specdog
Official@specdog · United States
Feed the dog. Ship with specs. — DAG-first architecture by Justin DiClemente: .dog=human, .dag=agent
Agent Skills by specdog
Showing 17 vetted skills indexed across 1 GitHub repositories.
dag-agent
Configure, extend, and operate the Collar Agent CLI across platforms and providers.
test-driven-development
Enforces RED-GREEN-REFACTOR test-driven development workflow for writing tests before production code.
systematic-debugging
Diagnose software bugs through a four-phase root cause investigation workflow.
plan
Writes actionable markdown implementation plans with bite-sized tasks to .dag/plans/ without executing code.
intelligence-engine
Injects DAG ground truth and multi-call reasoning techniques into LLM calls via shell hooks.
subscription-oauth
Configures OAuth login for AI subscriptions to authenticate the Collar agent without API keys.
apple-reminders
Manage Apple Reminders from the terminal using the remindctl command-line tool.
macos-computer-use
Drive the macOS desktop with background screenshots, clicks, typing, and scrolling via the computer_use tool.
imessage
Send and read iMessage and SMS messages via the imsg CLI on macOS.
findmy
Track Apple devices and AirTags via FindMy.app using AppleScript and screenshots.
apple-notes
Create, search, edit, and export Apple Notes via the memo CLI on macOS.
github-auth
Configures GitHub authentication via HTTPS tokens, SSH keys, or gh CLI login.
github-repo-management
Manage GitHub repositories, releases, secrets, and Actions workflows via gh CLI or REST API.
github-pr-workflow
Automates the GitHub pull request lifecycle from branch creation through CI monitoring and merge.
github-code-review
Review local git diffs and GitHub pull requests with inline comments via gh or REST API.
github-issues
Create, triage, label, and manage GitHub issues via gh CLI or REST API.
codebase-inspection
Inspect repositories with pygount to report LOC, language breakdown, and code-to-comment ratios.
Frequently Asked Questions About specdog
FAQPage SchemaWhat tasks can I accomplish with specdog's skills?▼
You can manage the full GitHub lifecycle (auth, repos, PRs, code review, issues), enforce TDD and systematic root-cause debugging, write structured implementation plans, control the macOS desktop and Apple apps (Reminders, Notes, iMessage, FindMy), measure codebases with pygount, and amplify reasoning via Tree-of-Thought, Reflexion, and DSPy techniques.
Who are specdog's skills designed for?▼
Developers and power users running Collar Agent (dag-agent) who want spec-driven, DAG-first development. macOS users gain desktop control and Apple ecosystem integration, while cross-platform engineers on Linux, macOS, and Windows get GitHub operations, TDD enforcement, debugging, and planning capabilities.
How do I install and run specdog's skills?▼
Skills load through the Collar Agent (dag-agent) skill system on Linux, macOS, or Windows. Certain skills require prerequisite binaries: remindctl for Apple Reminders, imsg for iMessage, memo for Apple Notes, and pygount for codebase inspection. Apple ecosystem skills are macOS-only.
Are specdog's skills free and open source?▼
Yes. Nearly all skills carry the MIT license, authored by Collar Agent with several adapted from obra/superpowers. The subscription-oauth skill lets you use existing ChatGPT, Claude, Gemini, Grok, or Qwen subscriptions via OAuth login instead of purchasing separate API keys.
What prerequisites and dependencies do the skills need?▼
Most skills need only the dag-agent runtime. GitHub skills use the gh CLI or REST with HTTPS tokens or SSH keys. macOS skills require remindctl, imsg, or memo binaries. Codebase inspection requires pygount. The intelligence-engine skill uses dag hooks to apply frontier reasoning techniques.