- 📁 agents/
- 📁 assets/
- 📁 references/
- 📄 SKILL.md
Inspect external prediction model implementations and adapt them to EasyTSF task contracts. Use when the user provides model code, class definitions, forward logic, or config fragments and wants Codex to classify the target task as `sequence_prediction`, `graph_prediction`, or `grid_prediction`, determine the current repository fit, and produce either a direct adaptation plan or a repository extension plan.
This skill should be used when the user asks to "set up OpenClaw", "get started", "onboard me", "plan my setup", or "help me choose channels". Conducts an interactive interview, then generates a tailored deployment plan.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
- 📁 demos/
- 📁 docs/
- 📁 references/
- 📄 .gitignore
- 📄 check-doc-sync.py
- 📄 README.md
Use when someone wants to CREATE or BUILD a slide deck, presentation, or 幻灯片/PPT/演示文稿 — from scratch, from notes, from a Word/PPTX file, or from an approved outline. Handles Chinese and English equally. Covers pitch decks, product launches, team standups, conference talks, capstone presentations, style previews, and converting existing files to web slides. Use for --plan (outline) and --generate (HTML from plan) flags. Does NOT apply to exporting finished HTML to PPTX/PNG (use kai-html-export), writing speeches, or non-slide documents.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Use inside the plan plugin when the user wants to execute an existing implementation plan, continue from the authoritative Linear issue plan, or resume work after leaving Plan mode. Consumes the routed Linear issue identity plus the canonical linked-document `tracked-plan/1`, requires valid tracked-plan and plan-event helpers before execution, updates only tracked-plan runtime state, and appends validated progress events instead of inferring authority from chat.
Converts a Lousy Agents spec or master plan into a structured Beads (bd) dependency graph of epics and tasks. Use when asked to 'convert plan to issues', 'create beads from spec', 'populate beads', 'plan to graph', or 'break down spec into tasks'.
Use when you have a written plan and want it reviewed for architecture, scope, and test coverage before execution. Use when the user says "review this plan", "autoplan", "check my plan", "is this plan solid", or before running superpowers:executing-plans or superpowers:subagent-driven-development.
Independent plan/spec reviewer — reads a plan file, verifies claims against the workspace, and returns a structured verdict with findings. Supports external judges (Codex, OpenAI, etc.) or runs inline.
Analyzes ADU permit corrections letters — the first half of the corrections pipeline. Reads the corrections letter, builds a sheet manifest from the plan binder, researches state and city codes, views referenced plan sheets, categorizes each correction item, and generates informed contractor questions. This skill should be used when a contractor receives a city corrections letter for an ADU permit. It coordinates three sub-skills (california-adu for state law, adu-city-research for city rules, adu-targeted-page-viewer for plan sheet navigation) to produce research artifacts and a UI-ready questions JSON. Does NOT generate the final response package — that is handled by adu-corrections-complete after the contractor answers questions. Triggers when a corrections letter PDF/PNG is provided along with the plan binder PDF.
Multi-agent development workflow using Agent Teams. Supports five modes: plan (architect teammate + PM teammate debate → plan.md), dev (developer teammate + code-tester teammate + qa-tester teammate + reviewer teammate iterate → code), full (plan → approval gate → dev), auto (plan → dev, no gate), and bugfix (tester + developer + reviewer TDD triad → fix + PR). Use when tasks benefit from collaborative agent teammates with peer messaging.
