MCP servers and skills: search, filter by where they run, and compare.
Use this skill when the user is doing hands-on DOCA AES-GCM work on a BlueField DPU or ConnectX NIC — configuring `doca_aes_gcm_task_encrypt` / `_task_decrypt`, querying `doca_aes_gcm_cap_*` for per-k
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Required for 4+ step requests; add tasks at start and update status after each step.
OfficialSkillApache-2.0★ 564 in collectionNo key
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
OfficialSkillApache-2.0★ 564 in collectionNo key
Run a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.
SkillMIT★ 483No key
Multi-model orchestration subagents for Claude Code — delegates by task scope to Gemini's 1M-token context or GPT's fast iteration, then routes every result back through Claude review.
SkillMIT★ 153No key
A production-ready, reusable template for building sophisticated multi-agent AI systems with Claude Code. This architecture enables hierarchical agent coordination, specialized task delegation, and co
SkillMIT★ 8No key
An orchestration DSL and embedded runtime for hosting agentic systems. Durable, inspectable workflows with deterministic step ordering, running in-process under a capability jail — the model lives in
SkillMIT★ 5No key
Silent NEXUS is a model-agnostic AI agent harness with interactive CLI workflows, scoped memory, user profiles, personas, planning, task orchestration, subagents, provider integrations, and bounded se
SkillApache-2.0★ 2Few starsNo key
Claude Code skill for orchestrating complex engineering work with atomic task decomposition, verification gates, and cost-aware model routing
SkillMIT★ 2Few starsNo key
Pick the right Claude model (haiku/sonnet/opus) per task using TypeSafe's Jev, with a Claude Code subagent hook
SkillMITFew starsNo key
A Claude Code harness: 13 specialized agents, 16 skills and a six-beat AGENTS.md workflow that takes a task from an isolated worktree to an evidence-backed pull request.
SkillMIT★ 1Few starsNo key
Intent alignment guard for Claude Code — 5-question task-start protocol, tiered action gate, and PreToolUse hook that blocks destructive actions before they execute.
SkillMITFew starsNo key
Work-process skills for Claude Code and Codex CLI. Each skill states one promise and ships the checks that would catch it breaking that promise.
SkillMITFew starsNo key
Primary agent config untuk OpenCode yang berperan sebagai Project Manager - mengoordinasikan subagent untuk menyelesaikan task user.
SkillMITFew starsNo key
reserve scarce Astra quota by routing architecture and final acceptance to Astra while delegating bounded execution to cheaper Codex models.
SkillMITFew starsNo key
Agent Skills that allow to extent Agentic Assistants like Claude or Gemini with specialized expertise, procedural workflows, and task-specific resources. Based on the Agent Skills open standard, a “sk
SkillApache-2.0Few starsNo key
Who stands behind it
