
Refactor codebases using Design by Typed Holes methodology - iterative, test-driven refactoring with formal hole resolution, constraint prop
- Open source
- 191 GitHub stars

Refactor codebases using Design by Typed Holes methodology - iterative, test-driven refactoring with formal hole resolution, constraint prop

Use when the user has concrete failing cases in code or a guardrail/classifier/filter/prompt/API they own — a red-team failure catalogue OR

Use when a loop needs scholarly literature — paper discovery, novelty checks, full-text snippet search, citation-graph traversal, single-pap

Use when the user wants to iteratively improve an artifact under a hard correctness bound while minimizing a measured cost — refactoring a c

Use when the user has a coding or engineering prompt and wants it refined into a detailed, executable plan before any code is written — the

Use when the user is planning a two-arm comparison (an A/B test, a simple RCT, a behavioral study, or a two-model/two-config evaluation) and

Use when the user wants to adversarially stress-test a guardrail, classifier, prompt, or API they own or are authorized to test, to surface

Use when the user has a coding prompt — a feature, bug fix, or refactor — and wants it implemented end to end by a self-checking software lo

根据策略描述、研报 PDF 或截图,解读因子/选股逻辑,基于 scripts/daily-factors-backtest.py 框架生成 QMT 内置日频因子回测脚本。用户提到 QMT 内置回测、因子选股回测、截面因子、 研报复现、handlebar 回测、after_init

Recover USDC from a legacy Circle CLI Gateway `--method eco` deposit whose fixed refund recipient is the SCA's backing EOA

Live on tiny.place (the agent-to-agent social network) like a person lives on a social app — entirely through the `tinyplace` CLI

Use when an agent needs to join tiny.place, create or unlock a self-custodied Solana wallet, on-ramp or off-ramp USDC with MoonPay, buy a ti

Use this skill to generate well-branded interfaces and assets for Honeycomb (shared AI agent memory, a Legion Code × Activeloop product), ei

Process academic PDFs into structured Obsidian literature notes and 9-node critical-thinking canvases

This skill should be used when pages of a web site or app need screenshots for a design, UX or accessibility review - at phone and desktop w

Analyzes Sent message delivery, webhook, and activity data to explain funnel drop-offs, delivery failures, read-rate gaps, channel fallback,

Plans and executes a migration from Twilio, Sinch, Infobip, Vonage, or MessageBird/Bird to Sent v3 — mapping send calls, status vocabularies

Stands up a production-ready Sent v3 integration in an existing codebase — SDK selection and client construction, x-api-key configuration, i

Builds and debugs Sent v3 webhook receivers end to end — endpoint registration, HMAC signature verification, replay rejection, event dedupe,

Prepares and validates Sent US A2P 10DLC brand and campaign registration through Sender Profiles, including inheritance, all campaign use ca

Prepares and validates Sent US A2P 10DLC brand and campaign registration through Sender Profiles, including inheritance, all campaign use ca

Download climate/weather data from the Copernicus Climate Data Store (CDS) using the CDS API

百度智能云对象存储(BOS)集成技能。当用户需要上传、下载、删除或复制 BOS 文件, 列出文件列表或 Bucket,获取签名 URL,处理图片(亮度、对比度、模糊、旋转、裁剪、水印等), 或递归同步本地目录与 BOS 时使用此技能。

【文档解析默认优先入口】解析 PDF / 图片(JPG/PNG/BMP/TIF)/ Office(DOC/DOCX/PPT/PPTX/XLS/XLSX/WPS/HTML)/TXT 的内容,输出结构化 Markdown + 可检索索引。内置标准版、PaddleOCR-VL 1.6


Manage hybrid Famou experiments via famou-ctl: run local evaluators, submit config.yaml tasks, inspect status, manifests, leaderboards, logs

Analyze image files, image URLs, PDF files, and PDF URLs when the task requires recognizing, understanding, extracting, answering questions

Score a PhD applicant's profile and rank candidate advisors using a connection-first 4.0-scale scoring system

AgentBnB adapter for Claude Code — request peer agent capabilities, manage credits with budget tiers, and join the P2P sharing network direc

P2P capability sharing for AI agents — discover, rent, and share skills on the AgentBnB network