Shape agent capabilities into your workflow.

font-pairing-skill helps an agent choose display and body faces, match typography to a project palette and icon weight, and build a coherent type scale. It includes eight archetype recipes, variable-font guidance, Google Fonts import references, and loading patterns such as preconnect, preload, font-display, and subsetting. The goal is a considered type system that avoids layout shift rather than a random font list.

icon-system-skill guides library selection across Lucide, Phosphor, Heroicons, Radix Icons, and React Icons, then defines optical sizing, stroke-versus-fill choices, weight matching, and color inheritance through currentColor. It also covers animated SVG patterns, aria labels, and 44×44px touch targets, with eight project-archetype recipes. Use it when an interface needs a consistent icon language rather than one-off symbols.

hyperagent-orchestrator teaches Claude to use Hyperagent’s hosted MCP server as a remote control for existing agents. Its core loop lists agents, creates a thread, polls until it stops, and sends follow-up messages; recipes cover sequential chains, parallel fan-out, and user-in-the-loop refinement. The opening request must be self-contained because an agent cannot ask for clarification mid-run, and scores or costs remain visible only in the Command Center.

eslint-complexity-guardian locates an ESLint configuration, checks whether the complexity rule exists, and adds or updates only that rule. It shows a focused diff and explains the effect, while leaving other files, rules, dependencies, and settings untouched. It supports legacy config files, Flat Config, and eslintConfig embedded in package.json.

psycho-cybernetics gives Claude a mindset lens based on self-image, clear targets, and feedback. It encourages the user to aim, act, read failure as steering data, and adjust instead of treating setbacks as a verdict about identity. Invoke it with /psycho-cybernetics or let it trigger when the obstacle is mental rather than informational. It is a coaching frame, not a diagnostic tool.

supertutor teaches through plain definitions, concrete worked examples, and explain-back rather than accepting a learner’s nod. After each restatement it identifies the first gap using a fixed rubric and ladders hints until the learner can rebuild the idea. The skill is aimed at genuine understanding, with first-principles engineering as its flagship example; simple one-line facts are better answered directly.

auto-skill-manager scans the available skills, installs missing ones, and activates the right tools for a task across Claude Code and Cowork. It supports Windows, macOS, and Linux, uses Python 3.8 or newer for scanning, and can bring in optional Python, Node, or command-line dependencies when needed. The convenience comes from handling local setup instead of requiring manual installation steps.

pentest-report normalizes existing penetration-test findings or scanner output into German or English reports and checks them against a selected BSI, OWASP, PCI-DSS, DiGA, or OSCP profile. It can detect missing fields, enrich findings with CVSS, CWE, OWASP, and MITRE references, deduplicate hosts, and render Markdown, PDF, or SysReptor JSON. It does not scan or exploit systems and does not certify compliance.

pull-context helps a Claude Code session import context from another session on demand. It searches candidates by topic, age, and message count, lets you choose a source other than the current session, and distills the long transcript into goals, decisions, pointers, and open questions. A verbatim tail can be pulled when exact wording matters. It relies on Claude’s local transcript layout, which is undocumented and may change.

strong-ads-google-skill is for Google Search/RSA and Performance Max, not Meta or Instagram. It studies the business, competitor ads, and real buyer frustrations before producing angle-based headlines, long headlines, and descriptions that fit Google’s character limits. Pain points are tied to sources, and the output is organized for Google Ads Editor rather than padded with generic marketing language.

report-writing is a reusable method library for formal DOCX reports, especially Traditional Chinese government and tender deliverables in Taiwan. It covers requirements, content strategy, layout, equations, clickable cross-references, page-numbered tables of contents, figures, and delivery checks, with linters for wording and English AI tells. The skill works with Claude Code and Codex and focuses on verified document output.

hom turns Andrew Grove’s High Output Management into a working advisor for real management problems. It diagnoses the underlying lever or bottleneck, then applies the relevant mechanics for delegation, one-on-ones, OKRs, decisions, organization design, motivation, or training. Responses are bilingual and grounded in the book’s terminology, with the emphasis on a concrete situation rather than a generic summary.

gtd operates Getting Things Done on your actual work instead of explaining the method. Give it a brain-dump, inbox, or vague task and it returns concrete next actions, projects with outcomes, waiting-for and calendar items, plus a short list of tasks that take under two minutes. It can also run weekly reviews and system audits, with every next action expressed as one visible physical step.

bbyt applies Dan Martell’s Buy Back Your Time to a real workload. It calculates the Buyback Rate, sorts tasks through the DRIP audit, returns a prioritized offload list, and identifies the next hire on the Replacement Ladder. Other modes transfer a task into a Definition of Done and playbook, build an energy-matched Perfect Week, plan the year, or diagnose recurring time traps.

phinq-governance adds a procedural memory layer that an autonomous agent is expected to consult before taking a structurally significant action. It classifies reversible and irreversible work, checks the action against rule documents such as SOUL.md or AGENTS.md, pauses for confirmation when risk is high, and records events in an append-only tamper-evident log. It covers deletions, bulk operations, external communications, credential access, and payment changes, but it is an advisory protocol rather than a runtime interceptor or sandbox.

UI/UX Consultant Skill gives Claude a multi-framework design reference for interface requests. It covers 16 frameworks with opinionated code patterns, accessibility checklists, 23 visual styles, 35 color palettes, 31 font pairings, and layout guidance for 41 product types. It can be initialized for Claude Code or Cursor and is intended for design direction plus implementation patterns rather than a visual editor.

Experience Skill searches Xiaohongshu, Doubao, Baidu, Zhihu, and Douyin for travel tips, tutorials, product advice, and everyday experience, then deduplicates and compares the results into a structured report. Each point carries a source so you can see where advice converges or comes from a single platform. It relies on browser automation, with the Xiaohongshu connector optional.

Colorway C packages the Code Meet AI and Malik Chohra brand as an agent-ready design system. It defines a dark-first editorial surface, one muted-teal accent, hairline structure, cursor motion, three Google fonts, and matching voice and token rules. Use the accompanying skill or read the ordered briefs to produce on-brand interfaces without repeating the art direction each time.