Loading...
Loading...
Found 12 Skills
Run an iterative code-improvement hill-climb against real Datadog LLM-Obs data, locally, with Claude Code as the agent. Establishes a baseline eval, makes one focused change, re-scores with the same harness, keeps the change if it improves the score in the goal's direction (labeling within-noise gains tentative), and repeats. Use when the user says "run an auto experiment", "hill-climb this code", "iteratively improve X and measure the delta", "optimize this prompt/file against my traces", "auto-optimize against LLM-Obs", or wants the local equivalent of the auto_experiments worker. Works from a local dataset file, an ml_app, a dataset_id, or a list of trace_ids.
Safe Rust refactoring with LSP analysis. Triggers on: /refactor, rename symbol, move function, extract, 重构, 重命名, 提取函数, 安全重构
Review pull request feedback with discerning judgment. The lynx scans comments, identifies legitimate concerns, addresses minor issues directly, and plans responses to significant feedback. Use when responding to PR reviews and addressing reviewer concerns.
Performs focused, depth-first investigation of specific reverse engineering questions through iterative analysis and database improvement. Answers questions like "What does this function do?", "Does this use crypto?", "What's the C2 address?", "Fix types in this function". Makes incremental improvements (renaming, retyping, commenting) to aid understanding. Returns evidence-based answers with new investigation threads. Use after binary-triage for investigating specific suspicious areas or when user asks focused questions about binary behavior.
Use when user wants autonomous iteration on any task — improving metrics, completing features, running experiments, optimizing code, or working unattended. Make sure to use this skill whenever someone mentions autoresearch, autonomous loops, iterating until done, running overnight, keep improving, hill-climbing, or any measurable improvement goal, even if they don't explicitly ask for a 'loop'.
Reviews and improves Claude Code skills against official best practices. Supports three modes - self-review (validate your own skills), external review (evaluate others' skills), and auto-PR (fork, improve, submit). Use when checking skill quality, reviewing skill repositories, or contributing improvements to open-source skills.
Survey a whole React codebase as a senior React engineer, using React Doctor's scan as evidence, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the React code", "audit this codebase", "make this app faster / more robust", or wants a roadmap of fixes rather than a review of a single diff. For a regression check or a fix-it-now pass, use the `react-doctor` skill instead.
Capture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises, and retrieves rules for future sessions. Use after mistakes or when the user says "remember this", "don't forget", "note this", or "learn from this".
Deep repository analysis skill for Z.AI Zread MCP.
Run a bounded, evidence-first audit-fix-review-verify loop on a codebase when the user asks to improve, harden, overhaul, or fix all confirmed defects. Use only with explicit edit authority in a git repository. Do not use for advisory-only reviews, a single narrow bug, or when the worktree is dirty and the owner has not chosen how to preserve it.
Code improvement workflow with polish and overhaul tracks. Triggers: 'refactor', 'clean up', 'restructure', 'reorganize', or /refactor. Phases: explore, brief, implement, validate. Existing code only — Do NOT use for bug fixes (/debug) or new features (/ideate).
Local Code Review - analyzes code changes and provides structured feedback before commit