AutoGineer
Generated banner for Implement Spec
Generated logo for Implement Spec

Implement Spec

Matt PocockCommunityCreated by Matt Pocock

  • Skill
  • Workflow
  • Software development
  • MIT
  • No issues found
Download ZIP

From the author

Implement the result of /to-spec and /to-tickets in code.
— the description by Matt Pocock

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The implement-spec skill provides a structured workflow for translating technical specifications and task tickets into functional code. It emphasizes a task-graph approach, utilizing concurrent subagents to handle exploration, implementation, and merging tasks. By managing worktrees and integration branches, it ensures that complex features are implemented systematically, reviewed, and finalized according to the project's issue tracking requirements.

What it does

  • Analyzes technical specifications and associated task graphs.
  • Orchestrates exploration subagents to gather necessary documentation or codebase insights.
  • Manages concurrent implementer subagents for parallel ticket execution.
  • Handles branch creation, merging, and integration branch maintenance.
  • Automates code review cycles to ensure quality before final submission.
  • Cleans up worktrees and finalizes ticket status in the issue tracker.

When to use it

  • When you have a defined technical specification and a set of linked implementation tickets.
  • When you need to manage complex, multi-step development tasks that require parallel execution.
  • When you want to ensure a consistent implementation process across multiple sub-tasks.
  • When you need to integrate code changes systematically into a main branch.

Advantages

  • Maximizes development speed through concurrent subagent execution.
  • Maintains a clean and organized repository state using worktrees.
  • Ensures all blocking relationships in a task graph are respected.
  • Provides a standardized process for code implementation and review.

Usage examples

“Implement the spec for the new user authentication module.”
The agent reads the spec and tickets, initializes an integration branch, and begins spawning concurrent subagents to implement the required authentication features.
“Finish the remaining tickets for the API refactor.”
The agent identifies the current frontier of the task graph, assigns implementer subagents to the remaining tickets, and merges the results into the integration branch.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/mattpocock/implement-spec/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip implement-spec.zip -d .agents/skills

Documentation by Matt Pocock

You have been provided a spec. This spec should have tickets associated with it, describing how to implement the spec.

The issue tracker should have been provided to you. If not, tell the user to run /setup-matt-pocock-skills.

The goal is the entire spec implemented on a single integration branch, with every ticket resolved the way the issue tracker closes work.

The tickets are not a list of steps. They are a task graph with blocking relationships between them. This means there is always a frontier of tickets which are ready to be grabbed.

Start every subagent with a fresh context window.

Communication to and from subagents should be sparse. Communicate primarily through context pointers: to the spec, tickets, research notes, and previous commits. Don't duplicate information already available via pointers.

Implementer subagents should be run in the background where possible for maximum concurrency.

Steps

  1. Read the spec and tickets to understand the task graph.

  2. (optional) Use an exploration subagent to conduct any exploration required by the tickets - relevant codebase files or external documentation. Ensure the exploration subagent can save files - it should save its markdown notes in a directory outside the repo, accessible by all future subagents. This lets implementer subagents focus on implementation rather than exploration.

  3. Create the integration branch. If the issue tracker closes work through PRs, or the user asks for one, open a draft PR after the first merge in step 5 (a branch with no commits ahead of main can't open one), marked as closing the spec and tickets.

  4. Use a fresh implementer subagent for each ticket, each in its own worktree on its own branch. Each implementer subagent:

    • confirms its worktree is based on the integration branch before starting, and resets onto it if not;

    • calls the Skill tool with tdd to build the ticket;

    • merges the integration branch tip into its own branch before reporting done

  5. Once an implementer subagent completes, merge its work to the integration branch with a merger subagent.

  6. If this changes the frontier of available tickets, kick off more implementer subagents to work on the new tickets. This allows for maximum concurrency.

  7. Once all tickets are complete, call the Skill tool with code-review on the integration branch. Fix all issues raised by the code review in a single fresh implementer subagent.

  8. If a draft PR exists, mark it ready for review. Otherwise, resolve each ticket the way the issue tracker closes work, and report the integration branch.

  9. Clean up all implementer subagent worktrees.

Files

SKILL.md

You have been provided a spec. This spec should have tickets associated with it, describing how to implement the spec.

The issue tracker should have been provided to you. If not, tell the user to run /setup-matt-pocock-skills.

The goal is the entire spec implemented on a single integration branch, with every ticket resolved the way the issue tracker closes work.

The tickets are not a list of steps. They are a task graph with blocking relationships between them. This means there is always a frontier of tickets which are ready to be grabbed.

Start every subagent with a fresh context window.

Communication to and from subagents should be sparse. Communicate primarily through context pointers: to the spec, tickets, research notes, and previous commits. Don't duplicate information already available via pointers.

Implementer subagents should be run in the background where possible for maximum concurrency.

Steps

  1. Read the spec and tickets to understand the task graph.

  2. (optional) Use an exploration subagent to conduct any exploration required by the tickets - relevant codebase files or external documentation. Ensure the exploration subagent can save files - it should save its markdown notes in a directory outside the repo, accessible by all future subagents. This lets implementer subagents focus on implementation rather than exploration.

  3. Create the integration branch. If the issue tracker closes work through PRs, or the user asks for one, open a draft PR after the first merge in step 5 (a branch with no commits ahead of main can't open one), marked as closing the spec and tickets.

  4. Use a fresh implementer subagent for each ticket, each in its own worktree on its own branch. Each implementer subagent:

    • confirms its worktree is based on the integration branch before starting, and resets onto it if not;

    • calls the Skill tool with tdd to build the ticket;

    • merges the integration branch tip into its own branch before reporting done

  5. Once an implementer subagent completes, merge its work to the integration branch with a merger subagent.

  6. If this changes the frontier of available tickets, kick off more implementer subagents to work on the new tickets. This allows for maximum concurrency.

  7. Once all tickets are complete, call the Skill tool with code-review on the integration branch. Fix all issues raised by the code review in a single fresh implementer subagent.

  8. If a draft PR exists, mark it ready for review. Otherwise, resolve each ticket the way the issue tracker closes work, and report the integration branch.

  9. Clean up all implementer subagent worktrees.

Requirements and compatibility

Written for: Claude Code

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Claude Code frontmatter

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by
Matt Pocock
Publisher
Matt Pocock (Community)
Source
mattpocock/skills · skills/engineering/implement-spec · commit 4ae2317
Licence
MIT License (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Matt Pocock or Matt Pocock.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download implement-spec.zip