Best agent workflow skills, page 15

Routes UI tasks to the smallest useful set of UI Skills through the ui-skills CLI, picking a category and loading at most three skills before implementing.

ibelick/ui-skills

A skill your agent uses when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help…

lingxling/awesome-skills-cn

Runs existing Harbor evaluation jobs against a local LobeHub build or LobeHub Cloud, with preflight checks, resume support, and failure triage.

lobehub/lobehub

Write and run custom Pi prompt templates (slash commands) for this extension.

nicobailon/pi-prompt-template-model

Embedded hardware debugging workflow for probe-rs targets using embedded-debugger-mcp.

Adancurusul/embedded-debugger-mcp

Looks up official Claude Code documentation stored as reference files instead of guessing about CLI commands, configuration, or plugin APIs.

obra/superpowers-developing-for-claude-code

Debug and trace ColecoVision and Super Game Module games using the Gearcoleco emulator MCP server.

drhelius/Gearcoleco

Registers durable project materials such as design docs, SOPs and research notes in a LoopX project's own registry so future agents can find them without raw URLs or private content.

loopx-project/loopx

Call Horosa (星阙) local metaphysics tools correctly over MCP or CLI — 110 real techniques: Western natal/predictive astrology (returns, progressions, primary directions, horary 卜卦, election 择日), 八字…

Horace-Maxwell/horosa-skill

Helps design and build AI agents for any domain around a minimal loop of capabilities, knowledge and context, adding planning or subagents only when needed.

shareAI-lab/lab-skills

A skill your agent uses when validating code-index-mcp language strategies, tree-sitter symbol extraction, calledby or import baselines, or sample projects under test/sample-projects after parser…

johnhuang316/code-index-mcp

Searches the user's persistent cross-session memory for timestamped observations synthesized from past agent sessions on cmem.ai.

thedotmack/claude-mem

A skill your agent uses when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'.

agent-sh/agnix

Run structured multi-agent debates using argue CLI for cross-examined, high-confidence answers.

onevcat/argue

Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for…

InditexTech/weavejs

Persistent memory enhancement for AI agents. An agent skill from sopaco/cortex-mem.

sopaco/cortex-mem

Set up the pstack plugin in a project through an interview, and keep every pstack project on one pinned tag and one shared AGENTS.md overrides block.

udecode/dotai

Work with Domscribe — the pixel-to-code bridge. An agent skill from patchorbit/domscribe.

patchorbit/domscribe

Use Memoria as OpenClaw's durable memory slot. An agent skill from matrixorigin/memoria.

matrixorigin/memoria

AI DevKit · Manage running AI agents with ai-devkit agent commands.

codeaholicguy/ai-devkit

This skill should be used for the tool-interface layer of an agent system specifically: writing tool descriptions agents can route on, designing tool schemas and response formats, naming…

guanyang/open-agent-hub

Codebase intelligence via FileScopeMCP — symbol lookup, dependency mapping, importance ranking, and semantic search.

admica/FileScopeMCP

Inspect recent session conversation turns and meta-run history.

clawdotnet/openclaw.net

Visualize and diagnose OpenClaw context window usage. An agent skill from jzOcb/context-doctor.

jzOcb/context-doctor

Generate, verify, or remove large synthetic ZCode task fixtures in local ~/.zcode persistence for UI/session performance testing.

zai-org/ZCode

Fires a Stop hook that captures a Claude Code session transcript automatically when the session ends without a verbal wrap-up.

NateBJones-Projects/OB1

Turns a GitHub course repository into an interactive tutor for the MCP Associate certification, making the learner explain and defend each step.

rohitg00/ai-engineering-from-scratch

Run a lightweight Ultracode workflow for serious coding tasks: plan, split, delegate when useful and allowed by the host, integrate, and verify.

PabloNAX/ultracode-skill

Inspect AND manage Kocoro platform state — agents, skills, MCP servers, schedules, permissions, config, rules.

Kocoro-lab/Kocoro

Scans project-local Claude Code settings files, finds permission patterns worth promoting to global config, then cleans up what global now covers.

malob/nix-config

Sorts what you learned in a session into the right memory surface, filtering out ephemeral notes and duplicates before anything is stored.

zereight/gitlab-mcp

ALWAYS use this skill for ALL sudocode spec and issue operations.

sudocode-ai/sudocode

Find official portals, APIs, and download paths for authoritative primary data sources (governments, international organizations, research institutions, etc.).

MLT-OSS/FirstData

Walks through installing and tuning memory-lancedb-pro, picking an embedding, reranker, and LLM combination from four preset configuration plans.

CortexReach/memory-lancedb-pro-skill

Claude Mind - Search and manage Claude's persistent memory stored in a single portable .mv2 file

memvid/claude-brain

Local-first long-term memory for AI agents via MCP — zero LLM calls at write time, typed retrieval at read time.

chunxiaoxx/nautilus-compass

When you want to pressure-test a potential new business, product, or side project against the serial-founder filter.

coreyhaines31/makerskills

Integrate Convex static self hosting into existing apps using the latest upstream instructions from get-convex/self-hosting every time.

waynesutton/markdown-site

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

hellangleZ/burn-in-cceverywhere-ralph

How to build production MCP servers with MCP Fusion using the MVA (Model-View-Agent) pattern.

vinkius-labs/mcpfusion

Compile a repository's instruction files (AGENTS.md, CLAUDE.md and friends) into an Abide rubric, then validate and calibrate it.

coldteadotai/abide

Installs, configures, and repairs AutoRAG's search model, approved folders, indexes, and datasources, and registers its Lite MCP server.

Marker-Inc-Korea/AutoRAG

Detects and gracefully cancels whichever OMC mode, autopilot, ralph, swarm, pipeline, or team, is currently active, then clears its state.

Yeachan-Heo/oh-my-claudecode

Routes one direct, unambiguous operator request to bind a bounded choice as a DecisionRecord.

m0n0x41d/haft

通过本地 easyeda CLI、daemon 和连接器操作嘉立创EDA专业版（EasyEDA Pro）：用可迁移样例和参数化数据构建或修复原理图、布局布线 PCB，并回读连接、几何、DRC 与保存结果。适用于已有工程操作及数据驱动电路设计。

zhoushoujianwork/easyeda-agent

Use TypeUI with OpenClaw to access project design skills, brand kits, UI prompts, and layout variations through the TypeUI MCP server when creating or refining user interfaces.

bergside/typeui

Rules for choosing Qdrant-Indexer semantic search over grep or file reads when exploring code, debugging or asking where and why questions.

Context-Engine-AI/Context-Engine

Give the agent durable, scoped, explainable memory across sessions and repositories through the Engraphis MCP tools.

Coding-Dev-Tools/engraphis