Best agent workflow skills, page 166

A skill your agent uses when the user asks to initialize a repo, create AGENTS.md, generate contributor guidelines, or set up agent-oriented documentation for a codebase.

EliasOulkadi/shokunin

Planning agent for task breakdown and implementation planning.

EliasOulkadi/shokunin

Run structured brainstorming sessions (divergent/convergent), improve prompts with 7-dimension framework, and apply decision frameworks (RICE, weighted scoring, first principles, pre-mortem).

EliasOulkadi/shokunin

Compress an overloaded week of startup, research, job-search, creator, or side-project work into one main bet, up to two microbets, essential maintenance, and an explicit kill list.

FAIRY123456789/human-edge-agent-skills

A protocol framework for long-horizon autonomous research tasks.

rongxinzy/RongxinAI

Apply Socratic questioning — systematic inquiry via clarification, assumption-probing, evidence-testing, perspective-shifting, implication-tracing, and meta-questions — to coach learning or surface…

asgard-ai-platform/skills

Build MCP (Model Context Protocol) servers including tool definition, schema design, authentication, error handling, and Claude Code integration.

asgard-ai-platform/skills

Save a summary of the Copilot CLI session on explicit user request.

nowledge-co/community

Check Nowledge Mem connection status, server version, active space, and CLI diagnostics in OpenHands.

nowledge-co/community

Alias for /origin:handoff — symmetric brief/debrief naming. An agent skill from davepoon/buildwithclaude.

davepoon/buildwithclaude

Loop engineering runtime Grill + Monitor. An agent skill from akitaonrails/my-skills.

akitaonrails/my-skills

Evolve any installed skill by generating four variations along separate theses (better inputs / sharper output / more robust / rethink), scoring them on a weighted rubric, and applying the winner.

BankrBot/skills

Use Agent Wormhole for one-time sealed handoffs between autonomous agents, including encrypted mission briefs, scoped secrets, temporary artifacts, receipts, config drops, CLI/API usage, ECHO holder…

BankrBot/skills

Cross-chain token swaps, quotes, portfolio and prices across 14 chains via the Suwappu DEX MCP server.

BankrBot/skills

Rules for writing concise, token-efficient workflow and skill files.

HoangNguyen0403/agent-skills-standard

Entry point for ALL work requests - triages scope from trivial to massive, asks clarifying questions, and routes to appropriate planning skills.

nicepkg/ai-workflow

Ralph Loop 기반 자율 개발 루프. An agent skill from jh941213/my-cc-harness.

jh941213/my-cc-harness

Ralph Loop 병렬 버전. An agent skill from jh941213/my-cc-harness.

jh941213/my-cc-harness

Build students' capacity to read historical documents closely — attending to word choice, tone, and rhetoric as evidence of perspective.

GarethManning/education-agent-skills

Build students' capacity to place historical documents in their temporal and social context.

GarethManning/education-agent-skills

Build students' capacity to compare accounts across multiple historical sources — identifying agreements, contradictions, and gaps.

GarethManning/education-agent-skills

Build students' capacity to interrogate a historical source before reading — asking who authored it, when, why, and what this means for reliability.

GarethManning/education-agent-skills

Multi-agent system research agent for CoWork OS. An agent skill from CoWork-OS/CoWork-OS.

CoWork-OS/CoWork-OS

Decide when specs are worth the overhead, then coordinate product, technical, and implementation work for substantial features.

Terry-Mao/AICodingFlow

Archive vault files into attic/ cold storage, or restore them — the executable runbook for the CLAUDE.md §2.1 contract.

HurricaHjz/second-yourself

Multi-agent consensus-driven code review. An agent skill from nwjs/chromium.src.

nwjs/chromium.src

Enforce engineering rigor and verification loop for coding tasks using multi-agent debate and TDD.

nwjs/chromium.src

Updates checklists and personas for multi-agent skills. An agent skill from nwjs/chromium.src.

nwjs/chromium.src

Resume a handoff (a side-topic spun off mid-grill) and turn it into a test-driven task.

ayoubben18/ab-method

Run an existing task autonomously to completion — each remaining mission in a subagent with tdd, tracker updated per mission, a commit after every green mission.

ayoubben18/ab-method

Decompose a multi-feature or multi-component specification into factory-consumable artifacts.

rsmdt/the-startup

Decompose a single-feature specification into a linear, phase-by-phase implementation plan.

rsmdt/the-startup

A skill your agent uses when creating new skills, editing existing skills, auditing skill quality, converting skills to markdown conventions, or verifying skills before deployment.

rsmdt/the-startup

Dispatch multiple subagents in parallel on independent tasks.

danielvm-git/bigpowers

Create an isolated Git worktree/branch or Jujutsu workspace, then verify a clean test baseline before code.

danielvm-git/bigpowers

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates specs/tech-architecture/tech-stack.md and specs/adr/ inline as decisions crystallise.

danielvm-git/bigpowers

Generate CLAUDE.md and CONVENTIONS.md for a brand-new project through a brief interview, and create the specs/ directory with evolved bigpowers structure (product/, tech-architecture/…

danielvm-git/bigpowers

Start a browser-based dashboard that visualizes architecture, implementation plans, and project status.

danielvm-git/bigpowers

Create a structured session handoff document for continuity across sessions.

robertguss/claude-code-toolkit

Extract insights from external documents (research papers, books, articles).

Abilityai/cornelius

Fast knowledge base retrieval - single FAISS search + graph connections, no subagents or LLM orchestration

Abilityai/cornelius

Measure what chaff reports on the named documents today, as the kind the person chose, and propose the setup — changing nothing yet.

receptron/mulmoterminal

Lay out a Worker with D1 and static Vue assets, with tests that run inside the Workers runtime.

receptron/mulmoterminal

Create the app skeleton: Express API, SQLite through node:sqlite, a Vue screen, and the test harness, following the layout the later checks rely on.

receptron/mulmoterminal

Find the repository's own gates — install, format check, lint, typecheck, build, test — record them, and prove they all pass before anything is touched.

receptron/mulmoterminal

Prove the style bites: write texts that deliberately break the guide and confirm chaff reports them.

receptron/mulmoterminal

Lay out a Vue app on the local Supabase stack, served as static files by wrangler, with tests that run against the local stack.

receptron/mulmoterminal

Applies structured divergent-convergent thinking to generate many creative options, organize them into meaningful clusters, then systematically evaluate and narrow to the strongest choices.

lyndonkl/claude