epic-dev
25neuromechanist/research-skills
Command
Part of project
Epic/sprint development workflow with git worktrees, GitHub issues, and phased delivery.
269 tagged copilot, measured the same way as everything else here.
Browse within: copilot-cli 40development 33engineering 33prd 33spec 33agentic-coding 27copilot-enabled 27agentic-rag 16llm-commands 16astro 13github-copilot 13plugin 13rules-for-ai 13spec-driven-development 13
neuromechanist/research-skills
Command
Part of project
Epic/sprint development workflow with git worktrees, GitHub issues, and phased delivery.
neuromechanist/research-skills
Command
Part of project
Show current epic/sprint workflow state.
neuromechanist/research-skills
Command
Part of project
Prepare a project release with version bump, changelog, and validation.
Command
Part of agent-decision-record
Trigger/Process/Rules sections below (Claude Code skills need self-contained instructions and can't just point at another file) — keep the two in sync. tools/claude-code/README.md links here rather than keeping its own copy. -->.
Command Claude Code
You are Orchestrator, the autonomous operations manager for this project. You coordinate AI agent roles to execute tasks with minimal CEO involvement.
Command
Create comprehensive Architecture Decision Records (ADRs) that systematically document architectural decisions with clear rationale, alternatives considered, and consequences through a structured analysis and review process.
Command
Generate comprehensive feature specifications using a contract-first approach that ensures complete alignment between developer and AI before creating any supporting files. This command eliminates presumptuous file creation by establishing a clear "contract" through structured clarification rounds.
Command
Execute a specific task and its sub-tasks systematically following a Test-Driven Development (TDD) workflow. This command reads task specifications from .code-captain/specs/ directories and implements features with comprehensive testing, following established code standards and best practices.
Command Claude Code
A Stripe Checkout implementation takes four steps.
Command Claude Code
Here's how environment variables are managed in this application.
Command Claude Code
Command "standalone-python-scripts" from iloveitaly/llm-ide-rules, covering standalone python scripts, /// script, requires-python = ">=3.13", dependencies = [] and ///.
Command ✓ vendor
Command "speckit.assess.decide" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the decide stage.
Command ✓ vendor
Command "speckit.assess.define" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the define stage.
Command ✓ vendor
Command "speckit.assess.intake" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the intake stage.
Command
Enable shell tab completion for OASR commands, subcommands, and dynamic resources (skills, agents, profiles).
Command
Command "CONFIG" from JordanGunn/oasr, covering oasr config, quick reference, usage, subcommands and config set.
Command
Execute skills as CLI tools from anywhere on your system. Run skills with agent-driven execution without needing to clone them first.
Command Claude Code
Look at the current git diff and generate an appropriate conventional commit message.
Command Claude Code
Fetch the current PR diff and provide a thorough code review.
Command Claude Code
Part of code-quality
Format code according to project style.
Command
Part of tech-debt-mcp
Analyze a single source file for technical debt and print a line-numbered issue table of findings sorted by severity.
Command
Part of tech-debt-mcp
Scan a project directory for technical debt across all supported languages and print a prioritized summary of findings.
Command
Part of tech-debt-mcp
Print an aggregate debt summary (health score, SQALE rating, issue counts, remediation estimate) for a project without listing individual findings.
Command
Auto-commit changes after a Spec Kit command completes.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: