515 skills · sorted by relevance
Assess iOS apps from IPA acquisition through file inspection and runtime testing. The skill helps uncover embedded credentials, insecure network settings, and app link handling issues using tools such as Frida, objection, and binary analysis utilities.
Inspect NTLM authentication responses from public IIS, SharePoint, and Exchange services to identify exposed internal domains, server names, and timestamps. Assess the disclosure in context and prepare reproducible evidence without completing authentication.
Examine a plan or design through focused questions, each with a recommended answer. Work through connected decisions to reach shared understanding, using codebase exploration to resolve questions that the code can answer.
Create bash scripts for routine Linux administration, including backups, resource monitoring, user management, and log analysis. Templates also cover scheduled tasks, file cleanup, encryption, and network checks, providing starting points for automating recurring maintenance.
Verify an engine app without a real terminal and record the full interaction as video. Produce a summary page with a clickable timeline, pass or fail checks, and snapshots to review the tested behavior.
Manage a project's stored materials through inventory, migration, archiving, and ranking based on verified source reads. Changes follow owner approval, preserve material references, and include validation records and rollback procedures.
Use this skill when the user is doing hands-on DOCA AES-GCM work on a BlueField DPU or ConnectX NIC — configuring `doca_aes_gcm_task_encrypt` / `_task_decrypt`, querying `doca_aes_gcm_cap_*` for per-key-type (only `DOCA_AES_GCM_KEY_128` / `_256` — AES-192 not supported) and per-task support, sizing plaintext against the max-buf cap, setting source / destination mmap permissions, validating with a NIST GCMVS or RFC 5288 vector, or debugging DOCA_ERROR_* including the security-critical tag-verification-failed outcome on decrypt. Trigger even when the user does not explicitly mention "DOCA AES-GCM" or "AEAD" — typical implicit phrasings: "decrypt completion IO_FAILED", "auth tag isn't verifying", "NOT_PERMITTED on my encrypt buffer", "is AES-192-GCM on this BlueField" (no), or "encrypted record came back tampered". Refuse and route elsewhere for non-GCM AES modes (CBC / CTR / XTS — CPU OpenSSL), key management (KMS / HSM / rotation), SHA (doca-sha), or general AEAD background.
The English summary is being prepared. Showing the original description.
SUPERSEDED by /claudex-loop (formerly /crucible; its docs-aware mode covers this variant) — prefer that skill unless you explicitly want this one. Two-act plan hardening with living documentation. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan, one question at a time, challenging it against your project's existing domain model and glossary (CONTEXT.md), sharpening fuzzy terms, stress-testing with concrete scenarios, cross-referencing code, and updating CONTEXT.md + ADRs inline as decisions crystallise. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE), Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-with-docs-codex", "grill me against the docs then have codex review", "stress-test this against our domain model then get a second model on it", or is about to build something high-stakes in a project with established terminology/ADRs and wants alignment, documentation, AND a cross-model sanity check. Builds on Matt Pocock's grill-with-docs (MIT). NOT for reviewing already-written code (use /codex:review) and NOT for trivial changes.
The English summary is being prepared. Showing the original description.
SUPERSEDED by /claudex-loop (formerly /crucible; adds a Phase 0 research/recon pass + rebuilt interview) — prefer that skill unless you explicitly want this one. Two-act plan hardening. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan or design, one question at a time, recommending an answer for each and exploring the codebase when it can answer itself, until every branch of the decision tree is resolved. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE), Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-me-codex", "grill me then have codex review", "grill me and stress-test the plan", "interview me about this plan then get a second model on it", or is about to build something high-stakes (auth, schema, concurrency, migrations, payments) and wants both alignment AND a cross-model sanity check before implementation. Builds on Matt Pocock's grill-me (MIT). For the docs-aware variant use /grill-with-docs-codex; if you already have a plan and want only the Codex review use /codex-review. NOT for reviewing already-written code (use /codex:review) and NOT for trivial changes.
The English summary is being prepared. Showing the original description.
Diagnoses and resolves Amazon RDS for Oracle connectivity, authentication, networking, and driver troubleshooting. Applicable to any RDS-for-Oracle question including connecting a Python Lambda to RDS Oracle in a VPC with pooling and cold-start optimization, EKS pods to RDS Oracle via the Secrets Manager CSI driver with IRSA and SecretProviderClass, ORA-12170 cross-VPC timeouts from EC2, DPI-1047 cannot-locate-64-bit-Oracle-Client errors, and Oracle Connection Manager (CMAN) on EC2 as a proxy with HA across two AZs. Covers python-oracledb thin vs thick mode, init_oracle_client, RDS Proxy does NOT support RDS Oracle, port 1521, VPC peering, Transit Gateway, Kerberos with AWS Managed Microsoft AD, SSL/TLS/NNE, SSM port forwarding, EC2/ECS Fargate/EKS/Lambda, SQL Developer/DBeaver/Toad/SQLcl, and Secrets Manager.
The English summary is being prepared. Showing the original description.
Amazon Redshift is NOT PostgreSQL; corrects LLM mistakes; covers SQL, metadata, connectivity/auth, storage, query performance, and operations. Applies ONLY to Redshift (provisioned or Serverless). Pushes back on: CREATE INDEX, string_agg, pg_catalog, text type, SERIAL, stl_query. Triggers on: Redshift SQL, Redshift CREATE TABLE, Redshift COPY/UNLOAD, slow or suddenly slow Redshift query, EXPLAIN plan, queue wait, stale statistics/ANALYZE, result cache, Redshift permission denied, Redshift disk full, storage growth, snapshot/backup cost, ghost rows/bloat, VACUUM, spill to disk, distribution skew, Redshift system views, QUALIFY, PIVOT, MERGE, materialized views, Redshift Data API (Python/boto3), Redshift workload management (WLM), concurrency scaling, Redshift resize, Spectrum, awsdatacatalog, connection failures (SSL/TLS, ODBC/JDBC, connection limit), IAM/SAML federation, IAM Identity Center, datashares. Does NOT apply to: S3 policies, Athena, Glue/Iceberg outside Redshift, Aurora, RDS, DynamoDB.
The English summary is being prepared. Showing the original description.
Reverse shell techniques playbook. Use when establishing remote shells including language one-liners, encrypted shells (OpenSSL/socat/ncat), web shells, PTY upgrades, file transfer methods, PowerShell shells, and Windows payload generation.
The English summary is being prepared. Showing the original description.
Android pentesting playbook. Use when testing Android applications for SSL pinning bypass, exported component abuse, WebView vulnerabilities, intent redirection, root detection bypass, tapjacking, and backup extraction during authorized mobile security assessments.
The English summary is being prepared. Showing the original description.
An overview of the core model API of SeisBench, a Python framework for training and applying machine learning algorithms to seismic data. It is useful for annotating waveforms using pretrained SOTA ML models, for tasks like phase picking, earthquake detection, waveform denoising and depth estimation. For any waveform, you can manipulate it into an obspy stream object and it will work seamlessly with seisbench models.
The English summary is being prepared. Showing the original description.
Expert network engineer specializing in modern cloud networking, security architectures, and performance optimization. Masters multi-cloud connectivity, service mesh, zero-trust networking, SSL/TLS, global load balancing, and advanced troubleshooting. Handles CDN optimization, network automation, and compliance. Use PROACTIVELY for network design, connectivity issues, or performance optimization.
The English summary is being prepared. Showing the original description.
Interview the user relentlessly about a plan, design, or topic, checkpointing every answer to a brainstorm file so nothing is lost. Use when the user wants to stress-test a plan, get grilled on a design, run a brainstorm or discovery session, extract what's in their head into a doc, build up their AI OS context over time, or says "grill me".
The English summary is being prepared. Showing the original description.
Generate cloned narration for the content workspace. Use local IndexTTS2 with the canonical lossless Pluviobyte reference for every local video, voice audition, digital-human narration, and subtitle-ready audio render. Preserve MiniMax only for public-facing articles or tutorials that teach users to connect through the relay service; never use MiniMax for local video production.
The English summary is being prepared. Showing the original description.
Investigate and resolve Cloudflare configuration issues using API-driven evidence gathering. Use when troubleshooting ERR_TOO_MANY_REDIRECTS, SSL errors, DNS issues, or any Cloudflare-related problems. Focus on systematic investigation using Cloudflare API to examine actual configuration rather than making assumptions.
The English summary is being prepared. Showing the original description.
Write calm, businesslike co-parenting messages that keep the focus on the kids and stay out of the old conflict — for scheduling, expenses, decisions, and hard topics. Use when asked to write a message to my co-parent, respond to my ex about the kids, co-parenting communication help, or how to reply without a fight. Produces a message drafted in a neutral, child-centered tone (the 'BIFF'-style brief/informative/friendly/firm approach), the bait removed, a clear ask or answer, and a note on documentation — steering away from anything that escalates. Not legal advice.
The English summary is being prepared. Showing the original description.
Sets up email on the user's own domain, such as hello@yourdomain.com, a real mailbox that sends and receives, with DropTheHassle. Use when the user wants domain email, a professional email address, an inbox like info@ or hello@ on their domain, or asks "can I get email on my domain". Checks the domain is active with site_status, then hands the human a checkout.stripe.com payment link from get_email_checkout_link (main inbox €5 / $5 a month). The agent never pays and never reads the mail.
The English summary is being prepared. Showing the original description.
Create or update OMA skills in the SSL-lite human-readable format. Use when adding a new `.agents/skills/{skill-name}/SKILL.md`, converting an existing skill to the standardized Scheduling / Structural Flow / Logical Operations / References structure, or validating whether a skill has enough routing, execution, resource, and safety detail.
The English summary is being prepared. Showing the original description.
Identify differentially bound regions across CLIP-seq conditions (knockdown vs control, treatment vs vehicle, disease vs healthy) using DEWSeq (sliding-window DESeq2), Flipper (Skipper-downstream), ASpeak, edgeR, or limma-voom. Use when computing condition-level changes in RBP binding intensity, choosing peak-level vs window-level vs crosslink-level testing, designing replicate experiments, or distinguishing biological binding shifts from technical confounders.
The English summary is being prepared. Showing the original description.
Preprocess CLIP-seq reads (eCLIP, iCLIP, iCLIP2, iCLIP3, irCLIP, PAR-CLIP, FLASH) with protocol-specific UMI extraction, adapter trimming, length filtering, and post-alignment PCR-duplicate collapse. Use when raw CLIP FASTQ must be turned into deduplicated, crosslink-preserving BAM input for peak calling; choosing between two-pass and single-pass adapter trimming; deciding minimum read length; or mapping UMI patterns to specific eCLIP/iCLIP/iCLIP2/iCLIP3 library preps.
The English summary is being prepared. Showing the original description.
Profiles RNA-binding protein targets without antibody or UV crosslinking using STAMP (APOBEC1-RBP fusion, C-to-U editing), scSTAMP (single-cell), TRIBE/HyperTRIBE (ADAR-RBP, A-to-I editing), DART-seq (APOBEC1-YTH for m6A), or Bullseye/SAILOR edit-site detection pipelines. Use when antibody is unavailable or specificity is doubtful, when single-cell RBP profiling is needed (scSTAMP), or when in vivo RBP profiling without UV is preferred.
The English summary is being prepared. Showing the original description.