Best agent workflow skills, page 162

A skill your agent uses when a bug, failing test, or unexpected behaviour needs investigation, especially across sessions or context resets.

coco-research/coco

A skill your agent uses when the user says m0 handoff, before I compact, end of session, save session state, resume where we left off, or continue in Cursor or Claude Code.

coco-research/coco

A skill your agent uses when the user says 'm0 remember', 'record what we did', 'note for next session' or 'write a checkpoint', or after finishing a step worth handing to the next session.

coco-research/coco

Convert 'Applied intelligently' Cursor rules (.cursor/rules/.mdc) and slash commands (.cursor/commands/.md) to Agent Skills format (.cursor/skills/).

coco-research/coco

A skill your agent uses when starting a new project, onboarding to an existing product, or auditing an existing folder structure against the standard.

coco-research/coco

A skill your agent uses when starting any task, before invoking any other skill or GSD command, to route between Superpowers skills and GSD commands from project state and task scope.

coco-research/coco

Your AI research and engineering brain trust. An agent skill from coco-research/coco.

coco-research/coco

Create custom subagents for specialized AI tasks. An agent skill from coco-research/coco.

coco-research/coco

Macro-driven trade idea generation, translating macroeconomic views into concrete stock ideas, sector selection from macro regime, international trade ideas via ADRs, cross-border idea sourcing…

agentii-ai/agentii-investment-intelligence

Decomposition methodology for pm agent — turns an approved ARCH document into a Beads task list with explicit dependencies, time-boxes, and acceptance criteria.

avelikiy/great_cto

Compresses artifacts for judge evaluation. An agent skill from closedloop-ai/claude-plugins.

closedloop-ai/claude-plugins

Structured format for capturing high-quality learnings during ClosedLoop runs

closedloop-ai/claude-plugins

Canonical reusable orchestration procedures for the ClosedLoop planning/implementation orchestrators — PLANVALIDATIONSEQUENCE and AWAITINGUSERSEQUENCE.

closedloop-ai/claude-plugins

Add or review developer- and AI-facing conference data endpoints such as llms.txt, sessions.json, speakers.json, or MCP routes for AI Engineer conference pages.

swyxio/skills

Run a structured brainstorm session for startup ideas. An agent skill from c0x12c/ai-toolkit.

c0x12c/ai-toolkit

Investigate a monitoring alert end-to-end. An agent skill from c0x12c/ai-toolkit.

c0x12c/ai-toolkit

Delegate all implementation to Opus sub agents, then review their output yourself.

vvedantb/eva

Automatically derives TLA+ properties (invariants, safety, liveness) from natural-language requirements or structured requirement documents.

ArabelaTso/Skills-4-SE

NLPM noun/verb registry (R51): pick the canonical term, detect vocabulary drift.

xiaolai/nlpm

Create a new custom agent for the workspace. An agent skill from evolution-foundation/evo-nexus.

evolution-foundation/evo-nexus

Create a new slash command for Claude Code. An agent skill from evolution-foundation/evo-nexus.

evolution-foundation/evo-nexus

Configure MCP servers for the workspace — web search, filesystem, GitHub, Stripe, etc.

evolution-foundation/evo-nexus

Create a new custom skill for the workspace. An agent skill from evolution-foundation/evo-nexus.

evolution-foundation/evo-nexus

Browse the EvoNexus plugin marketplace, searching for plugins by keyword, tag, or capability.

evolution-foundation/evo-nexus

Create a phased activation plan using the EvoNexus standard structure — single index file + folder-per-phase + file-per-item, each item detailed with owner, dependencies, decisions pending…

evolution-foundation/evo-nexus

End-of-day consolidation — analyzes agent memory, ADW logs, meetings, tasks, and learnings to generate a complete daily log.

evolution-foundation/evo-nexus

Creates implementation plan, writes project code with judge feedback loop, and submits final experiment run.

OpenLAIR/dr-claw

Builds and edits a model-driven Power Apps app from a natural-language intent — tables, columns, relationships, adaptive forms with sub-grids, views, Choice-column charts, business rules, business…

microsoft/power-platform-skills

Set up MoonPay as an MCP server for Claude Desktop or Claude Code.

moonpay/skills

Guided workflow for building custom AI agents using the OpenHands Software Agent SDK.

OpenHands/extensions

Set up a repository for effective use with OpenHands. An agent skill from OpenHands/extensions.

OpenHands/extensions

Discover and call the configured Volcengine DataPro dataProsearch(query:string) MCP tool for professional-dataset queries.

PKU-YuanGroup/OpenAI4S

A skill your agent uses when generating a human-readable onboarding document from HARNESS.md, AGENTS.md, and REFLECTIONLOG.md — produces a friendly guide for new team members joining a harnessed…

Habitat-Thinking/ai-literacy-superpowers

Multi-agent peer review simulation for finance/economics manuscripts.

franklee16/academic-research-skills

Local self-check of instructions and mask outputs (format/range/consistency) without using GT.

benchflow-ai/skillsbench

Implement data transmission between the local computer and the MCP Server using Base64 encoding

InternScience/scp

A skill your agent uses when about to refactor or refine a user-level or project-level AGENTS.md

vinta/hal-9000

Agent-native admin CLI for authentik identity provider with offline SQLite cache and an MCP server for Claude Desktop.

mvanhorn/printing-press-library

Every Conductor Cloud API primitive, plus bounded session orchestration that handles asynchronous lifecycle races.

mvanhorn/printing-press-library

Everything Flow's community CLIs and MCP servers do, plus the two things none of them do: real Google Drive ingestion and an honest audio-drama pipeline that closes the loop Flow itself cannot.

mvanhorn/printing-press-library

A CLI and MCP server for your Forkable office-lunch program, with a local database and history, spend, and preference queries the web app cannot answer, plus commands to set, confirm, and skip meal…

mvanhorn/printing-press-library

Every MCP Market search, leaderboard, and skill lookup — plus trending deltas, sync diffs, and author portfolios no other tool tracks.

mvanhorn/printing-press-library

The first CLI and MCP server for MotoGP — human-friendly commands, offline SQLite history, and analyses no single endpoint provides.

mvanhorn/printing-press-library

Generate and iterate on web apps with v0 from the terminal: create chats from prompts, stream agent output, sync history to a local SQLite mirror, and track credit spend across models.

mvanhorn/printing-press-library

Unified skill for figma-from-code Phase 3 per-component pipeline.

bitovi/ai-enablement-prompts

Subagent for figma-from-code Phase 0b. An agent skill from bitovi/ai-enablement-prompts.

bitovi/ai-enablement-prompts

Subagent for figma-from-code Phase 2.5. An agent skill from bitovi/ai-enablement-prompts.

bitovi/ai-enablement-prompts

Subagent for figma-from-code Phase 2. An agent skill from bitovi/ai-enablement-prompts.

bitovi/ai-enablement-prompts