Skill reviews

Lesson 2.4: GitHub. Use when the student types /start-2-4.

• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill
• Does not say what the process needs to start

Lesson 4.4: GitHub. Use when the student types /start-4-4.

• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill
• Does not say what the process needs to start

4.4 GitHub. Use when the student types /start-4-4.

• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill
• Does not say what the process needs to start

Module 3.4: GitHub. Saves the quiz project to GitHub.

• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill
• Does not say what the process needs to start

Debug Java applications systematically: JDWP remote debugging, jdb, VS Code and IntelliJ attach, debugging Maven/Gradle tests, Spring Boot and Quarkus dev mode, containers, breakpo

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Prepare payloads, run and monitor the Autonomous Vehicle Dataset Generation Airflow workflow, and inspect results for driving-clip retrieval and Cosmos3-Nano variants. Existing cli

• References files that are not bundled: ../cdf-video-data-augmentation/SKILL.md, ../cdf-event-video-generation/SKILL.md, ../../docs/autonomous-vehicle-dataset-generation/payload-guide.md
• The skill tells the model to perform an irreversible action with no human approval
• No test case covers injection arriving through data

Generate synthetic PCB inspection images on Kubernetes with the SMT Defect Image Generation (DIG) DAG in CDF Orchestration. The DAG renders components in simulation, turns the rend

• References files that are not bundled: ../cdf-orchestration-setup/SKILL.md
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (11 tags): a typed call is more reliable

Run the CDF Orchestration Event Video Generation DAG on Kubernetes or OSMO - image-to-video anomaly generation, auto-labeling, and anomaly dataset generation. Select for requests a

• References files that are not bundled: ../cdf-orchestration-setup/SKILL.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval

Build the native MSIX isolated-session Gateway from npm latest, a published packaging release with -GatewayChannel Packaged, or explicit openclaw sources. Register it beside the St

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (12 tags): a typed call is more reliable

Run complete OpenClaw Windows Node issue and PR triage, including landing queues, proof pools, ownership audits, and release planning.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 15 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Use the OpenClaw Windows app's local MCP server and winnode CLI for development, debugging, proof, and automation.

• References files that are not bundled: ../openclaw-proof-validation/SKILL.md, ../../../docs/GATEWAY_FIXTURE_TESTING.md, ../winnode/SKILL.md
• The skill tells the model to perform an irreversible action with no human approval
• 6 referenced file(s) missing: ../openclaw-proof-validation/SKILL.md, ../../../docs/GATEWAY_FIXTURE_TESTING.md, ../winnode/SKILL.md

Export Claude Code, Codex, and other coding-agent conversation history to Hugging Face. Use when the user asks about exporting conversations, uploading to Hugging Face, configuring

• The skill tells the model to perform an irreversible action with no human approval
• 15 mutating operations with no state check
• Says nothing while it works

End-to-end methodology for reproducing AND patching publicly disclosed, already-fixed vulnerabilities: sourcing the advisory and the fix commit, reading the patch diff, rebuilding

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma fr

• References files that are not bundled: ../figma-use/SKILL.md, ../figma-code-connect/SKILL.md, ../figma-use/references/variable-patterns.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval

Triage open GitHub issues and discussions on the Jarvis repo. Sweep for untriaged reports, reply to awaiting-user threads when new info lands, apply the right labels, close duplica

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Use this skill for planning, testing, and safely executing PostgreSQL schema migrations — especially when working with production data or shared databases. **Trigger when user ask

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

AI DevKit · Smoke-test the user flows a change affects (CLI, API, UI) end to end with a disposable sandboxed script against the real app. Use before calling a feature or fix done,

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

AI DevKit · Test-driven development — write a failing test before writing production code. Use when implementing new functionality, adding behavior, or fixing bugs during active de

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/. Use whenever the user mentions a goal, objective, target, milestone, or asks to track progr

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (14 tags): a typed call is more reliable
• Does not say what the result is

When provisioning, setting a limit, or committing an estimate under uncertainty, size a buffer to residual error and the cost of breach—not to the optimistic edge.

• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill
• Does not say what the process needs to start

Ship a JS/TS-only change to the already-installed SUB/WAVE app (the Expo project in `app/`) over-the-air via EAS Update — no new TestFlight/Play build, no store round-trip. Use thi

• References files that are not bundled: ../../../app/docs/RELEASE.md
• The skill tells the model to perform an irreversible action with no human approval
• 1 referenced file(s) missing: ../../../app/docs/RELEASE.md

Verify the Cua Driver daemon and CLI/MCP desktop tools against real fixture apps after driver changes, using Linux diagnostics, AX-first actions, side-effect checks, and retained e

• References files that are not bundled: scripts/ci/linux/run-rust-e2e-wayland.sh, scripts/ci/linux/run-rust-e2e.sh
• The skill tells the model to perform an irreversible action with no human approval
• 2 referenced file(s) missing: scripts/ci/linux/run-rust-e2e-wayland.sh, scripts/ci/linux/run-rust-e2e.sh

Scaffold, extend and deploy Shopify embedded apps on Firebase with Nitrogen. Use for a Shopify app on Cloud Functions, Firestore and Hosting, or inside a Nitrogen project.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Publish a website or share files at a live URL in seconds with no account, then let the person claim it, edit it over Webly's MCP server, and publish drafts they approve.

• References files that are not bundled: scripts/webly.mjs
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 top-level sections: this looks like several domains in one skill

Only use when the user explicitly invokes this skill by name.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start