{"id":"alirezarezvani-claude-skills","name":"claude-skills","homepage":"https://alirezarezvani.medium.com/","repo_url":"https://github.com/alirezarezvani/claude-skills","category":"devtools","subcategories":[],"tags":["agent-plugins","agent-skills","ai-coding-agent","prompt-engineering","python-cli","offline","tooling"],"what_it_does":"An open-source library of modular “Claude Code skills” / agent plugins plus supporting Python CLI tools, personas, and orchestration patterns. It provides structured instructions (e.g., SKILL.md), stdlib-only Python scripts, and converts/install packages for multiple coding agents/tools (Claude Code marketplace/plugin, OpenAI Codex via scripts, Gemini CLI, OpenClaw, Cursor, Aider, Windsurf, Kilo Code, OpenCode, Augment, Antigravity).","use_cases":["Install domain-specific workflow/knowledge packs into coding agents (engineering, product, marketing, compliance, C-level advisory, finance)","Run stdlib-only Python CLI utilities for analysis/generation (e.g., metrics calculations, prioritization, audits, scaffolders)","Use curated personas to standardize agent thinking and communication styles","Apply orchestration patterns (solo sprint, domain deep-dive, multi-agent handoff, skill chain)","Pre-audit skills for security risks using the included skill-security-auditor before installation"],"not_for":["Production usage that requires a hosted SaaS API with a documented service contract and SLA","Use cases needing managed secrets storage, hosted authentication flows, or customer-managed compliance controls from the provider","Environments where arbitrary third-party code execution is forbidden without additional sandboxing"],"best_when":"You want offline/local, tool-agnostic “skill” packages that can be installed into many agent clients and executed via Python scripts without external dependencies.","avoid_when":"You cannot vet or sandbox third-party code/instructions, or you need first-class hosted APIs/webhooks/SDKs with strong runtime governance from a single vendor.","alternatives":["Curated collections of agent instructions hosted inside a single agent ecosystem (e.g., only Claude Code marketplace)","General-purpose agent tooling frameworks (where you implement your own domain prompts/workflows)","Security-focused prompt/agent libraries with fewer executable artifacts","Using your own internal prompt packs and templates (repo-managed) instead of a community catalog"],"af_score":56.0,"security_score":28.5,"reliability_score":31.2,"package_type":"skill","discovery_source":["openclaw"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-29T14:56:36.248231+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":["No service authentication described (local repo/plugin installation)"],"oauth":false,"scopes":false,"notes":"Authentication is not applicable as this is a local/open-source repo. Agent clients may have their own auth, but no centralized API auth is described here."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Repo indicates MIT license and appears to be open-source; no hosted pricing model is described."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":56.0,"security_score":28.5,"reliability_score":31.2,"mcp_server_quality":0.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":100.0,"rate_limit_clarity":0.0,"tls_enforcement":0.0,"auth_strength":50.0,"scope_granularity":0.0,"dependency_hygiene":60.0,"secret_handling":35.0,"security_notes":"The README claims a “skill-security-auditor” that scans skills for issues like command injection, code execution, data exfiltration, prompt injection, and supply-chain risks, and also notes “stdlib-only, zero pip installs” for Python tools. However, as a general community skill bundle that may contain executable scripts/instructions, you should still assume the need for review/sandboxing before installing third-party skills. No explicit guidance is provided here about secret handling practices in the scripts or about TLS/auth for any hosted service (none described).","uptime_documented":0.0,"version_stability":55.0,"breaking_changes_history":45.0,"error_recovery":25.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["This is primarily an instruction/tooling bundle; success depends on the target agent client’s expected skill/plugin format and installation location","Skills may include scripts that execute locally; ensure you review/sandbox when running on untrusted skills","No centralized API means agent runtime error-handling/retry semantics are not standardized across tools"]}}