Best agent workflow skills, page 2

Writing documents for agents. An agent skill from bestofjs/bestofjs.

bestofjs/bestofjs

Benchmarks how much CodeGraph helps a coding agent on a real repository, comparing runs with and without it for a chosen local or published version.

colbymchenry/codegraph

Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

getpaseo/paseo

Drives cognee from the terminal with remember, recall, forget and improve memory commands, dataset and config management and database migrations.

topoteretes/cognee

Analyze application logs from the .evlog/logs/ directory. An agent skill from activepieces/activepieces.

activepieces/activepieces

Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

KKKKhazix/khazix-skills

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

trpc-group/trpc-agent-go

A skill your agent uses when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches…

geeksblabla/stateofdev.ma

Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage.

jarrodwatts/claude-code-config

Monitors task execution for skill improvement opportunities.

rebelytics/one-skill-to-rule-them-all

Create agent skills for Microsoft technologies using official documentation.

MicrosoftDocs/mcp

Builds new skills from scattered docs, specs or code, and refactors existing skills for clear triggers, reliable activation and a quality checklist.

2025Emma/vibe-coding-cn

Guides writing a new agent skill or improving an existing one, covering how to keep it concise, how much freedom to give the agent and how to lay out bundled resources.

shareAI-lab/Kode-CLI

Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

openobserve/openobserve

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

thedotmack/claude-mem

Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

prisma/orm

Query and invoke tools on MCP servers using fastmcp list and fastmcp call.

PrefectHQ/fastmcp

Runs an autonomous modify, verify, keep-or-discard loop against any metric, with subcommands for planning, debugging, fixing, security audits, shipping and more.

uditgoenka/autoresearch

Set up, review, debug, or validate an Orca per-workspace environment recipe: the on-demand, disposable runtime (cloud sandbox, VM, SSH host, or…

stablyai/orca

Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.

gastownhall/beads

Checks whether a sofa, table, bed or appliance fits in a measured Pascal room and reports only what the evidence supports, or asks for the missing measurements.

pascalorg/editor

Cut a FastMCP release end to end. An agent skill from PrefectHQ/fastmcp.

PrefectHQ/fastmcp

Saves and recalls markdown notes between agent sessions with the agent-carnet CLI, tracking which notes proved useful so stale ones expire and good ones stay.

yamadashy/repomix

Sets the rules for an agent working inside Rowboat Spaces: reply in the thread you were asked in, mention people and agents correctly and hand off work without loops.

rowboatlabs/rowboat

Starts three parallel reviewer subagents over the current conversation transcript, then turns their findings into concrete edits to existing skills.

cursor/plugins

Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.

MemPalace/mempalace

Turns reusable decisions, templates or workflows from the current conversation into a new workspace skill through plan, approval, draft, validation and publication.

agentscope-ai/QwenPaw

Router for the gstack skill suite. (gstack)

garrytan/gstack

Complete Hindsight documentation for AI agents. An agent skill from vectorize-io/hindsight.

vectorize-io/hindsight

Meta-skill that turns docs, APIs, code or specs into a reusable skill with references and a quality gate, and refactors skills that are unclear or misfire.

tradecatlabs/vibe-coding-cn

Records one solved and verified problem as a durable learning in the repository, but only when the reasoning is not already clear from the final code, tests or docs.

EveryInc/compound-engineering-plugin

Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.

slopus/happy

Forms a two-agent committee with contrasting profiles to analyze a stuck problem in parallel, reconcile their views and return a consensus plan without editing files.

getpaseo/paseo

Runs the Cognee AI memory platform in Docker, from a one-file prebuilt image to a full compose stack with UI, MCP server, Postgres and Neo4j.

topoteretes/cognee

Set up, index, and manage SocratiCode codebase indexing. An agent skill from giancarloerra/SocratiCode.

giancarloerra/SocratiCode

Packs a local or remote repository into a single AI-friendly file with the Repomix CLI, then reads and searches that output to explain structure, find patterns or report metrics.

yamadashy/repomix

Interviews you one question at a time about goal, trigger, permissions and data needs, then drafts a single agentic workflow markdown file.

dotnet/Open-XML-SDK

Mines local Copilot CLI session logs for dotnet/maui to rank costly or failing runs, tag recurring failure modes, propose repo edits and emit guard evals.

dotnet/maui

Reproduces a feature from Codex or Claude Code in Qwen Code by running the reference agent under capture, reading the traces, then implementing matching behavior.

QwenLM/qwen-code

Development conventions and architecture guide for the Claude Code CLI repository.

codeaashu/claude-code

Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

automazeio/ccpm

Verifies a delivery end to end by driving the real product on a CLI, web, desktop or iOS Simulator surface, capturing evidence and publishing a round with the lh CLI.

lobehub/lobehub

Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

charmbracelet/crush

Distills source material about a colleague, a relationship or a celebrity into reusable Person Profiles that an agent can later work from, in English or Chinese.

titanwings/distilly

Teaches an agent to use the Mission Control dashboard API: register, send heartbeats, fetch assigned tasks, report progress and disconnect, with API key auth.

builderz-labs/mission-control

Guides setup, classroom generation and secondary development for OpenMAIC, the multi-agent interactive classroom, one confirmed phase at a time.

THU-MAIC/OpenMAIC

Pairs the claude-mem Cowork plugin with a cmem.ai account by writing the sync token, user id and SyncHub URL into the plugin config without exposing the secret.

thedotmack/claude-mem

Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

mksglu/context-mode