Loading...
Loading...
Found 3,029 Skills
Count the Tokens consumed by the local Codex in recent time by task purpose dimension, and output a Chinese table including model and category proportions; output the Faster x2 status only when explicit session-level fields exist.
Four-mantra debugging discipline — reproduce, trace the fail path, falsify the hypothesis, cross-reference every breadcrumb. Recite the mantra block verbatim at the start of any debugging session, then apply the four steps in order before proposing any fix. Trigger on /debug-mantra and proactively whenever debugging starts — user reports a bug, says something is broken/throwing/failing, asks to debug/diagnose/investigate an issue, or pastes a stack trace or error log.
Evaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator Launcher (NEL). Triggers on "evaluate model", "benchmark accuracy", "run MMLU", "evaluate quantized model", "accuracy drop", "run nel". Handles deployment, config generation, and evaluation execution. Not for quantizing models (use ptq) or deploying/serving models (use deployment).
A qualitative research assistant tool based on Braun & Clarke's Reflexive Thematic Analysis framework. Supports two input modes: (1) Provide raw interview text directly → The skill completes initial TA coding for each document, then proceeds to theme identification after summarization; (2) Provide existing initial coding pool → Directly enter the process of clustering, review, and naming suggestions. Outputs a structured candidate theme table, clearly marking codes with ambiguous boundaries and naming suggestions to be decided by researchers. This skill is triggered when users mention terms such as "thematic analysis", "theme coding", "help me cluster codes", "extract themes from codes", "Braun Clarke", "candidate themes", "how to categorize these codes into themes", "help me check the theme structure", "conduct thematic analysis on interviews". Note the difference from grounded-coding: grounded-coding focuses on category construction and theoretical relationships for procedural grounded theory; thematic-analysis focuses on semantic theme identification following the Braun & Clarke approach, outputting theme structures rather than theoretical propositions.
Soroban smart contract development on Stellar (Rust SDK). Covers project setup, contract structure, storage types, authorization, cross-contract calls, events, error handling, testing (unit, integration, fuzz, property, mutation, fork, differential), security patterns and vulnerability classes, advanced architecture patterns (upgrades, factories, governance, DeFi primitives), and common pitfalls. Use when writing, testing, securing, or shipping Soroban contracts.
Stellar Assets (classic) + trustlines + Stellar Asset Contract (SAC) bridge to Soroban. Covers asset issuance, distribution, authorization flags, clawback, regulated assets, trustline management, and the SAC interop layer that exposes classic assets as Soroban tokens. Use when tokenizing real-world assets, issuing stablecoins, managing trustlines, or bridging classic assets to Soroban contracts.
Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic, Bedrock, Gemini, Strands) to a managed config, or stage a full hardcoded-to-LaunchDarkly migration.
[user] Perform security inspection and monitoring for Alibaba Cloud DDoS security products, covering DDoS Basic Protection, DDoS Native Protection, and DDoS Anti-DDoS Pro/Premium. Supports querying blackhole/scrubbing events, QPS spikes/drops, L4 traffic anomalies, HTTP status code (4xx/5xx) period-over-period surges, origin status code anomalies, and instance asset inventory. Use this Skill when users need security inspection, DDoS protection status checks, attack event queries, traffic anomaly investigation, or to confirm whether DDoS security products are provisioned. Triggers: "DDoS inspection", "security check", "DDoS protection check", "attack event query", "traffic anomaly"
This skill should be used when the user asks to "optimize for Instagram", "YouTube Shorts format", "make it 9:16", "square video", "TikTok format", "Reels format", "prepare for social media", "encode for Twitter", "optimize for Facebook", "LinkedIn video", "crop for portrait", or mentions any platform-specific video format or upload requirements.
Evolve your brain's schema pack. Add page types, propose new ones from corpus scans, backfill page.type on existing pages, audit pack health. Triggers when an agent notices untyped pages, custom domains needing typed entities (researcher, contract, deposition), or wants to see what types the pack declares.
Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply fixes when requested. With appropriate review rules, can detect various types of issues including bugs, security vulnerabilities, performance problems, and code quality concerns.
Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing academic-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.