Skip to content
Skill category

Agent Workflows skills

Agent skills for subagents, delegation, handoffs, agent memory, self-improvement and skill authoring. Compare ways to run long coding work with several agents.

50 skills

About Agent Workflows

A single agent session has limits. Context fills up, work that could run in parallel runs one step at a time, and lessons from one session vanish before the next. The skills in this category give the agent a working method for those limits.

They fall into four groups. Orchestration skills split a plan across implementer and reviewer subagents or drive other agent command line tools as peers. Handoff and status skills write the note a fresh session starts from and keep a log of long runs. Memory and self-improvement skills read past sessions, record corrections and turn repeated friction into rules or hooks. Authoring skills help you write, test and tune new skills and instruction files.

When choosing, look at who holds the decisions. Good delegation skills keep approval with you and ask subagents to report evidence you can verify. Check which agent harness each skill assumes, because some target Claude Code and others target Codex or Cursor. Be careful with skills that edit your own instruction files or skills on a schedule, and read what they change before turning them on.

Start with one orchestration skill and one handoff skill, then add memory and authoring skills when you notice the same correction coming up again and again.

Showing 34 of 50 skillsGit Credentials Network Clear all
Model-led2,975 tokens in use

Ask Matt

329,112

Agent Workflows

A router over Matt Pocock's engineering skills that tells you which skill or flow fits your situation, from idea to shipped code.

Skill
22idle
2,975in use
3,931up to
Tokens, counted offlineView skill
Model-led1,013 tokens in use

chief-of-staff

329,112

Agent Workflows

Pursue a long-running goal in one session by coordinating subagents and keeping a dated wiki of what was learned.

Skill
24idle
1,013in use
1,013up to
Tokens, counted offlineView skill
Model-led257 tokens in use

claude-handoff

329,112

Agent Workflows

Hand the current conversation to a fresh named background Claude agent that picks up the work immediately.

Skill
22idle
257in use
257up to
Tokens, counted offlineView skill
Model-led152 tokens in use

Handoff

329,112

Agent Workflows

Compact the current conversation into a handoff document so a fresh agent can continue the work, with suggested skills and secrets redacted.

Skill
19idle
152in use
152up to
Tokens, counted offlineView skill
Model-led106 tokens in use

Implement

329,112

Agent Workflows · Developer Tools

Builds the work in a spec or ticket by driving TDD at pre-agreed seams, then runs code-review and commits to the current branch.

Skill
16idle
106in use
106up to
Tokens, counted offlineView skill
Model-led572 tokens in use

Implement Spec

329,112

Agent Workflows · Developer Tools

Implements a whole spec on one integration branch by running implementer subagents in parallel across the ready tickets.

Skill
18idle
572in use
572up to
Tokens, counted offlineView skill
Model-led518 tokens in use

loop-me

329,112

Agent Workflows

Get grilled about the recurring loops in your work and end up with workflow specs ready to delegate.

Skill
20idle
518in use
518up to
Tokens, counted offlineView skill
Model-led123 tokens in use

Research

329,112

Agent Workflows · Research And Academic Writing

Delegates reading to a background agent that investigates primary sources and saves cited findings as a Markdown file in your repo.

Skill
49idle
123in use
123up to
Tokens, counted offlineView skill
Model-led926 tokens in use

retro

329,112

Agent Workflows

Run a retrospective on a coding agent session and get ranked suggestions for improving its environment.

Skill
12idle
926in use
926up to
Tokens, counted offlineView skill
Model-led1,288 tokens in use

Software Factory

329,112

Agent Workflows

A shared vocabulary for designing a software factory: the agent tasks it runs and the services it plugs into, with surveys for picking each product.

Skill
23idle
1,288in use
9,720up to
Tokens, counted offlineView skill
Model-led2,313 tokens in use

writing-for-agents

329,112

Agent Workflows · Writing And Communication

A reference for writing any document an agent reads, from skills to AGENTS.md and CLAUDE.md, built on context pointers, the information hierarchy and pruning.

Skill
28idle
2,313in use
2,866up to
Tokens, counted offlineView skill
Model-led1,340 tokens in use

dispatching-parallel-agents

322,961

Agent Workflows · Developer Tools

Splits two or more independent problems across focused subagents, each with its own scope, constraints and expected output.

Skill
26idle
1,340in use
1,340up to
Tokens, counted offlineView skill
Mixed4,484 tokens in use

subagent-driven-development

322,961

Agent Workflows · Developer Tools

Runs an implementation plan with a fresh implementer subagent per task, a spec and quality review after each, and a final branch review.

Skill
17idle
4,484in use
10,486up to
Tokens, counted offlineView skill
Model-led706 tokens in use

using-superpowers

322,961

Agent Workflows

The bootstrap skill that makes your agent check for a relevant skill before any response, including clarifying questions.

Skill
29idle
706in use
3,783up to
Tokens, counted offlineView skill
Model-led815 tokens in use

verification-before-completion

322,961

Agent Workflows · Code Review And Quality · Developer Tools

Requires fresh command output as evidence before your agent claims work is done, fixed or passing.

Skill
43idle
815in use
815up to
Tokens, counted offlineView skill
Mixed7,253 tokens in use

skill-creator

198,136

Agent Workflows · Developer Tools

Anthropic's skill for making skills: Claude drafts a SKILL.md, runs test prompts with and without it, shows the results in a review viewer and tunes the description that triggers it.

Skill
64idle
7,253in use
18,660up to
Tokens, counted offlineView skill
Model-led2,171 tokens in use

using-agent-skills

119,431

Agent Workflows

Map incoming work to the right agent skill and follow six operating behaviors that apply across all of them.

Skill
55idle
2,171in use
2,171up to
Tokens, counted offlineView skill
Model-led4,089 tokens in use

Neat Freak

22,434

Agent Workflows

End-of-session cleanup that aligns project docs, CLAUDE.md or AGENTS.md rule files and agent memory with what the code and running services do today.

Skill
259idle
4,089in use
11,634up to
Tokens, counted offlineView skill
Model-led2,081 tokens in use

SkillOpt Sleep for Claude Code

19,174

Agent Workflows

Gives Claude Code a sleep cycle: it reads past sessions, replays recurring tasks and stages CLAUDE.md and SKILL.md edits that beat a held-out score.

Skill
131idle
2,081in use
2,081up to
Tokens, counted offlineView skill
Model-led2,241 tokens in use

SkillOpt Sleep for Codex

19,174

Agent Workflows

Gives Codex a sleep cycle: it reviews past sessions, replays recurring tasks and stages skill and CLAUDE.md edits that pass a held-out score gate.

Skill
107idle
2,241in use
2,241up to
Tokens, counted offlineView skill
Model-led2,196 tokens in use

SkillOpt Sleep for Cursor

19,174

Agent Workflows

Reviews recent Cursor sessions, replays recurring tasks and stages edits to a project Cursor skill that pass a held-out score gate.

Skill
82idle
2,196in use
2,196up to
Tokens, counted offlineView skill
Model-led1,017 tokens in use

prompt-engineer

12,473

Agent Workflows

Designs, tests and refines LLM prompts with few-shot and chain-of-thought patterns, structured output schemas, system prompts and eval suites.

Skill
93idle
1,017in use
23,137up to
Tokens, counted offlineView skill
Mixed2,794 tokens in use

dbs-install-skill

11,518

Agent Workflows

Links one skill, or a folder of skills, into every agent installed on the machine with a single script, and cleans up duplicate entries.

Skill
87idle
2,794in use
2,794up to
Tokens, counted offlineView skill
Mixed1,255 tokens in use

goal-prompt

8,320

Agent Workflows

Drafts one-line /goal commands for Claude Code and Codex that have a checkable end state, a stated check, invariants and a stop bound.

Skill
67idle
1,255in use
1,255up to
Tokens, counted offlineView skill

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers