2,427 tagged spec-driven-development, measured the same way as everything else here.
Browse within: github-copilot 43ai-development 36workflow 36vscode-extension 30speckit 27claude-code-hooks 26parallel-agents 25kiro 24steering 24akka 22bmad-method 22claude-code-plugins 22gemini-ai 22ai-sdlc 20
Agent
Coordinate parallel execution of independent plan tasks. For single tasks — implements directly with quality sidecars. For parallel tasks — dispatches implement-worker workers. Use via claude --agent implement-coordinator.
Agent
Iteratively polish a plan by launching plan-polisher in a loop until critique passes or max iterations reached. Use via claude --agent plan-coordinator.
Agent
Create or refresh an /aif-plan plan, critique it, and run one refinement round at most. The caller launches another plan-polisher for further iterations if needed.
zhu1090093659/spec_driven_develop
Instructions file CodexOpenCode
Instructions for zhu1090093659/spec_driven_develop, covering project agent instructions, scope, truth sources, development rules and validation.
zhu1090093659/spec_driven_develop
Instructions file
Instructions for zhu1090093659/spec_driven_develop: Read AGENTS.md first. It is the shared project-level instruction source for Codex, OpenCode, Cursor, Claude Code, and other Markdown-aware coding agents.
zhu1090093659/spec_driven_develop
Plugin Claude Code
Three complementary AI agent skills: (1) Spec-Driven Develop — automates full development workflow for large-scale complex tasks: project analysis, task decomposition, project governance, progress tracking, and execution; (2) Deep Discuss — structured deep discussion for problem analysis, brainstorming, and solution…
zhu1090093659/spec_driven_develop
Agent
Reviews one execution lane's diff against its per-task acceptance criteria, commits fixes directly to the lane branch, and returns a structured verdict to the orchestrator. Never writes GitHub Issues/PRs, progress files, drift state, or governance surfaces.
zhu1090093659/spec_driven_develop
Agent
Designs phased task decomposition and delivery batches for large-scale project transformations. Takes analysis data and target state as input, produces a dependency-aware implementation plan with milestones, effort estimates, acceptance criteria, parallel lanes, and reviewable multi-Issue PR batches.
zhu1090093659/spec_driven_develop
Agent
Executes a coherent delivery batch or one assigned lane from a phased plan. Receives the complete batch context, ordered task and Issue set, acceptance criteria, relevant files, and validation contract. Implements and commits the work, but leaves integration state, cumulative telemetry, and the single batch PR to the…
zhu1090093659/spec_driven_develop
Skill Claude CodeCodex
A structured discussion workflow for exploring a problem over several rounds before choosing a solution.
zhu1090093659/spec_driven_develop
Skill Claude CodeCodex
Findings-first code review workflow for AI coding agents. Use when the user asks to review uncommitted changes, commits in a date range, or a branch compared to the main branch / PR-style diff. Focuses on bugs, regressions, correctness risks, missing tests, security/data-safety issues, and other behavior-changing…
zhu1090093659/spec_driven_develop
Skill Claude CodeCodex
Automates pre-development workflow for large-scale complex tasks. Use when the user mentions "rewrite", "migrate", "overhaul", "refactor entire project", "transform", "rebuild in [language]", "spec-driven", or describes any large-scale project transformation that requires planning before coding. Also triggers on…
Plugin Claude Code
Spec-first workflow: integrates OpenSpec planning engine + Superpowers execution discipline. 9 collaborative skills with embedded TDD, SDD, code review, debugging, and delta spec sync.
Instructions file GitHub Copilot
Instructions for the exploring stage of the spec-superflow software-change workflow. At this stage, the agent can clarify needs and compare options but cannot create plans or implementation files.
Instructions file CodexOpenCode
Instructions for MageByte-Zero/spec-superflow, covering agents.md, what this is, commands, build typescript and run integration tests.
Instructions file Gemini CLI
A set of instructions for running the spec-superflow workflow, a step-by-step process for planning, building, reviewing, debugging, and closing a software change.
Hook
Runs when a session starts, running an inline shell check. From MageByte-Zero/spec-superflow.
Skill Claude CodeCodex
Govern implementation from an approved execution contract. Invoke when execution-contract.md is approved and the user wants disciplined build work, TDD execution, or guarded batch-by-batch implementation.
Skill Claude CodeCodex
Close out a spec-superflow change with verification, summary, and archive readiness. Invoke when implementation is complete, verification is underway, or the user asks for a final wrap-up.
Skill Claude CodeCodex
Primary entry point for the spec-superflow state-machine workflow. Invoke when the user is inside an active spec-superflow change directory (look for .spec-superflow.yaml, changes/ /, proposal.md, specs/, design.md, tasks.md, or execution-contract.md) and asks to start, continue, resume, implement, plan, or figure out…
Command Claude Code
Create a branch. I am going to take a shower for the next 90 minutes and I need the next stage to be finished before I come back. All of the research, contracts, specification, plan, and tasks in .shotgun/ this directory is just specifications and example code. Second Explore the codebase to come up with a detailed…
Command Claude Code
make sure mypy and ruff checks pass, and that the pytest ONLY smoke tests pass. then get this up into a PR.
Command Claude Code
Review the current pull request to look for things like: Inline imports = We must remove these unless they are truly needed. dicts being returned by services/routers that should be Pydantic Models. Pydantic Model classes should be moved to a models.py file in the appropriate folder. Any leftover TODOs = We need to…
Instructions file
Instructions for shotgun-sh/shotgun, covering claude code instructions for shotgun, evals, writing eval test cases, architecture documentation and commit message convention.
At most 3 mods per repository are shown here — the rest are on their repository pages: