browser-automation
Browser automation for rendered UI exploration, validation, screenshots,
Use when planning, executing, checkpointing, finishing, or inspecting
$ npx -y skills add alexei-led/cc-thingz --skill spec-flow --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/spec-flowContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when planning, executing, checkpointing, finishing, or inspecting
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 spec loop for controlled task-by-task work.
Loop: plan one slice → execute one task → checkpoint or close → repeat.
`specctl` owns state. Do not edit task status or `.spec/SESSION.yaml` by hand.
Task states: `todo`, `in-progress`, `done`.
New project:
scripts/specctl init
Then plan the first executable slice. Do not build a full backlog unless the user asks.
Existing project:
1. Inspect current code and project instructions. 2. Create the smallest task that can be verified. 3. Link optional REQ/EPIC context only when it reduces ambiguity.
Stop and resume:
scripts/specctl checkpoint --message "<where to resume>" scripts/specctl session handoff
Iterate:
scripts/specctl ready scripts/specctl start TASK-<id> # implement + verify scripts/specctl done TASK-<id> --summary "..." --tests "..."
Use when the user asks for status, next task, resume, health, or what to do next.
scripts/specctl status scripts/specctl ready scripts/specctl session handoff scripts/specctl validate
Report active session, next ready task, validation issues, and the smallest next action.
Use when the user has an idea, requirement, bug, or project gap and wants an executable plan.
1. Run `scripts/specctl init`. 2. Check status/session before changing files. 3. Ask 3-5 questions only if the slice is unclear. 4. Optionally scan the codebase for relevant files and patterns. 5. Draft the smallest useful artifact set:
6. Show the proposed plan; obtain approval if the user has not already authorized that scope. 7. Write with `scripts/specctl new task <slug>` when possible, then edit details. 8. Run `scripts/specctl validate` and `scripts/specctl ready`.
Do not write implementation code in plan files.
Use when the user wants to work, continue, or implement a task.
1. Run `scripts/specctl status` and `scripts/specctl session show`. 2. Resume an existing matching session when the user asks to continue. Ask before replacing a conflicting session. 3. Select with `scripts/specctl ready` or verify the named task with `scripts/specctl show TASK-<id>`. 4. Start with `scripts/specctl start TASK-<id>`. 5. Make a short implementation plan; obtain approval if that implementation scope is not already approved. 6. Implement only the approved task. 7. Run project-appropriate checks from project instructions and changed files. 8. Show scoped diff or `scripts/specctl session handoff` before close. 9. Close with `scripts/specctl done ...` or checkpoint with `scripts/specctl checkpoint`.
Use when the user stops, switches context, or finishes.
Checkpoint:
scripts/specctl checkpoint --message "<where to resume>"
Close:
scripts/specctl done TASK-<id> \ --summary "<what changed>" \ --tests "<checks passed or not run: reason>" \ --files "<changed files or none>" \ --commits "<sha or none>"
`specctl done` needs `--summary` and `--tests` unless the user explicitly approves `--force`. These fields record the caller's evidence; the helper does not execute or certify checks. Name commands and results honestly, including skip reasons, and satisfy project gates before closing.
## 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.
Repo: alexei-led/cc-thingz
Browser automation for rendered UI exploration, validation, screenshots,
Support-only Playwright runtime/reference for browser-automation — dev-server
Create normal git commits with logical grouping. Use when committing,
Create or update human-facing docs, agent-facing instructions, architecture
Fix code defects with a reproducible feedback loop, root-cause diagnosis,
Improve test design, speed, and coverage with behavior-focused tests,