading, bootstrapping, and indexing an “aelf agent skill” ecosystem. It provides a machine-readable skills catalog (skills-catalog.json), a bootstrap.sh CLI for fetching/installing selected skills, and health/security checks plus routing documentation for multiple agent clients.","use_cases":["Automated discovery and bootstrap of AElf-related agent skill repositories/packages","Capability indexing and client-specific activation routing via a stable catalog schema","Running health checks and security audits for downloaded/installed skills","Providing AI agents a consistent, structured “install contract” (clientInstall) for skills"],"not_for":["Serving as a runtime API for on-chain operations (the hub focuses on distribution/bootstrap, not contract execution logic)","Replacing each individual skill repository’s client integration logic","A hosted service with network endpoints (appears to be a local/CLI/tooling package)"],"best_when":"You want a single catalog + bootstrap workflow to standardize how multiple agent clients (OpenClaw/Codex/Cursor/Claude Code/IronClaw) obtain and activate AElf skills.","avoid_when":"You need a managed hosted service with authenticated HTTP APIs, or you cannot run local bootstrap/install steps safely in your environment.","alternatives":["Directly install individual skill packages from npm/GitHub without a central catalog","Use each client’s native skill integration/registry (e.g., ClawHub/other hubs) without this consolidated bootstrap layer"],"af_score":62.8,"security_score":33.8,"reliability_score":30.0,"package_type":"skill","discovery_source":["openclaw"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T13:38:35.638494+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":false,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":[],"oauth":false,"scopes":false,"notes":"No auth requirements are described for using the hub itself; it operates as a local CLI/tooling package. Skill install commands may have their own auth needs, but those are not specified here."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No hosted pricing model is described; appears to be distributed as an npm package/CLI."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":62.8,"security_score":33.8,"reliability_score":30.0,"mcp_server_quality":0.0,"documentation_accuracy":85.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":90.0,"rate_limit_clarity":5.0,"tls_enforcement":60.0,"auth_strength":20.0,"scope_granularity":0.0,"dependency_hygiene":45.0,"secret_handling":50.0,"security_notes":"Security boundary is explicitly stated: bootstrap does not execute setup commands; it downloads and optionally installs dependencies and runs health checks. There is a security:audit step to detect risky setup-command patterns. However, the documentation does not clearly specify how secrets are handled during bootstrap/install, nor does it describe TLS/transport guarantees for downloads beyond typical HTTPS assumptions. Since activation may involve executing per-skill installCommand, the primary risk is supply-chain/trust management for third-party skill repositories and commands.","uptime_documented":0.0,"version_stability":35.0,"breaking_changes_history":30.0,"error_recovery":55.0,"idempotency_support":"false","idempotency_notes":"Not clearly documented. Health checks and bootstrap steps are described, but idempotency guarantees for repeated bootstrap runs are not explicitly stated.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Bootstrap/install may execute or rely on per-skill install commands (clientInstall). Agents should ensure trust boundaries before running installCommand locally.","GitHub repo URLs are treated as discovery sources, not final install artifacts (routing/activation uses skills-catalog.json contracts)."]}}