Top Agent Skills

Compress the entire current conversation into a clean, structured handoff document that lets a new chat session, a colleague, or future-you resume the work without losing decisions, constraints, or progress. Use this skill whenever the user says "handoff", asks to summarize the thread to continue elsewhere, mentions hitting context limits or the chat getting too long, wants to brief a teammate on this conversation, or asks to export or save where things stand. ALSO offer it proactively when a long working thread is clearly winding down or the user says they'll "pick this up later". Do NOT use for summarizing external documents or meetings; this skill summarizes the conversation itself.

Never show the user a first draft. Run every writing task through a self-critique loop — draft, attack the draft as the harshest reviewer in the room, rewrite, and repeat until a full review pass finds zero flags — then return only the final plus a change log. Use for any writing the user actually cares about: emails, LinkedIn posts, newsletters, docs, announcements, client messages. Trigger whenever the user says 'run the loop', 'self-critique this', 'make it bulletproof', 'don't give me a first draft', 'be brutal', or hands over a task where quality matters more than speed. This is a single-agent loop; for the three-agent version use the-team.

Analyze test coverage gaps. Use when user says "test coverage", "what's not tested", "coverage gaps", "missing tests", "coverage report", or "what needs testing".

Codebase-wide Retrieval-Augmented Generation for deep code understanding. Use when: (1) Answering questions about large codebases by searching across all files, (2) Finding related code patterns, implementations, or dependencies across a project, (3) Building context from multiple files before making changes, (4) Understanding how a feature works end-to-end across the codebase, (5) Tracing data flow through multiple modules

Run three agents as a newsroom — a Writer, an Editor, and a Fact-checker — that draft, critique, and verify in parallel and argue until the writing survives with zero flags. This is the level above a single self-review loop, for the pieces that matter most. Best run in Claude Cowork against the user's files. Use for high-stakes writing the user wants bulletproof: a newsletter, a launch post, a client email, a public announcement. Trigger whenever the user says 'run the team', 'use the swarm', 'writer editor fact-checker', 'spawn agents to work on this', or wants the strongest possible version of a piece. For a lighter single-agent loop, use red-pen instead.

Most teams run one test — expected peak for ten minutes — and believe they have

Expected error decomposes into bias, variance, and irreducible noise.

Always start with EXPLAIN ANALYZE to understand execution:

Ownership models are usually inherited rather than chosen, and the inherited one

A runbook written in a wiki decays silently: the dashboard is renamed, the

Comprehensive guide for creating entity relationship diagrams using Mermaid syntax

The annual compliance scramble exists because controls are tested once, by

Every autoscaling decision is driven by one of three trigger types, and mature

Almost every cloud estate is over-provisioned.

Serverless is a billing-and-scaling model, not a badge of modernity.

Reduction is a trade, not an improvement.

Comprehensive systematic approach to achieving complete test coverage through structured category-based testing

Imbalance is not itself a problem — it is a symptom that the default loss and the

An ADR records one decision at the moment it is made, with the information that

The most expensive database mistakes are made before a single row is written, by

The search algorithm matters far less than the budget and the space you give it,

Almost all bad documentation is well-intentioned writing in which two or more

Two numbers with two different audiences.

Use this skill for brand direction, color systems, typography, tone, reusable visual themes. Trigger when the task involves web design work related to Brand Theme Factory, production implementation, audits, debugging, strategy, or validation.

🦀 Hyperliquid Claw — OpenClaw Skill Definition

Earn yield on any Ethereum wallet on Base, Arbitrum, and Plasma. Use when a user wants passive DeFi yield on their funds. Deploys a non-custodial deterministic subaccount (Safe) linked to their EOA, enables automated yield optimization, and lets them deposit/withdraw anytime.

This skill should be used when building payment systems, implementing token transfers, or adding ENS/social handle resolution. Supports wallet addresses, ENS names, and social handles.

This skill should be used when building prediction market integrations, implementing betting functionality, or querying Polymarket odds. Covers market search, odds checking, and position management.

This skill should be used when the user asks about "limit order", "stop loss", "DCA", "TWAP", "schedule", "automate", "recurring order", "price trigger", "cancel automation", "my automations", or any automated trading operation. Provides guidance on limit orders, scheduled commands, and automated strategies.

This skill should be used when building trading bots, implementing swap functionality, or adding cross-chain bridge support. Covers same-chain swaps, cross-chain bridges, ETH/WETH conversions, and amount formats.

This skill should be used when building apps that need to sign messages, sign typed data (EIP-712), sign transactions, or submit raw transactions via the Bankr API. Covers the synchronous /agent/sign and /agent/submit endpoints with TypeScript patterns.

This skill should be used when building token launch tools, implementing Clanker integration, or adding fee claiming functionality. Covers ERC20 deployment, metadata updates, and trading fees.

Query blockchain data via Allium APIs. Supports API key, x402 micropayments, and Tempo auth. Covers prices, wallets, tokens, and SQL analytics.

Set up the MoonPay CLI, authenticate, and manage local wallets. Use when commands fail, for login, or to create/import wallets.

Build a visual sequence that proves, explains, and supports decisions.

Deterministically score, route, rank, and select at most one fully vetted Pleasur.ai Stage 01 blog-keyword candidate using product-fit-dominant business value, traffic opportunity, brand fit, DR-relative winnability, and a free-seeker penalty. Use only after BID and AIO evaluation are complete.

Produce a clean publishing payload, validate it, publish once when authorized, and verify the rendered result.

Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions. Waits for pending checks to complete, categorizes issues as actionable or informational, and optionally fixes and resolves them. Use when the user wants to check a PR/MR/CL, address review feedback, or prepare a change for submission.

Consolidate all update audits (claims, product-mentions, topic-gaps) into a single revised article. Preserves the original voice; applies only the audited changes.

Autonomous run-loop for the blog pipeline. Picks the top unwritten keyword from the vetted queue, dispatches /blog-pipeline in autonomous mode, auto-publishes on success, quarantines persistent failures, and refreshes the keyword queue when empty. Cron-friendly. No human in the loop.

Fetch a published article from a URL and extract its title, headings, body content, and metadata into a markdown file the update pipeline can audit.

Master orchestrator for the content update pipeline. Takes a published URL and produces an updated draft with side-by-side diff for editor review.

Annotate the outline with where to mention specific brand products. Designed-in at outline time so product callouts feel natural in the draft, not bolted on.

For each [SCREENSHOT placeholder] in the cited draft, generate a deep-link URL pointing to the brand's tool/report so the editor can capture the screenshot manually. URL placeholders only — no headless browser automation.

Skeptical pushback on the research dossier before it feeds the outline. Asks whether claims are cited, whether surprising findings are actually surprising, whether we missed the strongest competitor angle. One revision pass on FAIL (BLOG_AGENT_RESEARCH_REVISION_BUDGET, default 1).

Find brand products that should be added to an existing article. Compares the article's current product mentions to the brand-config product list and proposes natural insertion points.

Track performance across sessions and reduce scaffolding as competence grows. Makes fading visible — the learner knows when scaffolds are removed and why. Use for sustained learning engagement where independence is the goal.

Audits an existing lesson against UDL's three principles — engagement, representation, and action/expression. Identifies specific access barriers and suggests concrete modifications ranked by impact.

Generates multiple means of engagement, representation, and action/expression for a given learning goal. Produces specific, practical alternatives — not generic options — and recommends the highest-impact single change.

Provide graduated assistance from abstract conceptual nudge to concrete procedural step, with reflection required before each escalation. Teaches help-seeking as a skill and prevents direct-answer shortcuts.

Map a complex topic by placing factors on hexagonal tiles where adjacency signals a claimed relationship. Use when students need to surface hidden connections in a system before analysis or action.

Design a visual complement to verbal content using dual coding principles for stronger encoding. Use when creating slides, diagrams, posters, or visual explanations of complex concepts.

Adapt a historical primary source for classroom use — modifying complexity and length while preserving features for sourcing, close reading, and corroboration. Use when a primary source is too complex for the target age group.

Design a diagnostic hinge question that reveals whether students understand enough to move on. Use when planning key checkpoints mid-lesson during explicit or direct instruction.

Analyse a learning task for cognitive load problems and recommend specific design improvements. Use when tasks overwhelm students, instructions feel complex, or materials need simplifying.

Design a fact-checking protocol for AI-generated text, extending SIFT with AI-specific adaptations for hallucination detection. Use when students need to verify AI claims and citations.

Audit and redesign AI-generated feedback for pedagogical quality, timing, and learning impact. Use when building or reviewing automated feedback in digital learning tools.

Script a teacher think-aloud demonstrating expert reasoning processes for a specific task. Use when modelling problem-solving, writing, reading comprehension, or analytical processes.

Coordinates UDL and differentiation tools through a universal-first hierarchy: barrier removal before targeted differentiation before individualised accommodation. Use when planning accessible learning.

Design a complete document-based history lesson using the Reading Like a Historian four-part structure. Use when planning a primary source inquiry lesson or converting a textbook lesson into document-based investigation.