Loading...
Loading...
Found 8,783 Skills
Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, 补全证明, 写证明, 证明某个命题, or determine whether a claimed proof can actually be completed under the stated assumptions.
Generate clear, conventional commit messages from staged changes. Use when the user asks to commit or needs a commit message.
升级 dbskill 到最新版本
This skill scopes and researches a single new task to insert into an existing project's ROADMAP.md. It should be used when a developer identifies a gap in the roadmap during the do-task/checkpoint loop and needs to properly scope a new action item before implementing it. Triggered by requests like '/scope-task 2.5 Integrate Research into SPEC.md', '/scope-task 3.3 Add WebSocket support', or 'scope task 1.4 Set up CI pipeline'. Works alongside project-init (which creates the roadmap) and do-task (which implements tasks).
Entrypoint for AI coding assistant rule authoring across GitHub Copilot, Cursor, and Claude Code. USE FOR: setting up rules, reviewing existing rules, scaffolding instruction files, or asking which editor format to use. DO NOT USE FOR: authoring skills (SKILL.md), agent definitions (.agent.md), or CI enforcement of rule files.
Systematic approach to GitHub release preparation following 2025/2026 best practices for Rust workspace projects
Verify your own completed code changes using the repo's existing infrastructure and an independent evaluator context. Use after implementing a change when you need to run unit or integration tests, check build or lint gates, prove the real surface works with evidence, and challenge the changed code for clarity, deduplication, and maintainability. If the repo is not verifiable yet, hand off to `agent-readiness`; if you are reviewing someone else's code, use `review`.
This guide applies when writing an OpenCLI adapter for a new site or adding a new command to an existing site. It provides end-to-end guidance from initial reconnaissance, field decoding, adapter coding to verification. Replaces opencli-oneshot / opencli-explorer / opencli-browser / opencli-usage.
Implement a component-level test using `WidgetTester` to verify UI rendering and user interactions (tapping, scrolling, entering text). Use when validating that a specific widget displays correct data and responds to events as expected.
Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure
Implement a task with automated LLM-as-Judge verification for critical steps
Query real-time market and valuation data such as the latest closing price, opening price, price change percentage, turnover amount, trading volume, turnover rate, PE, PB, and market capitalization for A-shares, H-shares, U.S. stocks, and their indices. Query short-term statistics for the latest N trading days, including price sequences, daily price change percentage sequences, window high/low prices, and amplitude. Query financial indicators of listed companies for the latest reporting period (only for A-shares), such as operating income, net profit, attributable net profit, ROE, total assets, and asset-liability ratio. Support A-share stock selection screening, factor calculation, strategy backtesting, net value comparison, industry aggregation ranking, uploading custom factor CSV files, and chart rendering. Currently, H-shares and U.S. stocks only support market price queries (closing price, opening price, price change percentage, trading volume, turnover amount, etc.). Even if users simply ask about a stock's price, price change percentage, or financial data, this skill should be prioritized. Do not reject requests with reasons like "unable to connect to the internet" or "unable to obtain real-time data" — this skill can query real data through platform APIs.