llm-serving-auto-benchmark
Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, or another serving framework. Use when a user wants to find the…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-14 00:15
Agents & models
26,291 results
agent-audit
Audit your AI agent setup for performance, cost, and ROI. Scans OpenClaw config, cron jobs, session history, and model usage to find waste and recommend…
intent-memory
Retrieve and verify prior decisions, preferences, and work from permitted memory sources with bounded semantic searches when needed. Optionally delegate to a…
vidu-s-api
Integrate Vidu S2-Avatar real-time digital characters and Vidu S2-Editing live video editing. Use for Vidu S session creation, Aliyun RTC media, control…
ac-workflow
Workflow entrypoint for feat/fix/refactor/chore/docs/continue tasks in this Android repo. Use when the user asks to change code, AGENTS.md, .agents/skills,…
agent-fathom
Search and read Fathom meeting recordings: transcripts, AI summaries, action items, highlights, attendees, CRM matches, meeting types, teams, and users. Also…
fire-in-the-hole
Run scope-it --publish and go-for-it for the current work.
grill-me-quick
Grill the user's plan or design in quick mode, auto-deciding confident calls and asking only when uncertain or high-risk. Uses Chain-of-Verification via…
skill-review
Review a skill using writing-for-agents and skill-creator, and optionally apply fixes.
splitoff
Hand the current conversation to a fresh background agent using a self-contained handoff summary; use a named Claude Code agent or a native Codex subagent.
llm-friendly-context
Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute without guessing. Use when writing or…
recipe-persona
Create or update personas with demographic, contextual, JTBD, and behavioral data
llm-friendly-context
Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute without guessing. Use when writing or…
recipe-plan
Create work plan from design document with optional test skeleton generation.
subagents-orchestration-guide
Guides subagent coordination through implementation workflows. Use when: orchestrating multiple agents, managing workflow phases, determining autonomous…
claude-to-grok
Maps Claude Code tool, agent, and progress-tracking identifiers to Grok runtime equivalents while preserving claude-code-workflows (dev-workflows*) execution…
knowledge-base
Project-specific prompt optimization knowledge management. Use when storing or retrieving learned patterns from comparisons. Provides schema, extraction…
recipe-eval-prompt
Compares original and optimized prompts through repeated blind paired execution in git worktrees. Use when evaluating prompt improvement effects or learning…
recipe-eval-skill
Creates or updates Claude Code skills through interactive dialog, then evaluates effectiveness with sequential paired comparisons. Use when creating new…
worktree-execution
Git worktree management for isolated parallel prompt execution. Use when creating isolated environments for prompt comparison or managing worktree lifecycle.…
skills-sync
Manage, upload, and version local Agent Skills with the `skills-sync` CLI. Use this skill whenever the user wants to scan local/global/project Skills, upload…
threadline-gateway
Submit durable work context to a Threadline Human-Agent Gateway and close cross-session decisions with the Threadline CLI. Use whenever an agent produces a…
full-output-enforcement
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any…
high-impact-journal-publishing
Guidance and workflow for planning, writing, submitting, revising, and publishing scientific manuscripts in high-impact journals. Use when Claude needs to…