Explore skills

Guidelines for creating and updating Claude Code skills. TRIGGER when: writing a new SKILL.md, modifying an existing skill, or the user asks about skill conventions.

Install and configure `agent-browser` on a Windows machine with WSL2 after a browser path is already working. Use when a user wants the `agent-browser` CLI, its downloaded runtime, the `vercel-labs/agent-browser` repository, or an `agent-browser` attachment to a Windows host browser bridge from WSL2.

Access OpenAI Codex CLI conversation history to continue work started in Codex, or to find a past Codex chat by topic or keyword. Use when the user says "codex history", "continue from codex", "what was I doing in codex", "pick up from codex", "codex session", "find the codex chat about X", or wants to resume or locate a task that was started in Codex CLI.

Turn macOS caffeinate sleep prevention on or off, check its status, or explain the launchd-backed setup. Use when the user says to enable, disable, start, stop, toggle, inspect, or troubleshoot caffeinate / coffee Nate / keep-awake behavior for local terminal, Codex, Claude Code, or other agent workflows.

Troubleshoot and operate OpenClaw browser on local or remote gateways. Use when Codex needs to enable the bundled browser plugin, resolve `pairing required` or device approval errors, choose between the managed `openclaw` profile and the attached `user` profile, handle Linux headless or Chrome CDP startup failures, or prove browser control with `profiles`, `start`, `open`, `snapshot`, and `screens

Troubleshoot Arthur's Dell P2725DE/P2225D monitor setup, especially DisplayPort daisy chaining, "No DP signal from your device" on the P2225D, Windows Fast Startup or shutdown-related display breakage, and reset/reinstall steps for a Lenovo laptop or Dell desktop tower using original Dell cables.

Ingest the live documentation manual into the ontology as ground-truth Doc nodes, then enrich them with doc→ontology DESCRIBES links. Runs the mechanical doc extractor (docs-ingest → doc-nodes.jsonl, split by heading/anchor, prose referenced from ../documentation), rebuilds the graph (embeds the doc prose), spawns the doc-analyser subagent per un-enriched page (live-URL verification + DESCRIBES to

Run the methodology meta-review — a single methodology-reviewer agent that traces the whole current methodology (APPROACH.md, the ADRs, the agent contracts, the skills, the playbooks, the case-law, the live artefacts), diffs against the prior review, runs fresh blind spot-checks against real source, and emits real gaps + improvement proposals at lineage/{repo}/meta-reviews/{date}/review.md. `/pane

Run one or more dynamic-verification probes against a local ephemeral docker-compose mirror of the target system. Captures observation traces as committed artefacts at `lineage/{repo}/probe-runs/{date}-{probe_id}.yaml` and merges measured values back into `feature-flows.yaml`, `test-map.yaml`, and per-sidecar `confidence_per_field` annotations. Local-only execution per APPROACH.md section 5 rule 1

Run the test-coverage-mapper reducer subagent over the per-node enrichment sidecars + actual test files in the target repo. Verifies sidecar-claimed test files exist; surfaces uncovered behaviours as TEST-GAP-NNN candidates ranked by node criticality (anchored on concepts.yaml's security/performance aggregates); cross-references with `doc-gaps.md` for double-jeopardy findings (undocumented AND unt

第二步：为 refs/ 下的参考书籍建立章节索引。调用方式：/index-book <book-id>

Generate clean architecture and system-design diagrams as SVG files. Use this skill whenever the user wants to visualise how services, systems, or components connect: migration diagrams, current-state vs target-state architectures, integration maps, data-flow diagrams, platform overviews, or any diagram that shows technology boxes with arrows between them. Triggers on phrases like: "draw a diagram