browser-automation
Browser automation for rendered UI exploration, validation, screenshots,
Use when planning, executing, checkpointing, finishing, or inspecting
Claude Code
$ npx -y skills add alexei-led/cc-thingz --skill spec-flow --agent claude-code
Codex
$ npx skills add alexei-led/cc-thingz --skill spec-flow -a codex -y
Cursor
$ npx skills add alexei-led/cc-thingz --skill spec-flow -a cursor -y
Gemini CLI
$ npx skills add alexei-led/cc-thingz --skill spec-flow -a gemini-cli -y
GitHub Copilot
$ npx skills add alexei-led/cc-thingz --skill spec-flow -a github-copilot -y
OpenCode
$ npx skills add alexei-led/cc-thingz --skill spec-flow -a opencode -y
Windsurf
$ npx skills add alexei-led/cc-thingz --skill spec-flow -a windsurf -y
description: Use when planning, executing, checkpointing, finishing, or inspecting lightweight spec-driven work. Runs one task at a time using `.spec/` markdown files and the bundled `specctl` helper. NOT for broad product discovery beyond a short requirement interview. NOT for generic implementation planning that does not read or write `.spec/` files. name: spec-flow
Lightweight loop for controlled work, one task at a time: plan one slice, execute one task, checkpoint or close, repeat.
`scripts/specctl` (written `specctl` below) owns state. Do not edit task status or `.spec/SESSION.yaml` by hand. `references/specctl-commands.md` lists every command. `references/method.md` covers task quality, templates, the planning output, and the mini-interview.
Task states: `todo`, `in-progress`, `done`.
For status, the next task, resume, or health: run `specctl status`, `ready`, `session handoff`, and `validate`. Report the active session, the next ready task, validation issues, and the smallest next action.
For an idea, requirement, bug, or project gap that needs an executable plan. Done when the smallest useful artifact set exists and passes `specctl validate`, and its first task appears in `specctl ready` (a REQ-only plan has no ready task yet). Create tasks and requirements with `specctl new task|req`, then fill in the details; write an `EPIC-*` file by hand. Pick the smallest set:
Run `specctl init` when `.spec/` is missing, and check status and session before changing files. In an existing project, read the code and project instructions first, and link REQ or EPIC context only when it reduces ambiguity. Ask questions only when the slice is unclear. Show the proposed plan before writing it unless the user already authorized that scope. Build a full backlog only on request, and keep implementation code out of plan files.
For work, continue, or implement. Done when the relevant build/test/lint checks pass on what you changed, or you name each check that did not run and why. Before closing, confirm the acceptance criteria and show the scoped diff or `specctl session handoff`; if the task cannot finish, checkpoint it instead.
session when the user asks to continue; ask before replacing a conflicting one.
then `specctl start TASK-<id>`.
Implement only this task; file follow-up tasks instead of widening scope.
project has `make`.
Checkpoint before stopping or switching context:
scripts/specctl checkpoint --message "<where to resume>"
Close a finished task:
scripts/specctl done TASK-<id> \ --summary "<what changed>" \ --tests "<checks passed, or not run: reason>" \ --files "<changed files or none>" \ --commits "<sha or none>"
`--summary` and `--tests` are required unless the user approves `--force`. They record your evidence; `specctl` does not run or certify checks. Name the commands and results, including skip reasons such as `--tests "not run: docs-only task"`.
Approval covers the agreed plan and implementation scope; do not ask again at each mechanical step. Ask when scope changes, before using `--force`, or before clearing a conflicting session.
## Spec flow Mode: orient | plan | execute | checkpoint | close Task: <TASK-id or none> Status: <ready | in-progress | checkpointed | done | blocked> Evidence: <commands/tests/checks or skipped reason> Next: <one command or action>
Portable skills, agents, hooks, and Pi-native extensions for Claude Code, Codex CLI, GitHub Copilot, Cursor, Grok, and Pi. Gemini is retired.
Browser automation for rendered UI exploration, validation, screenshots,
Create normal git commits with logical grouping. Use when committing,
Write, rewrite, or update project docs from implementation facts - README
Fix code defects with a reproducible feedback loop, root-cause diagnosis,
Improve test design, speed, and coverage with behavior-focused tests,
Prepare, publish, or repair a software release and write its release notes. Use for cutting a versioned release or editing…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.