Skills Library

Reusable agent skills

Preview what each skill can do, inspect the markdown contract, then copy it or open the upstream source on GitHub.

8 skills available

Plan concurrent coding-agent work with explicit dependencies, exclusive workspace ownership, a bounded worker count, evidence requirements, and an ordered integration path.

Audit content exclusions, MCP server admission, tool permissions, and indirect context paths with a per-client coverage matrix and synthetic tests that never require real secrets.

Use Brain when an AI coding agent needs durable repo memory, compiled context, local retrieval, session enforcement, note history, and undo inside the project.

Use Plan to turn rough ideas into shaped execution plans through brainstorms, specs, runtime slices, and explicit source-of-truth modes.

Use Caveman to compress agent output across Claude Code, Codex, Gemini, Cursor, Windsurf, Cline, Copilot, and other agents while preserving technical accuracy.

Use Skill Creator when a repeated agent workflow should become a portable SKILL.md with triggers, rules, references, and scripts.

Use Review when the goal is to find bugs, regressions, missing tests, and unsafe assumptions before summarizing the diff.

Use Agent Observability Audit to find broken trace links, unstable identities, unsafe payload capture, high-cardinality metrics, and missing outcome evidence in agent systems.

planningready

Parallel Agent Work Planner

Plan concurrent coding-agent work with explicit dependencies, exclusive workspace ownership, a bounded worker count, evidence requirements, and an ordered integration path.

Source

Capabilities

  • Finds hidden dependencies and serialization points before dispatch
  • Defines independent work packets with exclusive writable ownership
  • Sets concurrency from review and infrastructure capacity
  • Requires inspectable evidence from every worker
  • Plans dependency-aware integration and final-head verification

Best used for

  • Splitting a multi-package feature across isolated coding-agent sessions
  • Planning research, implementation, and review packets for a large change
  • Reducing overlap and stale-branch failures in multi-agent work
  • Deciding when a task should remain sequential
agentsparallel-workorchestrationworktreesplanning

SKILL.md

---
name: parallel-agent-work-planner
description: Plan parallel coding-agent work when a task may benefit from concurrent agents, worktrees, or subagents. Produce a dependency-aware work packet plan; do not dispatch agents or change files.
metadata:
  author: Ryan VerWey
  reviewed: "2026-09-10"
---

# Parallel Agent Work Planner

Turn a software task into a safe parallel execution plan. Use concurrency only for work that can proceed independently and be reviewed on its own.

## Inspect

1. Read the goal, acceptance criteria, repository instructions, and current revision.
2. Identify shared contracts, generated artifacts, migrations, lockfiles, deployment state, and other serialization points.
3. Draw the task dependency graph before assigning workers.
4. Estimate review capacity and shared infrastructure limits.

## Decide

Keep the task sequential when it is small, tightly coupled, destructive, or dominated by one shared boundary. Parallelize only packets that have stable inputs, distinct writable ownership, independent checks, and no need for another packet's unreviewed output.

Use read-only research or review packets when exploration can proceed independently. Do not invent work merely to occupy another agent.

## Define Each Work Packet

For every packet, provide:

- goal and observable output
- prerequisites and dependency edges
- exact repository and base revision
- writable files or boundaries
- relevant read-only context
- non-goals and forbidden external actions
- required checks and evidence
- stop conditions and blocker reporting
- integration order and result handoff

Assign one writable owner per file or shared contract. Workers may inspect neighboring code but must not refactor, publish, merge, deploy, or close tracking work unless the user separately grants that authority.

## Set the Concurrency Budget

Recommend the smallest worker count that shortens the critical path. Limit it by independent packet count, reviewer capacity, CI and sandbox capacity, rate limits, and expected coordination cost.

Explain which packets run concurrently and which remain ordered. If independence is uncertain, keep the edge sequential and state what evidence would make fan-out safe.

## Plan Fan-In

Name one integration owner. Specify the order for contracts, consumers, tests, documentation, generated files, review fixes, and release metadata.

Require every worker to return its base revision, changed files or research scope, commands and outcomes, source URLs, assumptions, blockers, and interaction risks. Require focused checks after each integration step and the full project checks on the combined head.

Add an independent review of the combined diff. Passing checks on separate branches are not evidence that the integrated result works.

## Return

Produce:

1. Parallelism decision and rationale.
2. Dependency graph in a compact text or table form.
3. Work packets with exclusive ownership and checks.
4. Concurrency budget and dispatch groups.
5. Fan-in order and conflict policy.
6. Final verification and release gates.
7. Assumptions, blockers, and work kept sequential.

## Sources

Reviewed September 10, 2026. Product capabilities below are examples; the planning method is SLOPSTACK guidance.

- [GitHub Copilot app agent sessions](https://docs.github.com/en/copilot/how-tos/github-copilot-app/agent-sessions)
- [GitHub Copilot SDK custom agents and sub-agent orchestration](https://docs.github.com/en/copilot/how-tos/copilot-sdk/features/custom-agents)
- [GitHub Copilot app slash commands](https://docs.github.com/en/copilot/reference/github-copilot-app-reference/slash-commands)
- [OpenAI model guidance](https://developers.openai.com/api/docs/guides/latest-model)