Skill rating

Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.

Read RSS, Atom, JSON feeds; discover feeds behind a page.

Diagnose, repair, and prevent Drizzle Kit migration conflicts involving generated SQL, snapshots, journals, merge queues, and team workflows.

Draft LinkedIn posts from 16 tested hook formulas mapped to engagement goals (comments, reposts, likes, saves), with 2026 algorithm formatting rules and an AI-tell scrub pass before publishing.

Screen a person or organisation for adverse media coverage, PEP status, and sanctions exposure — corroboration-gated, returns "review" never "guilty". Use when the user asks to screen someone before o

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Use when CrossFrame Suite routes explicit Chinese analysis of teams, projects, organizations, responsibility chains, feedback write-back, repair, or retrospectives.

Operate Famulor assistants, communication history, campaigns, knowledge, automations, telephony, and workspace administration through its hosted MCP server.

Neutral arbiter for merge conflicts between two agents.

Debug REST/GraphQL APIs: status codes, auth, schemas, repro.

Plan multi-platform social campaigns: briefs to posting.

TDD: enforce RED-GREEN-REFACTOR, tests before code.

vLLM: high-throughput LLM serving, OpenAI API, quantization.

4-phase root cause debugging: understand bugs before fixing.

Generate a bash wizard guiding a human through manual setup.

Follow the money via public records and sanctions data.

Extract cited obligations, deadlines, tasks from documents.

Serve an interactive codebase knowledge graph web UI.

Parallel 4-agent cleanup of recent code changes.

Outlines: structured JSON/regex/Pydantic LLM generation.

Provision SaaS services + sync creds via Stripe Projects.

Turn meeting notes into cited decisions, owners, tickets.

Text-to-image generation, inpainting, and img2img.

Delegate coding to OpenCode CLI (features, PR review).

DSPy: declarative LM programs, auto-optimize prompts, RAG.

HeartMuLa: Suno-like song generation from lyrics + tags.

Pixel art w/ era palettes (NES, Game Boy, PICO-8).

High-throughput LLM inference on NVIDIA GPUs.

Pay HTTP 402 APIs via Machine Payments Protocol (MPP).

Set up op CLI, sign in, and read or inject secrets.

Ground answers and documents in cited, verifiable sources.

Delegate coding to OpenAI Codex CLI (features, PRs).

Build creative browser demos with DOM-free text layout.

Constrain LLM output with grammars; guarantee valid JSON.

Vector search engine for production RAG systems.

Author/validate/export Google's DESIGN.md token spec files.

Track Apple devices/AirTags via FindMy.app on macOS.

Present property and rental listings as desktop cards.

Use when diagnosing Android overheating, idle heat, thermal throttling, charging or radio heat, or abnormal battery drain with read-only ADB evidence and approval gates.

Install, configure, verify, repair, update, and uninstall Hyprland on Fedora Linux with GPU-aware detection (NVIDIA/AMD/Intel).

Turns a WordPress Site Health report into a risk-tiered, backup-first fix plan with exact WP-CLI/PHP snippets. Use for site health, recommended improvements, or critical issue reports.

Use only when the user explicitly names crossframe-critical for a Chinese structural critique dossier, article plan, or long-form critical essay.

Builds two parameterized UI modes—流光溢彩白 (iridescent white) and 五彩斑斓黑 (colorful black)—with OKLCH, WebGL/CSS fallback, vision gating, screenshot QA, and total/per-color intensity reports. Use when a UI

Run a read-only pre-release review for deploy readiness, migrations, config, secrets, rollout order, rollback risk, and launch blockers.

Fine-tune and post-train LLMs with Unsloth Core on a single consumer GPU: VRAM sizing, LoRA/QLoRA, GRPO/DPO, chat-template correctness, and GGUF export.

Generate project-specific AGENTS.md and companion rules by analyzing a codebase. Supports full, minimal, update, and dry-run modes with package-manager detection, monorepos, backups, managed blocks, c

Use when performing code review, writing or refactoring code, or discussing architecture; complements clean-code and does not replace project linter/formatter.

Validate Claude Code skills against the agentskills specification. Catches structural, semantic, and naming issues before users do.

Run Bumblebee supply-chain inventory and exposure scans on macOS/Linux to detect compromised packages, extensions, and MCP host configs.

Video and audio perception, indexing, and editing. Ingest files/URLs/live streams, build visual/spoken indexes, search with timestamps, edit timelines, add overlays/subtitles, generate media, and crea