405 skills · sorted by relevance
Evaluates task complexity and selects a small set of existing skills for work spanning multiple areas. Uses agent-memory-mcp to record and retrieve successful combinations, while keeping simple tasks within the agent’s ordinary capabilities.
Design and build an OpenMAIC lesson series using a spiral curriculum: core ideas return with deeper explanations, new representations, and unfamiliar applications. It maps conceptual growth across lessons and checks that revisits add understanding.
Create and maintain due diligence checklists for acquisitions or investments. Tailor requests to the company and deal, track owners and review status, and summarize missing documents and issues that could affect valuation or deal terms.
Refactor Java methods by extracting related blocks into separate, clearly named methods. Assess method length and complexity, preserve existing functionality, and return complete Java 17 methods with brief comments explaining each newly extracted method.
Plan how users discover, try, and pay for a product through self-service. Compare product-led growth with sales-led approaches, improve the first useful experience, assess acquisition channel economics, and identify when sales support should step in.
Coordinate a small AI development team with planning, implementation, and optional independent testing roles. Adapt the process to the work’s complexity, prepare pull requests, and preserve decisions and next steps so later sessions can continue.
Turn a screen recording of repetitive work into automation scripts. The skill reconstructs the workflow, proposes options suited to installed tools, and helps build and test the chosen approach while preserving human review steps.
Review completed code changes for defects, security risks, unnecessary complexity, and missing tests. Findings are verified and reported with severity, file locations, and concrete failure scenarios, with separate assessments of standards and intended behavior for larger changes.
Approach engineering problems by checking assumptions, defining performance constraints, and choosing suitable tools before implementation. The skill guides algorithm analysis, complete code, performance optimization, and correctness checks through tests, assertions, or formal verification, meaning mathematical checks of correctness.
Guides the use of RWKV, a language model architecture that carries information forward in a compact state. Covers streaming text generation, long document processing, fine-tuning, and memory comparisons with Transformers.
Plan SDK behavior changes by defining required outcomes, compatibility boundaries, and unsupported cases. Reuse existing implementation paths, assess review feedback, and reconsider designs when repeated fixes introduce complexity beyond the original requirement.
Review Qwen Code issues and pull requests through staged checks. Assess product fit, code simplicity, and CI evidence, then prepare English and Chinese comments that explain findings and flag decisions needing maintainer attention.
Estimate development effort using affected code, design documents, dependencies, and past sprint results. Get optimistic, expected, and pessimistic day estimates, along with a confidence level, key risks, and a suggested breakdown into smaller tasks.
Prepare a development branch for final maintainer review by checking security, unnecessary complexity, and billing abuse risks. Fix confirmed issues, run local checks and tests, then push changes and create or update the pull request.
Review a pull request, a proposed code change, for code that can be removed or simplified. Consider product decisions, final functionality, and whether rare edge cases have led to unnecessary complexity.
Review Handsontable code changes for architecture, code quality, performance, accessibility, and test coverage. Findings include severity, confidence, and file locations, helping developers assess whether changes follow project rules and demonstrate the intended behavior.
Audit an entire codebase for unnecessary complexity and dependencies. Receive a ranked list of code to delete, simplify, or replace with standard library and platform features, with file paths and estimated reductions.
Review and simplify the ego-lite codebase by finding unused code, duplicated state, and unnecessary layers. The skill checks real callers and API requirements, explains behavior changes, and coordinates implementation, tests, and documentation updates.
Guides you through setting up RWKV, generating text, processing long documents in chunks, and fine-tuning models. Explains how to carry context between steps and compare memory use with Transformer models.
Review a pull request or code diff from several angles, then have separate agents test each potential finding. Receive a ranked findings table, confidence assessments, a merge recommendation, and concrete follow-up work.
Build a graph of functions and calls across multiple programming languages to investigate entry points, paths to sensitive operations, and potential impact. Use the results to prioritize security reviews and connect external findings with source code.
Analyze code structure with Trailmark to identify complex functions, trace input flow, assess impact across connected code, and locate privilege boundaries. The resulting JSON provides detailed evidence for deciding where to focus a code audit.
Compares code relationships before and after a branch, pull request, or release change using Trailmark. Flags structural security regressions, such as removed authorization checks or newly reachable sensitive operations, and provides evidence for reviewers.
Assesses smart contract and blockchain codebases against Trail of Bits’ nine-category maturity framework. Produces evidence-backed ratings covering areas such as arithmetic, access controls, documentation, and testing, plus a prioritized improvement roadmap with effort estimates.