skills

Audit an existing CLI against cli-build: how well an agent can operate it and how well a human can read it. Use when the user wants to audit a CLI, check whether a tool is agent-first, find out what a published CLI got wrong, grade a CLI's human output, verify that named safety features are actually wired, or prepare a patch list before improving an existing command-line tool. Reports findings with evidence; it does not patch.

Design and build a CLI that an AI agent can operate safely and a human can supervise. Use when the user wants to build a CLI, wrap an API in a command-line tool, build a CRUD or local-first tool over a database or filesystem the user already owns, add --json or --dry-run to an existing CLI, design a trust ladder or approval gate for risky commands, wrap an async API so agents do not write their own poll loop, or decide how to distribute a CLI (npm, native binary, source). Runs on its own when the contract is yours to define; follows a surface-recon report when the target is someone else's service.

Generate OG images and favicon based on project branding. Use when: (1) user needs social media preview images for their project, (2) user wants to generate a favicon, (3) user is setting up branding assets for a website or app, (4) user has brand colors and wants professional-looking Open Graph images. Automatically generates correctly sized images optimized for social platforms (Twitter, LinkedIn, Facebook) and favicon formats.

Set up hierarchical Intent Layer (AGENTS.md files) for codebases. Use when initializing a new project, adding context infrastructure to an existing repo, user asks to set up AGENTS.md, add intent layer, make agents understand the codebase, or scaffolding AI-friendly project documentation.

Release a new version of an Obsidian community plugin without forgetting steps. Use when: (1) user says "release the plugin", "bump <plugin> to X.Y.Z", "ship a new Obsidian release", "tag a new plugin version", "publish to the obsidian directory", (2) the working directory contains manifest.json + main.js + versions.json (Obsidian plugin signature), (3) user wants to scaffold the release workflow into an existing plugin (`scaffold-workflow` arg). Handles version bump across manifest.json + package.json + versions.json, build, lint, conventional commit, signed annotated tag, push, and lets the GitHub Actions workflow publish the release with build-provenance attestation. Idempotent and dry-run-safe.

Deprecated. Auto-generate Claude skills from documentation URLs using Firecrawl agent. Use when user wants to create a skill from docs, API references, or tool homepages. Asks up to 3 clarifying questions before deep extraction. Supports topic focus (e.g., "only auth endpoints") and outputs to local .claude/skills/ by default. No longer recommended: the generated output needed enough rewriting that authoring the SKILL.md by hand was faster.

Read-only audit of a developer machine for npm/PyPI supply-chain compromise. Checks for known IOCs from the 2025-2026 wave — Shai-Hulud 2.0 (Nov 2025), Mini Shai-Hulud / TeamPCP (May 2026), Axios DPRK (Mar 2026), Shai-Hulud 3.0 / keyv-cacheable (Aug 2026), and any future campaigns added to the IOC pack. Scans persistence artifacts (LaunchAgent / systemd unit / Windows Run key / gh-token-monitor / .claude and .vscode droppers), payload files (router_init.js, setup_bun.js, bun_environment.js, Math_Symbol.js, math_init.js), compromised package versions in every node_modules under the user's project roots, C2 / typosquat domain strings (git-tanstack.com, api.masscan.cloud, sfrclak.com, getsession.org, npm-cache.com), malicious commit hashes (79ac49ee), payload SHA256s, optionalDependencies pointing at git refs, and files written during the published attack windows. Produces a PASS/FAIL verdict, IOC checklist, at-risk package list, phase summary, and 48h bake-period remediation. Use this skill whenever the user asks "am I affected by the npm attack", "scan my machine", "check if I'm infected", "is package X compromised", "audit my coworker's machine", mentions Shai-Hulud / TanStack hack / TeamPCP / Mini Shai-Hulud / keyv hack / cacheable hack / pull_request_target compromise / npm worm / axios attack / Bun installer malware / TruffleHog secret theft, asks about IOCs or supply chain risk, or wants to verify a host after a security disclosure. Trigger even when the user uses informal phrasing ("estoy chiveado?", "ya me hackearon?", "this safe?"). Never modifies files.

Map an authorized target into evidence-backed contracts and produce a recon report an implementer can build from. Use for web or mobile APIs, login portals, desktop apps, CLIs, SDKs, MCP servers, local daemons, file and project formats, USB/BLE/serial/HID devices, firmware packages, runtimes, and accelerators. Trigger when the user says recon, reverse engineer, map the interface or protocol, inspect an undocumented integration, discover what a device actually supports, or wants to build a client, CLI, MCP, SDK, adapter, or compatible implementation before its contract is verified.

Compile a mapped surface into working interfaces and keep them alive as the target changes. Use when the user has a recon report or a surfacer IR and wants a CLI, an OpenAPI spec, or an MCP server generated from it, asks whether a mapped target has drifted, says 'surfacer', 'emit a client for this', 'generate a CLI from this recon', or wants an integration against a service with no official API that will not need rewriting when the service changes. Pairs with surface-recon, which produces the IR.