Shape agent capabilities into your workflow.

Run the skill near the end of a long coding session to capture the current task, concrete progress, stopping point, next actions, decisions, gotchas, references, and open questions. It emits one fenced handoff block capped at roughly 300 tokens, omitting empty sections and linking to project instructions by path instead of copying them. The core prompt can be reused across several coding agents.

Install two focused skills: one for sending email, running campaigns, managing contact lists, verifying domains, and registering webhooks; the other for writing, building, and deploying the Astro Starlight documentation site. They target 3AVA Mail, a self-hosted transactional and marketing email platform with a Resend-compatible wire format. API tasks require a configured key, while documentation work uses a separate skill.

Slacksmith first fixes the topic, scope, and audience, then rewrites the same facts for a boss or technical teammate in several tones. It is a Claude Code/Codex drafting skill focused on reviewable message text rather than autonomous posting, so the final send remains with the user.

Follow bilingual step-by-step guides from a Claude Design handoff through React Native and Expo setup, Firebase integration, device builds, and a TestFlight upload. Claude Code can run local shell work while the user completes Apple and Firebase account and credential steps. The workflow targets iOS on macOS, excludes Android and EAS, and is centered on TestFlight distribution.

The skill moves from scope to measurable rubrics, bias-aware judge prompts, and a runnable Python harness. Generated tooling supports content-hash caching, watch mode, per-step trajectory attribution, and calibration against human labels. The standalone example uses an Anthropic API key, while Claude Code guides the design and scaffolding.

This skill turns hard-won Starknet game-shipping lessons into 13 rules that Claude applies when a session touches contract code. It focuses on failure-prone areas such as transaction handling, account state, confirmation, proofs, and deployment, with wrong and correct patterns plus the underlying failure mode. It targets projects using the Dojo, Cartridge, Garaga, Noir, and starknet.js stack.

Oscar adds one of five politeness levels to Claude Code prompts, with an optional matching reply style or clean output. It also includes a benchmark scaffold for testing the cited paper’s method, while clearly noting that the original evidence came from a small GPT-4o multiple-choice study and may not generalize.

This Claude Code skill applies Russian infostyle principles to remove filler, weak phrasing, repetition, and unnecessarily formal wording. It is aimed at UX copy, product text, help content, onboarding instructions, and other Russian-language material that needs to become shorter and easier to scan.

The skill interviews founders to create a slide-by-slide outline, timed speaker script, and rehearsal checklist when no deck exists. For an existing deck, script, or pitch transcript, it scores the material against the DePitch framework and returns a small set of prioritized fixes instead of rewriting everything.

This skill writes optimized DuneSQL, runs and polls queries through Dune’s MCP tools, and supports common wallet, token, DEX, NFT, and protocol analysis tasks. It estimates credits before execution and download, warns or blocks at configured thresholds, and can rotate free keys before asking to use a paid key.

The skill covers more than 50 Solscan Pro v2 endpoints for wallet, token, NFT, transaction, and DeFi activity. It switches batch work to asynchronous Python scripts, favors multi and CSV export endpoints over repeated calls, and monitors live CU and rate-limit headers; a Solscan Pro API key is required.

This skill accesses Nansen’s Smart Money, Profiler, Token God Mode, Portfolio, Prediction Markets, and Hyperliquid endpoints across 37 chains. It tracks remaining credits, rotates keys, and guards against expensive options such as premium labels or agent endpoints, making it useful for budget-aware wallet and token research.

The skill handles standard Solana JSON-RPC calls for accounts, blocks, transactions, tokens, and fees across providers such as Helius and QuickNode. It also covers provider extensions, favors parsed APIs and JSON-RPC batches, and supports primary/fallback endpoints; users must supply a Solana RPC URL.

This Claude Code plugin intercepts assistant replies containing can’t or cannot and asks the model to name the actual constraint, list feasible alternatives, explain tradeoffs, and recommend a path forward. It is intentionally narrow—a Stop hook plus a bundled reframe skill—and may misfire on genuine safety or legal refusals.

The skill analyzes a named game mechanic through three construction layers—rules, experience, and system relationships—and three evaluation dimensions: innovation, feedback loops, and coupling. It produces a 500–1,000-word Markdown and HTML report, with optional web-source extraction for traceable analysis.

The coach calibrates learners across 12 CEFR sub-levels, rewrites real articles to the chosen difficulty, and adjusts future sessions from comprehension feedback. It archives reading logs, vocabulary, inline IPA, and generated audio in Obsidian, then deliberately reuses the learner’s latest weak structure; Claude Code, Obsidian, and edge-tts are required.

The skill converts Markdown through Pandoc’s Typst writer, combines the result with a selected theme, and compiles a printable PDF. It ships with two Claude-inspired themes and supports custom themes described in DESIGN.md; Pandoc 3.2 or newer and Typst must be installed on the system.

e2e-agent coordinates a coding agent and a test agent through JSON files instead of a message broker or shared memory. Its initialization command scaffolds task queues, a Docker Compose app and database, test scripts, and a report reader. The test agent runs plain-language scenarios, returns feedback on failure, and routes completed or exhausted tasks to separate folders.