Best agent workflow skills, page 21

Creates, updates or audits a project's CLAUDE.md by analyzing the codebase, drafting for review and flagging anti-patterns, aiming for under 200 lines.

lhfer/claude-howto-zh-cn

Guides creating, updating, reviewing and validating GitHub Copilot agent skills, from deciding whether a skill is the right tool to structuring bundled resources.

thomast1906/github-copilot-agent-skills

Define metrics from Kayba insights, implement them as Python measurement code, run against traces, and iterate until the metrics are clean and meaningful.

kayba-ai/agentic-context-engine

End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification…

Sahir619/fable-method

Launch an installed Bello supervisor in the background for a repository coding task, or inspect an existing Bello run.

Makson179/Bello

Update, create, improve, and synchronise this repository's AI agent instructions and related assets (including skills).

JocysCom/FocusLogger

How to deploy MCP servers to Vinkius Edge using mcpfusion deploy.

vinkius-labs/mcpfusion

Maps a codebase directory by directory and writes linked AGENTS.md files, each pointing to its parent, to document what each area contains.

Yeachan-Heo/oh-my-claudecode

Creates detailed, sectionized, TDD-oriented implementation plans through research, stakeholder interviews, and multi-LLM review.

piercelamb/deep-plan

A Claude Code skill that allows you to search, browse, and install skills from a database of 31,767+ community skills with intelligent folder-level downloads.

buzhangsan/skill-manager

Search and query past Claude Code, Codex, Kimi Code, Kiro, and Pi session history.

tommy0103/obelisk

Generate 3-5 genuinely distinct candidate approaches for a current question, with the weakest link of each kept visible.

m0n0x41d/haft

Answer questions about the user's own bank accounts and money using the bank MCP tools (listaccounts, getbalances, gettransactions, watches).

noskillish/bankmcp

Manage Bernstein agents - list active agents, inspect their output, kill stalled agents, or stream live logs.

sipyourdrink-ltd/bernstein

Calculate weighted risk scores from specialist agent reports.

Abilityai/trinity

Delegate coding to the Octomind CLI — a token-efficient, model-agnostic coding agent.

Muvon/octomind

Comprehensive project planning and documentation generator for software projects.

adrianpuiu/claude-skills-marketplace

All AI CLI tools × available models × required subscriptions × Bloom max capability.

yohey-w/multi-agent-shogun

Guide for creating Kit extensions. An agent skill from mark3labs/kit.

mark3labs/kit

Write and improve agent skills (SKILL.md files). An agent skill from millionco/expect.

millionco/expect

Task management for AI agents across context windows. An agent skill from marcus/td.

marcus/td

Hand off to a fresh Dave session — ask the user what to work on next, spawn a new session in the current worktree, and send it the task as its first message.

damus-io/notedeck

A skill your agent uses for authorized, read-only research on public Xiaohongshu content or the local Xiaohongshu-like playground fixture.

jumodada/Drissionpage-MCP-Server

Guides the agent to use the OpenFate Bazi MCP server for deterministic Four Pillars charts, true solar time, Da Yun cycles and branch interactions.

openfate-ai/openfate-mcp

Agent Script DSL for deterministic Agentforce agents. An agent skill from Jaganpro/sf-skills.

Jaganpro/sf-skills

Running a team of subagents on one design build: clone briefs, disjoint file ownership, isolated builds, the evidence packet, review lenses, the fix plan, verdicts, cold eyes and the stop rule, with…

AThevon/genjutsu

Conventions and efficient workflows for Outline knowledge bases via mcp-outline tools.

Vortiago/mcp-outline

Control Metis Desktop Inspector built-in browser for local preview (HTML/SVG/file paths), page interaction, accessibility snapshots, and screenshots.

Wholiver/metis

A skill your agent uses when asked to create the initial spec graph for an existing codebase that has source code but no specs.

JetBrains/thinkrail

Add persistent graph-based memory to NanoClaw agents using mnemon.

mnemon-dev/mnemon

Keeps task_plan.md, findings.md and progress.md on disk as the agent's working memory for multi-step work, wired into Kiro steering, with no hooks.

OthmanAdi/planning-with-files

Inspect only enough read-only project information to recommend a route and list the facts behind that recommendation.

Spielewoy/autoprompt-skill

Improves skill-creator generated skills by updating SKILL.md Gotchas and verified examples with reusable learnings.

sandiiarov/skill-creator

Traces a factual error the user points out back to its source (a brain page, a memory file, SOUL.md or USER.md, or a hallucination) and fixes that source instead of just noting the correction.

garrytan/gbrain

Keeps a branch-local issue brief, decision log and session handoffs so a pull request's context survives across separate agent sessions.

pydantic/pydantic-ai-harness

A skill your agent uses when a task involves continuing a project, restoring project context, maintaining file-based project memory, updating current-state summaries, or recording meaningful…

Frappucc1no/recall-loom

Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md short enough for prompt use.

LearnPrompt/cc-harness-skills

Give a Node.js agent (such as OpenClaw) durable, local-first memory plus a queryable SPARQL knowledge graph, backed by CortexDB through its gRPC sidecar and the cortexdb-client npm package.

liliang-cn/cortexdb

Memory consolidation skill for Claude Code. An agent skill from grandamenium/dream-skill.

grandamenium/dream-skill

How to create and maintain agent skills in .agents/skills/. An agent skill from vercel/next.js.

vercel/next.js

Reference for MoAI-ADK's core development principles: TRUST 5 quality gates, SPEC-first domain-driven workflow, agent delegation and token budgeting.

modu-ai/moai-adk

Install, register, and configure x-use, the browser-native MCP server for X (Twitter) automation that needs no X API key.

ihuzaifashoukat/x-use

Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for…

cyberchitta/llm-context.py

Long-horizon robot task execution workflow for multi-step manipulation tasks.

RoboClaw-Robotics/RoboClaw

Applies a 12-stage verified workflow, from research to deploy, to non-trivial coding tasks, scaled to lightweight, standard or full mode by task size.

artemiimillier/bulletproof

Checks and tunes token-saver output compression: reads stats, explains why a command was or was not compressed, and edits config files or environment variables.

ppgranger/token-saver

Adversarial review skill. An agent skill from blueberrycongee/termcanvas.

blueberrycongee/termcanvas

A skill your agent uses when reviewing ava-labs/firewood code changes — pull request or local workspace.

ava-labs/firewood