malskill

In the author's own words, from each skill's SKILL.md — showing the first 30 of 337 files.

• keras

  Keras model loading and structure-inspection workflow for `.keras`, SavedModel, and HDF5 artifacts. Use when you need to inspect layers, summaries, configs, weights, or quick inference behavior from TensorFlow/Keras model files.

  ai/keras/SKILL.md on GitHub (opens in a new tab)

• langchain-py

  Build and maintain production-grade LangChain Python systems (LangChain 1.3.x / LangGraph 1.2.x baseline) with create_agent, middleware, tools, structured output, and multi-agent architectures (subagents, handoffs, router, skills). Activate for Python agent design, debugging, migrations from older APIs, context engineering, and Tavily-backed web search integration.

  ai/langchain-py/SKILL.md on GitHub (opens in a new tab)

• pytorch

  PyTorch model inspection and checkpoint workflow for loading tensors, `state_dict` data, modules, and parameters. Use when working with `.pt` or `.pth` artifacts, auditing model structure, extracting weights, or scripting inference-oriented inspection of deep-learning checkpoints.

  ai/pytorch/SKILL.md on GitHub (opens in a new tab)

• scikit-learn

  scikit-learn model inspection workflow for loading persisted estimators, pipelines, and tree models. Use when you need to inspect `joblib` or pickle-based model artifacts, view parameters, feature names, importances, or pipeline structure, or run lightweight predictions for analysis.

  ai/scikit-learn/SKILL.md on GitHub (opens in a new tab)

• vec2text

  vec2text: embedding-inversion library for reconstructing approximate text from sentence embeddings. Use when working with saved embedding tensors, privacy/inversion research, or AI/ML challenge workflows where you need to load a corrector model and invert strings or embeddings directly.

  ai/vec2text/SKILL.md on GitHub (opens in a new tab)

• 1337-brain

  Maintain and query an Obsidian knowledge vault. Use /1337-brain for source ingestion, linked notes, project indexes, grounded answers, deduplication, or vault audits.

  behaviours/1337-brain/SKILL.md on GitHub (opens in a new tab)

• 1337

  Structured operator behavior for coding and authorized security work: explicit reasoning, evidence, verification, and concise execution. Use when the user requests /1337 or execution-first structured analysis.

  behaviours/1337/SKILL.md on GitHub (opens in a new tab)

• agentic-offensive-orchestration

  Design and review authorized multi-agent security workflows: delegation topologies, deterministic worker contracts, agentic trust boundaries, and worker-compromise containment.

  behaviours/agentic-offensive-orchestration/SKILL.md on GitHub (opens in a new tab)

• design-before-implementation

  Clarify and review designs before substantial changes. Use when requirements, interfaces, alternatives, or success criteria are unclear; skip a separate design phase for an already specified local fix.

  behaviours/design-before-implementation/SKILL.md on GitHub (opens in a new tab)

• evidence-before-claims

  Evidence gate for security research, scanner triage, code review, and reporting. Use before confirming vulnerability impact, auth material, control results, cleanup, or root cause.

  behaviours/evidence-before-claims/SKILL.md on GitHub (opens in a new tab)

• handoff

  Write a portable handoff document so another agent can continue the current work. Use only when the work must move to a new harness, directory, repo, operator, or a forked parallel session; invoke on explicit request, not autonomously.

  behaviours/handoff/SKILL.md on GitHub (opens in a new tab)

• humanizer

  Edit stiff, formulaic or promotional prose into a natural author voice while preserving meaning. Use when humanizing a draft or revising its tone; not for detecting AI authorship.

  behaviours/humanizer/SKILL.md on GitHub (opens in a new tab)

• hypothesis-driven

  Investigate an uncertain cause using testable hypotheses and discriminating evidence. Use for persistent bugs, flaky behavior, incident diagnosis, or conflicting research observations; skip routine edits with a known solution.

  behaviours/hypothesis-driven/SKILL.md on GitHub (opens in a new tab)

• implementation-planning

  Turn settled requirements into an executable plan. Use for work with dependencies, shared-file ownership, or a handoff; skip a separate plan for a straightforward local edit.

  behaviours/implementation-planning/SKILL.md on GitHub (opens in a new tab)

• loop-control-and-pivots

  Stop unproductive retries and repeated polling. Use when the same failure recurs, a side issue consumes the task, or unfinished jobs are checked without new evidence.

  behaviours/loop-control-and-pivots/SKILL.md on GitHub (opens in a new tab)

• memory-hygiene

  Read, update, or design persistent agent memory. Use when deciding what may be stored, retrieving prior decisions, or resolving stale, conflicting, or incorrectly scoped notes.

  behaviours/memory-hygiene/SKILL.md on GitHub (opens in a new tab)

• reading-budget-discipline

  Limit context consumption when inspecting large files, tool output, logs, or collections of artifacts. Use when a targeted search or bounded extraction can answer the question without loading everything.

  behaviours/reading-budget-discipline/SKILL.md on GitHub (opens in a new tab)

• untrusted-input-hygiene

  Handle retrieved content and artifacts without promoting them into instructions. Use for prompt-injection review, external files/pages, tool results, memory retrieval, and worker reports.

  behaviours/untrusted-input-hygiene/SKILL.md on GitHub (opens in a new tab)

• verification-before-completion

  Check evidence before reporting work complete, fixed, passing, or ready. Use at a completion boundary or when later changes may have invalidated an earlier result.

  behaviours/verification-before-completion/SKILL.md on GitHub (opens in a new tab)

• software-architecture

  Design, evolve, and review software architecture, from small tools and libraries to multi-service systems. Use for module boundaries, domain models, public contracts, data ownership, quality trade-offs, architectural refactoring, and behavior-preserving simplification.

  coding-behaviours/software-architecture/SKILL.md on GitHub (opens in a new tab)

• software-guidelines

  Implement and review scoped code changes in a repository. Use for patch impact, dependent caller updates, repository conventions, and preserving unrelated work; use software-architecture for structural design and simplification decisions.

  coding-behaviours/software-guidelines/SKILL.md on GitHub (opens in a new tab)

• systematic-debugging

  Root-cause-first debugging workflow for software, exploit tooling, fuzzing harnesses, reverse-engineering helpers, C2/client code, flaky tests, crashes, races, and environment-specific failures. Use when a failure is not immediately obvious or when repeated quick fixes risk hiding the real defect.

  coding-behaviours/systematic-debugging/SKILL.md on GitHub (opens in a new tab)

• test-driven-development

  Develop behavior through a failing test or reproducer, implementation, and refactoring. Use when test-first development is requested or a new behavior or bug fix benefits from an executable regression before implementation.

  coding-behaviours/test-driven-development/SKILL.md on GitHub (opens in a new tab)

• testing-reliability

  Diagnose flaky tests, misleading mocks or fakes, sleep-based waits, brittle fixtures, test-only production hooks, weak assertions, and mutation-testing gaps. Use when CI behavior differs, tests hide defects, or coverage creates false confidence.

  coding-behaviours/testing-reliability/SKILL.md on GitHub (opens in a new tab)

• android-jni-ndk

  Kotlin/Java ↔ native (C/C++/Rust) bridging on Android: NDK setup, JNI mechanics, `System.loadLibrary`, `RegisterNatives`, `@FastNative`/`@CriticalNative`, reference hygiene, exception propagation, 16 KB page-size compliance, native crash triage. Use when building or debugging a native module, embedding a `.so` library, decoding a native ANR or SIGSEGV, or reverse-engineering an APK's native code…

  coding/android-jni-ndk/SKILL.md on GitHub (opens in a new tab)

• android-testing

  Android testing patterns for unit tests, instrumented tests, Compose UI tests, screenshot tests, and end-to-end journeys. Use when setting up JUnit4/JUnit5 + Robolectric, wiring Hilt/Koin for tests, choosing between Espresso and Compose Test APIs, adding Roborazzi/Paparazzi/Dropshots screenshot tests, or diagnosing flaky Android tests.

  coding/android-testing/SKILL.md on GitHub (opens in a new tab)

• asm-patterns

  Assembly language patterns, calling conventions, and code structure for x86-64 and ARM64. Use when writing, reviewing, or generating .asm/.s/.S files; when implementing functions that interoperate with C/system code; or when establishing correct prologues, epilogues, stack management, SIMD loops, syscall stubs, or PIC data access.

  coding/asm-patterns/SKILL.md on GitHub (opens in a new tab)

• asm-performance

  Assembly performance optimization workflow: collect compiler-emitted ASM, classify bottlenecks with TMA, audit for codegen issues (bounds checks, register spills, dependency chains, missed vectorization, memory traffic, bad instruction selection, store-forwarding stalls, frontend pressure, data layout), apply one change at a time, measure, and report. Use after profiling confirms ASM is the bottl…

  coding/asm-performance/SKILL.md on GitHub (opens in a new tab)

• asm-testing

  Assembly code testing, debugging, and bug-hunting workflow for hand-written and injected assembly: C/Go harness testing, GDB/LLDB/WinDbg/x64dbg verification, objdump structural analysis, Python helpers (Capstone/Unicorn/Keystone), Frida dynamic instrumentation, offensive ASM debugging (trampolines, callgates, syscall stubs, stack spoofing, PIC shellcode), reverse engineering own binaries, and com…

  coding/asm-testing/SKILL.md on GitHub (opens in a new tab)

• c-patterns

  C language patterns and best practices for safe, maintainable C: ownership, API contracts, error handling, integer safety, portability, and concurrency boundaries. Use when writing or reviewing C code (C11+), designing module interfaces, refactoring legacy C, or hardening low-level code paths.

  coding/c-patterns/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• superpowersby obra An agentic skills framework & software development methodology that works. 313k stars · 15 skills
• agent-skillsby addyosmani Production-grade engineering skills for AI coding agents. 114k stars · 25 skills
• skillsby google Agent Skills for Google products and technologies 22.4k stars · 30 skills
• garden-skillsby ConardLi ConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more. 14.1k stars · 6 skills
• ui-skillsby ibelick Skills for Design Engineers 10.7k stars · 9 skills
• Claude-Redby SnailSploit claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md fil… 10.4k stars · 30 skills