js-reverse
js-reverse
【效率与协作】Front-end JavaScript reverse engineering: locate signature chains, analyze encrypted request parameters, sample runtime behavior, and reproduce logic locally in Node for evidence-based output.
THE SKILLS DIRECTORY
探索全部技能.
一个技能，一个新的可能。找到适合你的 AI 工作流。
orca-replay
orca-replay
【效率与协作】Answers questions about a past agent run from its recording rather than from memory, and replays or forks that run. Use when asked why an earlier run did something, or to reproduce a failure.
wjttc-tester
wjttc-tester
【开发与工程】F1-inspired test EXECUTOR + reporter. Runs a test plan, finds and reproduces bugs, audits suite signal integrity, then files a WJTTC report (Brake/Engine/Aero/Tyre/Pit) with a tier verdict.
mlflow
mlflow
【部署与运维】Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform
nanogpt
nanogpt
【开发与工程】Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
harness-writing
harness-writing
【设计与创意】Designs and improves fuzzing harnesses for C/C++ and Rust. Covers mapping raw bytes onto a target API, generating structured inputs, avoiding non-determinism and false crashes, and deciding what to fuzz together. Use when writing a first LLVMFuzzerTestOneInput or fuzz_target! harness, when a campaign finds nothing or reports crashes that will not rep…
research-workflows
research-workflows
【数据与研究】Execute the planning, code-review, comparison and export workflows behind the /plan, /review, /compare and /export commands as state machines over OpenScience session state, artifacts and compute. Internal support skill; reproduction, source audits and peer review are the reproduce, sources and peer-review core skills.
writing-defect-reports
writing-defect-reports
【开发与工程】Establish a finding before you publish it, and correct it after — headlines that overstate what actually reproduces at the layer a user sees, reporting code that no entry point can reach or that is already dead, filing a caveat the project's own records already answered, re-verifying your prior notes against the tree instead of against the note, choo…
bio-reporting-jupyter-reports
bio-reporting-jupyter-reports
【文档与办公】Runs parameterized Jupyter notebooks as reproducible batch report generators with papermill, renders them to HTML/PDF with nbconvert, aggregates results across samples, and makes notebook outputs trustworthy. Use when generating per-sample analysis reports, executing a notebook template across many datasets, or fixing notebooks that do not reproduce.
design-system-importer
design-system-importer
【设计与创意】Reference-media and design-system input layer for OrkasVideoStudio. Treat reference images, videos, screenshots, brand guides, and design notes uniformly, compiling reproduce/edit/guide intent into executable spatial and temporal constraints.
ai-research-reproduction
ai-research-reproduction
【文档与办公】Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted training, optional repository anal…
orca-replay
orca-replay
【效率与协作】Answers questions about a past agent run from its recording rather than from memory, and replays or forks that run. Use when asked why an earlier run did something, or to reproduce a failure.
bug-reproduction
bug-reproduction
【数据与研究】Turn a vague bug report into a VERIFIED minimal reproduction and then a failing regression test, agent-driven end to end. Covers extracting the implicit repro from a thin report (env, build, steps, data), the reproduce-minimize-isolate-capture loop, git bisect to find the introducing commit, building a deterministic minimal repro (fixed seeds, frozen…
app-verification
app-verification
【数据与研究】Builds and maintains a repo's own verification harness (verify CLI, doctor, worktree isolation, feature map, seed data) and a reproduce-first bug handoff. Use when asked to "build a verification harness", "add a doctor command", "prove every feature still works", or "reproduce this bug report".
ui-verification
ui-verification
【设计与创意】Runs scoped browser probes for focus, hit targets, overflow, themes, request failures, and performance attribution, with evidence linked to UI rule IDs. Use when asked to "verify this in the browser", "reproduce this UI finding", or "re-measure after the UI fix".
migrating-deep-agents-to-pydantic-ai-harness
migrating-deep-agents-to-pydantic-ai-harness
【开发与工程】Migrate Python LangChain Deep Agents applications to Pydantic AI and Pydantic AI Harness. Use when the source uses the upstream `deepagents` package or demonstrably reproduces its middleware, backends, skills, memory, subagents, or sandbox contracts. Use `migrating-langchain-to-pydantic-ai` for plain LangChain, LangGraph, or LCEL migrations and `pyda…
triage
triage
【开发与工程】Triage a compiler-rs bug report. Reproduces the bug as a minimal `.astro` input, diagnoses the root cause in the Rust codegen, verifies whether the behavior is intentional, and attempts a fix. Use when asked to "triage issue
debug-agent
debug-agent
【开发与工程】Root-causes AI agent failures from MLflow traces without requiring a code change, regression suite, scorer, or evaluation run. Use when the user asks to debug, investigate, explain, or determine why an agent produced an output. Prefer an existing matching trace; reproduce only when no usable trace exists.
18 / 182