Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 961 files from 2 125 authors, of which 68 678 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.
Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, \"model-check this race\", \"prove this invariant\", or when concurrency, retries, state machines, parsers, or unsafe code need more than tests.
Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, \"make a control skill for this repo\", or when a project has no scripted way to prove UI/CLI/service behavior.
Restate in your own words what you think the user's goals are and what problem they're trying to solve. Use for /in-your-own-words.
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions. Use for /figure-it-out or 'figure it out'.
Use for \"interrogate\", \"adversarial review\", \"multi-model review\", \"challenge this\", \"stress test this code\", \"find blind spots\", or \"tear this apart\". Multiple LLM reviewers challenge changes from independent angles.
Catch the user up like /ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /ketchup-video.
>- Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /maintain-formal-verification-skill, \"is the model still true to the code\", or after merges and refactors that touched verified code without rechecking it.
Catch the user up on what changed in this chat since their last message, in plain words and small visuals. List every item waiting on them with what they need to decide it from the reply alone. Use for /ketchup.
Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or \"audit the verify skill\".
Apply when two or more fixes that share one premise have failed the same gate. Write the premise down and test it directly before you write another fix that assumes it.
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.
Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.
Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.
Apply when debugging. Trace each symptom back to the first place the system went wrong and fix it there. A guard is a fix only when the state it handles is legitimate.
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files.
Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.
Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.
Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.
Apply when tempted to ask 'should I do X?' on reversible work.
Apply when integrating a new requirement into an existing design.
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.
Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, exhaust variants, derive from authoritative schemas.
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming work.
Configure which models pstack uses per role and at what reasoning budget. Detects your available models and writes an always-applied rule that overrides the skill defaults. Use for /setup-pstack, "configure pstack models", "pstack budget", or changing pstack's model choices.
Make a task deeper, not bigger, then rewrite the prompt. Use for /sharpen.
Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.
Draw how any system moves between states, such as a product flow, a protocol, or a service, as a Mermaid statechart from a TLA+ model. Each bug is a numbered path with blue borders to a state that breaks a rule. Use for /statechart, to show a bug as a path through states, or to turn an agreed chart into a TLA+ skeleton.
Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
Cut AI tells from any writing.
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
| Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
| Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
>- Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software, SDKs, GPUs, Jetson/JetPack/L4T/BSP/SDK Manager/driver/flashing/setup, CUDA, NIM, NeMo, Omniverse/OpenUSD/SimReady, RAPIDS/cuDF, cuPyNumeric, cuOpt, Dynamo, Holoscan, TensorRT, DeepStream, VSS, TAO, NGC/NVCF. Do not use for generic non-NVIDIA route, optimize, deploy, AI, video, data, or infrastructure tasks.
>-
Install and verify cuPyNumeric for Python — requirements, commands, verification. Source builds are out of scope.
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/GPU variants. Use when no single-call loader fits, including when per-shard row counts differ across files. Prefer cupynumeric.load or legate.io.hdf5.from_file when they apply.
Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.
Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.
Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.
Used for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification or clinical clearance.
Stage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest. NOT for scoring (use /digital-health-clinical-asr-eval).
Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).
Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR auth (/riva-asr).
Claude Skills — questions
Answers built from the skills we actually parsed.