IM

implement-spec

Implements technical specifications from local plan files by following architecture guidelines.

Install

mkdir -p .claude/skills/implement-spec && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/7456" && unzip -o skill.zip -d .claude/skills/implement-spec && rm skill.zip

Installs to .claude/skills/implement-spec

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Implement a spec from the plans directory
41 charsno explicit “when” trigger
Advanced

Key capabilities

  • Load specification files from plans
  • Read layered architecture documentation
  • Break down tasks via TodoWrite
  • Implement features following style guides

How it works

Parses YAML/Markdown specifications to generate a sequence of implementation tasks, cross-referencing against architectural documentation to maintain code hierarchy.

Inputs & outputs

You give it
Path to specification file
You get back
Implemented feature code with tests

When to use implement-spec

  • Implementing low-level PDF manipulation logic
  • Creating high-level feature adapters
  • Writing tests for new architectural specs

About this skill

You are implementing a specification from the .agents/plans/ directory. Work autonomously until the feature is complete and tests pass.

Your Task

  1. Determine the spec - Based on the conversation context, identify which spec file in .agents/plans/ to implement. Ask the user if multiple specs exist or if unclear.
  2. Read the spec - Load the identified specification file
  3. Read ARCHITECTURE.md - Understand the project's layered architecture and how your feature fits into the high-level/low-level API structure
  4. Read CODE_STYLE.md for formatting conventions
  5. Plan the implementation using the TodoWrite tool to break down the work
  6. Implement the feature following the spec and code style
  7. Write tests for all new functionality
  8. Run tests and fix any failures
  9. Run typecheck and lint and fix any issues

Implementation Guidelines

Before Coding

  • Understand the spec's goals and scope
  • Identify the desired API from usage examples in the spec
  • Review related existing code to understand patterns
  • Consult ARCHITECTURE.md - Determine which layer(s) your feature belongs to and how it fits into the overall structure
  • Break the work into discrete tasks using TodoWrite

Architecture Patterns

Most features should implement both low-level and high-level variants:

Low-level first:

  • Direct manipulation of PDF COS objects (PdfDict, PdfArray, PdfStream)
  • Core functionality without ergonomic abstractions
  • Typically in src/core/ or appropriate layer directory

High-level adapter:

  • User-friendly methods on main classes (PDF, PDFPage, etc.)
  • Validates inputs, provides defaults, handles edge cases
  • Delegates to low-level implementation

Example structure:

src/
├── core/
│   └── shading.ts          # Low-level: PdfStream creation
└── api/
    └── page.ts             # High-level: page.drawGradient()

During Implementation

  • Follow CODE_STYLE.md strictly (2-space indent, double quotes, braces always, etc.)
  • Use #src/* import alias for internal imports
  • Co-locate tests as *.test.ts files
  • Write tests as you go, not at the end
  • Mark todos complete as you finish each task
  • Commit logical chunks of work

Code Quality

  • No stubbed implementations or skipped tests
  • Handle edge cases and error conditions
  • Include descriptive error messages with context
  • Use async/await for all I/O operations

Testing

  • Write tests first when practical (TDD)
  • Test happy paths and edge cases
  • Test error conditions
  • Use fixtures from fixtures/ directory with loadFixture()

Autonomous Workflow

Work continuously through these steps:

  1. Implement - Write the code for the current task
  2. Test - Run bun run test to verify
  3. Fix - If tests fail, fix and re-run
  4. Typecheck - Run bun run typecheck
  5. Lint - Run bun run lint:fix
  6. Repeat - Move to next task

Stopping Conditions

Stop and report success when:

  • All spec requirements are implemented
  • All tests pass
  • Typecheck passes
  • Lint passes

Stop and ask for help when:

  • The spec is ambiguous and you need clarification
  • You encounter a blocking issue you cannot resolve
  • You need to make a decision that significantly deviates from the spec
  • External dependencies or fixtures are missing

Commands

bun run test                    # Run tests in watch mode
bun run test:run                # Run tests once
bun run test -- --grep "pattern" # Run specific tests
bun run typecheck           # Type check
bun run lint:fix            # Fix lint issues

Begin

Identify the spec file from the conversation context, read it along with CODE_STYLE.md, then start implementing. Use TodoWrite to track your progress throughout.

When not to use it

  • Task definition or exploratory design
  • Non-layered architecture projects

Prerequisites

Plans directory containing specsProject architecture documentation

Limitations

  • Requires clear spec files
  • Dependent on existing architecture patterns

How it compares

It enforces strict architectural compliance (low-level vs high-level APIs) defined in project-specific docs.

Compared to similar skills

implement-spec side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
implement-spec (this skill)16moReviewAdvanced
software-architecture3336moNo flagsIntermediate
codex322moReviewAdvanced
game-development706moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

software-architecture

davila7

Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development.

333868

codex

Lucklyric

Invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. This skill should be invoked when users explicitly mention "Codex", request complex implementation challenges, advanced reasoning, or need high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.

32238

game-development

davila7

Game development orchestrator. Routes to platform-specific skills based on project needs.

70195

senior-fullstack

davila7

Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project scaffolding, code quality analysis, architecture patterns, and complete tech stack guidance. Use when building new projects, analyzing code quality, implementing design patterns, or setting up development workflows.

35110

command-name

anthropics

This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.

697

python-project-structure

wshobson

Python project organization, module architecture, and public API design. Use when setting up new projects, organizing modules, defining public interfaces with __all__, or planning directory layouts.

860

Search skills

Search the agent skills registry