Explore skills
Showing 29851–29880 of 71536 skills
Review a diff against dynamic-neural-field-composer's own standards - backwards compatibility, Clean Code, tools/ helper reuse, C++20 idiom, hot-path performance, and test coverage. Use before opening a PR or when asked to review a branch or change.
Jgocunha/dynamic-neural-field-composer
Stars: 19Claude CodeCodexAdd a new agent source/provider to agent-office (e.g. LangGraph, OpenAI Agents SDK, OpenTelemetry GenAI spans, Claude Code hooks). Use when asked to support or ingest agents from another framework or data source.
arxdsilva/agent-office
Stars: 9Claude CodeCodexAdd or extend a driven port and its adapter in agent-office's hexagonal core — storage/persistence, OS integration, clock/scheduling, external services, a new notification channel. Use whenever the core needs something new from the outside world.
arxdsilva/agent-office
Stars: 9Claude CodeCodexChange agent-office's Blender-built 3D assets — the atrium, Main Street, wings and their themes, garden, cap, furniture kit, lighting/bake, the character mesh, rig or animation clips, the manifest or the graphics contract. Use for any edit under assets/ (assets/blender/**, assets/build.mjs, assets/validate*.ts), to docs/graphics-contract.md, or for anything in packages/web/public/assets/.
arxdsilva/agent-office
Stars: 9Claude CodeCodexChange agent-office's desktop shell — tray menu, native notifications, settings, IPC channels, windows, the auto-updater, packaging/installers or icons. Use for edits under packages/desktop/ (main, preload, electron-builder.yml, e2e) or to core domain tray/attention/update/settings logic.
arxdsilva/agent-office
Stars: 9Claude CodeCodexChange how users talk to agents in agent-office — message states, InboxService, the HTTP inbox/replies routes, the IPC send path, the chat panel, the Claude Code hook (hooks/agent-office-hook.mjs), its wrapper (FsHookRunner) or HookService/installer. Use for edits in core message/hook domain, inbox-service, http-api, ipc-api, panel adapters, hooks/ or scripts/hook-install.ts.
arxdsilva/agent-office
Stars: 9Claude CodeCodexChange agent-office's public contracts — AgentEvent fields, inbox/reply/messages HTTP APIs, the IPC contract (AgentOfficeApi, ServerMessage), or the hook's output. Use whenever packages/shared/src/{protocol,desktop-api,ipc-channels}.ts or an /api route's request/response shape changes.
arxdsilva/agent-office
Stars: 9Claude CodeCodexLaunch the agent-office desktop app locally and verify a change in the real UI (screenshot). Use when asked to run, start, demo or screenshot the app, or before calling any scene/UI/desktop change done.
arxdsilva/agent-office
Stars: 9Claude CodeCodexChange the agent-office 3D scene at runtime — which wing, desk or room an agent uses, agent behavior and choreography, characters and animation playback, labels, lighting/render pipeline and quality presets, camera or walk controls. Use for any edit to packages/web/src/app/{building,seating,reservations,behavior,navigation,choreography,layout}.ts, packages/web/src/adapters/three/*, or shared/src/grouping.ts. For the Blender assets themselves use asset-change.
arxdsilva/agent-office
Stars: 9Claude CodeCodexDirect a claim-driven research experiment project from post-Idea intake through method realization, prioritized evidence collection, Human Gates, and Evidence Freeze. Use for scientific planning, state transitions, queues, budgets, or recovery; not for running code or independently auditing results.
cpt13-g/build-research-evidence
Stars: 54Claude CodeCodexImplement and execute approved research Experiment, Tuning, or Design Cards with reproducible logs, metrics, environment, and artifacts. Use for bounded coding, debugging, and runs; not for changing claims, priorities, budgets, or the Research Spine.
cpt13-g/build-research-evidence
Stars: 54Claude CodeCodexValidate and scientifically interpret completed research runs, including negative, null, boundary, confounded, failed, and inconclusive outcomes. Use after execution to assess evidence and claim impact; not to edit methods or schedule experiments.
cpt13-g/build-research-evidence
Stars: 54Claude CodeCodexAudit recent high-relevance papers from a target venue to identify claim-relevant experimental evidence gaps after core P0 results exist. Use for venue completeness and reviewer-risk analysis; not for redefining the research question or running experiments.
cpt13-g/build-research-evidence
Stars: 54Claude CodeCodexUse when reverse-engineering or detecting malware — static triage + capa/YARA-X, emulation/DBI/.NET unpacking, dynamic/fileless/Volatility 3 memory analysis, C2 config extraction (Cobalt Strike/CAPE), C2 traffic detection (JA4+, beaconing)
hypnguyen1209/offensive-claude
Stars: 421Claude CodeCodexUse when pentesting an Android/iOS app — Frida 17 instrumentation, SSL-pinning & root/jailbreak bypass, Android 14/15 CA injection, exported-component/content-provider abuse, deep-link/WebView chains, biometric bypass, Flutter/React-Native RE
hypnguyen1209/offensive-claude
Stars: 421Claude CodeCodexUse when running a full red-team engagement end-to-end — initial access, persistence, privilege escalation, defense evasion, C2 infrastructure, EDR bypass, living-off-the-land
hypnguyen1209/offensive-claude
Stars: 421Claude CodeCodexUse when auditing source code for vulnerabilities — drive CodeQL/Semgrep/Joern to taint untrusted data source-to-sink across injection, memory safety, deserialization/prototype-pollution, secrets/crypto/authz/race, and supply-chain risks
hypnguyen1209/offensive-claude
Stars: 421Claude CodeCodexPavedPath Code is the code-focused edition of PavedPath. It helps agents solve software engineering problems by finding proven implementation paths from GitHub repositories, issues, pull requests, discussions, code examples, release notes, and open-source evidence.
Jia-Ethan/pavedpath-code
Stars: 439Claude CodeCodexProteins, drug targets and peptides. Look up protein function, location and diseases (UniProt), a drug's targets, mechanism of action and indications (ChEMBL), protein interaction partners (STRING), fetch protein sequences, compute sequence properties and align sequences (Biopython). Use for any question about targets, mechanisms, protein biology or protein/peptide sequences.
ScilifelabDataCentre/scilifelab-ai-agent-mcp-workshop-2026-11-02
Stars: 4Claude CodeCodexSmall-molecule cheminformatics with RDKit. Resolve compound names or IDs to SMILES, remove salts, compute physicochemical properties, check drug-likeness rules (Lipinski, Veber), compare structural similarity (Tanimoto) and search for substructures. Use for any question about a compound's structure, properties, drug-likeness or analogues.
ScilifelabDataCentre/scilifelab-ai-agent-mcp-workshop-2026-11-02
Stars: 4Claude CodeCodexSearch PubMed for evidence with the NCBI LitSense2 semantic-search API. Returns passages from papers with their PMIDs. Use whenever an answer needs published evidence or citations, e.g. mechanism of action, resistance, clinical findings, or PK parameters to feed into a simulation.
ScilifelabDataCentre/scilifelab-ai-agent-mcp-workshop-2026-11-02
Stars: 4Claude CodeCodexPharmacokinetic / pharmacodynamic simulation with SciPy. Concentration-time profiles for repeated oral or IV dosing (Cmax, trough, AUC, half-life, steady state), Emax effect models, dose finding, regimen comparison, loading or missed doses and custom compartment models. Use for any dosing, exposure or target-coverage question.
ScilifelabDataCentre/scilifelab-ai-agent-mcp-workshop-2026-11-02
Stars: 4Claude CodeCodexUse the Crossplane v2 OKF MCP server as the exclusive external knowledge source for Crossplane v2 core, API, Composition, provider, function, runtime, Upjet, security, multi-tenancy, and example facts. For an external service's behavior or security guidance, use its primary vendor documentation as defined by the evidence boundary.
jkroepke/okf-crossplane-v2
Stars: 37Claude CodeCodexDebug a reversible-circuit primitive that is value-exact in isolation but leaves identical classical, phase and ancilla dirt on every Fiat-Shamir shot once wired into the full circuit. Run a three-step falsifier ladder first: stale stream-specific optimization indexes, free-pool qubit-ID aliasing, then the measurement-vent discharge target. Use before blaming the primitive's math.
odinfree/storm-ecdsa-harness
Stars: 4Claude CodeCodexRun production GPU jobs on Google Colab (G4 = RTX PRO 6000 Blackwell 96 GB by default; H100/A100/L4/T4 also available on a paid plan) from a local machine, with the signed-in `colab` CLI and the `colab-lane` wrapper (tools/wolkeschieber in this repository). Use when a lane needs to run, compile or benchmark something on a cloud GPU (CUDA, torch, nonce/prescreen kernels, Rust builds). Jobs run until done, then results are downloaded and the runtime is stopped. Covers spend, auth, disconnect handling and the exact failure semantics.
odinfree/storm-ecdsa-harness
Stars: 4Claude CodeCodexAdversarial review before you commit. Before a route change, paid CPU or GPU compute, or a worker handoff, an independent worker from another lab tries to kill the route. The output is a falsifiable decision (proceed, measure, park, kill or human review) plus the hidden assumption that could make it wrong. Advisory only.
odinfree/storm-ecdsa-harness
Stars: 4Claude CodeCodexIterate on an ecdsa.fail route until a fresh official `ecdsafail run` says it is better, never on a self-reported number, and keep a route journal (tried, killed, next cut) that survives context compaction. Use for "loop this route", "run it to a verified win", "what have I already tried". Adapted from tanweai/pua (discipline only).
odinfree/storm-ecdsa-harness
Stars: 4Claude CodeCodexSearch academic literature through the Elicit API: papers, clinical trials, reports, systematic reviews and Research Agent sessions. Use when a question needs published evidence or an outside, literature-backed view. Needs your own Elicit API key.
odinfree/storm-ecdsa-harness
Stars: 4Claude CodeCodexBuild and validate a fast, exact local copy of a benchmark's official evaluator: same inputs, same counts, same score, proven by a differential fuzz test and a reproduced graded log. Use when the official judge is too slow, too memory-hungry or too opaque to sit inside the edit loop of an optimization campaign (circuits, provers, gas, proof size), when many candidates must be scored per day, or when a failure-rate estimate needs fresh samples the judge cannot give.
odinfree/storm-ecdsa-harness
Stars: 4Claude CodeCodexBefore porting a module from another source tree, measure whether and at what cost it builds under your resource cap (fit probe), then import it verbatim through an adapter that remaps its resources and asserts its contract, instead of rewriting it. Use when a rival's or a library's routine is cheaper than yours, is self-contained, and shares your artefact's op format: a circuit gadget, a prover gadget, a contract library under a size cap.
odinfree/storm-ecdsa-harness
Stars: 4Claude CodeCodex