Skill Claude CodeCodex
Drive the machine Chrome debug browser via OpenClaw-managed MCP (chrome-devtools). Use for page navigation, snapshots, screenshots, clicks, forms, console/network inspection — not for host shell risk.
Skill Claude CodeCodex needs its repo
A set of rules for handling development work in approved repositories, including when to use the main branch or a separate worktree, which is an isolated copy of a repository.
Skill Claude CodeCodex
Full error closed-loop for Dex (Main): diagnose, safe self-fix, verify, report; platform Exec failed handling; escalation with options. Load when handling failures or writing failure reports.
Skill Claude CodeCodex needs its repo
Host shell MUST go through claw-run (gate then exec). Three layers: rules → Grok re-check → human only if still danger. Prefer claw-run over bare exec. Also: exec hygiene — short shell, scripts on disk via claw-script-run (no fragile python -c / node -e), split chains, gateway self-update only via detached unit.
Skill Claude CodeCodex
Host ↔ Claw Session Adapter Kit: list/capture host tmux panes, list/tail OpenClaw sessions, poke agent turns, lease-gated host-send-keys, bot-send, optional say-as-me, take/watch poller for focused-pane handoff. Use for Feishu/host interop — not a second TUI.
Skill Claude CodeCodex needs its repo
Ledger development tasks to Feishu Base via dev-task-ledger.sh. Write roots from /.openclaw/tasks-allowlist.json (per agent). Use on accept/confirm/close of coding/ops work; not for pure Q&A.
Skill Claude CodeCodex needs its repo
A multi-role code-review process that searches for problems, tries to disprove the proposed changes, and reproduces issues in a sandbox. Different agents or backends can take part in the review.
Skill Claude CodeCodex needs its repo
A brainstorming workflow that uses several independent viewpoints, then challenges and combines the resulting ideas. It is intended for open-ended questions where you want options.
Skill Claude CodeCodex
Engineer judgment for concrete problems: evidence → options → decision → verify → mine transferable practice. Routes real capabilities when needed and distills design decisions + personal preferences. Load for adjudication, multi-option recommendations, or end-of-task experience capture. Not idea divergence…
Skill Claude CodeCodex
A workflow for sending work tickets between separate code repositories. It lets an agent create a ticket for another project, then lets the receiving project list, claim, question, answer, or close that ticket.
Skill Claude CodeCodex
Mandatory handoff when a human (not the agent) must run a script/command. Agent loads this skill, ensure-env, propose.sh --cwd (default --wait until x finishes), then the agent continues follow-up itself. Handoff script bodies must be non-blocking kickoffs (trigger/async ack) — never wait for CI/deploy inside x. Never…
Skill Claude CodeCodex
A repository hygiene audit and pre-commit gate for checking project files before a Git commit. Git is the system used to track code changes; the checks cover broken Markdown links, shell syntax, diagrams, possible secrets, and line-size limits.
Skill Claude CodeCodex needs its repo
A procedure for resetting a long-lived Git worktree after its current round of work has been delivered. A worktree is another working directory connected to the same Git repository; this procedure checks it, resets it to the latest main branch, and performs project setup for the next task.
Skill Claude CodeCodex
Produce a stable personal development-habit weekly report from WezDeck observability: pane-scoped agent concurrency, Claude/Grok/Codex skills+slash+CLI+MCP, CDP verify→iterate, hotkey intensity (Alt+l etc.), optional WakaTime summaries, and optional push to a private habit archive repo. Default window is the previous…
Skill Codex
Operate the WezDeck runtime environment: run the read-only environment and dependency checks, then synchronize this repository's WezTerm runtime. Reuse a valid cached target from repo-root .sync-target or WEZTERMSYNCTARGET when available; otherwise list candidate homes, confirm one with the user, and run the…
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: