AI & ML

privasys Skill

Turn "make me an agent that…" into a folder in the user's own Drive that the harness runs as a workspace, unattended when it has a trigger. Asks for each consent in the conversation. Never edits an agent from inside one of its scheduled runs.

ucsandman Bundle

Apply DashClaw governance: guard decisions, approvals, action recording, and agent session lifecycle.

franck-dev-hub Skill

Use when asked to review, validate, audit or check a Claude skill (SKILL.md) against the Agent Skills specification and authoring best practices, or after creating or editing a skill.

jiangeplus Bundle

Equity valuation modeling: three-statement linked financial model, WACC, DCF, comparable-company multiples, sensitivity and scenario grids, and target price derivation. TRIGGER when: the user asks to build a DCF or financial model, calculate WACC, run comps / relative valuation, do sensitivity or scenario analysis, or derive a price target. DO NOT TRIGGER for: earnings commentary (use fundamentals-analysis), writing the report itself (use research-report), or position sizing (use risk-monitoring). 触发词：DCF、现金流折现、WACC、财务建模、三表模型、可比估值、comps、相对估值、敏感性分析、目标价推导。

jiangeplus Bundle

增强提示词（Prompt Enhancement）Skill。对用户提供的模糊、不清晰、有歧义或存在错误的指令进行改写与增强，使其更清晰、更具体、更可执行。触发词：增强提示词、优化提示词、改写指令、润色提示词、enhance-prompt、prompt enhancement。适用场景：用户说「帮我把这个需求描述改清楚」「优化一下这段指令」「增强提示词」，或用户在 /enhance-prompt 命令后附带待改进的指令内容时。

ckodex-labs Bundle

A pre-existing Agent Skills v1 skill that ships only SKILL.md. Used by the ckodex-skill-tools self-test to exercise the migration path.

ckodex-labs Bundle

Template for Claude Code Agent Skills — demonstrates the deterministic JSON envelope contract, the dual-channel exit-code split (stdout exit 0 for success or retriable error; stderr exit 1 for fatal config error), anchor-term routing, token masking, HTTPS-only enforcement, --dry-run default on write paths, and the three-test-gate CI surface (structure + scripts + agent). Adapt by renaming the skill and replacing the hello script with domain-specific scripts that follow the same envelope contract.

shoonenterprises Skill

Audit the citations in a finished research report, memo, or agent deliverable before you declare it complete. For every cited source, verify the URL resolves and check that the quoted text you attribute to it actually appears verbatim on the fetched page — then attach an Ed25519-signed audit receipt that anyone can verify offline. Use this skill as a pre-delivery verification gate whenever your work cites web sources: deep research reports, literature reviews, briefing memos, fact-checked summaries, or any document where silent citation failures (dead links, quotes that don't exist on the page) would undermine trust. Fix or drop every failing citation before delivery. Free pilot service; no API key required.

yltw27 Bundle

Explicit-only audit of local coding-agent setup, installed skills, MCP servers, plugins, and recent usage signals. Use only when the user explicitly invokes $agent-hygiene.

omarchyfans Skill

Chief of staff on an Omarchy desktop: see every agent, its tokens and cost, delegate work to bigger models (API, OAuth, GPU endpoints), read results, stop or remove agents.

jcaraballo113 Bundle

AI-guardrail linting — size/complexity caps that force extraction over sprawl, no comments, named constants, everything an error, and the config protected from agent edits by a deny hook. Ecosystem-agnostic philosophy with per-ecosystem implementations (ESLint for JS/TS today). Standalone-safe on existing repos. Use when the user says "setup linting", "add lint guardrails", or via setup-tooling.

jcaraballo113 Bundle

Implement several ready tickets at once — one fresh implementer per ticket in its own worktree, landed in a decided order, then a fresh agent's cleanup and code-review over the whole landing.

chambear2809 Bundle

Use when the user asks about MLTK, Splunk AI Toolkit, Machine Learning Toolkit, PSC, Python for Scientific Computing, DSDL, Deep Learning Toolkit, Splunk anomaly detection assistants, AI Toolkit Agent Launchpad or the earlier Agent Builder preview, the `aiagent` command, Cisco Time Series Model, Cisco Deep Time Series Model, Smart Alerts Assistant, or AI/ML product coverage outside Splunk AI Assistant, including Cisco Data Fabric requests about AI Toolkit or machine-data model workflows. Install, render, validate, and audit Cisco Data Fabric AI Toolkit and Splunk-owned AI and machine-learning workflows beyond Splunk AI Assistant: Splunk AI Toolkit / MLTK (`Splunk_ML_Toolkit`), Python for Scientific Computing (PSC), Splunk App for Data Science and Deep Learning (DSDL), MLTK anomaly workflows, LLM/`ai` command readiness, external model runtimes, and legacy anomaly app migration.

chambear2809 Bundle

Use when the user asks to accelerate a CIM data model, constrain CIM data model indexes, map data to CIM with tags and eventtypes, fix CIM compliance, or manage datamodels.conf for CIM or custom data models. Not for Enterprise Security-specific acceleration, which lives in splunk-enterprise-security-config. Render, validate, and apply Splunk Common Information Model (CIM) data model governance: install handoff for the CIM add-on (Splunk_SA_CIM), data model acceleration settings, allowed-index constraint macros (cim_<model>_indexes), and CIM eventtype/tag mapping to make sourcetypes CIM-compliant, with tstats validation.

chambear2809 Bundle

Use when the user asks to install, configure, prepare, or validate PCI Compliance for Splunk. Render, install, and validate Splunk App for PCI Compliance readiness, including package delivery, cardholder data environment index and macro intake, Enterprise Security or standalone installer selection, CIM/data-model prerequisites, roles, reports, dashboard evidence, and dependency handoffs.

chambear2809 Bundle

Use when deploying, upgrading, configuring, or validating DefenseClaw on an AMD Ryzen AI or other Lemonade-backed deskside. Install or upgrade the official Cisco AI Defense DefenseClaw release on a Linux Lemonade deskside, select a local Qwen model, configure the stable OpenAI-compatible API, wire the supported Codex hook connector, and verify observe or action enforcement.

chambear2809 Bundle

Use when users need Cisco Data Fabric architecture, feature or product coverage, readiness assessments, gap analysis, machine-data activation, federation targets, storage tiering, AI-ready data, or AgenticOps data foundation requests. Distinguish this architecture from a single product, package, entitlement, or direct API. Research, map, render, doctor, validate, and safely delegate complete Cisco Data Fabric adoption plans across Splunk data management, Edge Processor, Ingest Processor, SPL2, Federated Search, Machine Data Lake, Data Catalog, Splunk indexes and external stores, AI Toolkit and hosted models, Agent Builder, MCP Server, AI Canvas, context, governance, and cross-domain consumers.

chambear2809 Bundle

Use when the user asks to manage universal forwarder or heavy forwarder fleets, create serverclass.conf, configure deploymentclient.conf, or prepare Splunk 10.x Agent Management / legacy Deployment Server workflows. Render, preflight, apply, and validate Splunk Enterprise agent management assets for deployment-server style server classes, deployment apps, and deployment clients.

chambear2809 Bundle

Use when the user asks to investigate WideField findings, audit identity threat coverage, build remediation packets, or validate OAuth/NHI/AI-agent identity risks without destructive remediation. Diagnose WideField identity threat coverage for OAuth token abuse, rogue or over-privileged apps, non- human identity ownership, MFA and credential posture, AI-agent identities, and anomalous sessions using read-only Splunk, Okta, and evidence checks.

chambear2809 Bundle

Use when adding Galileo OTLP fan-out to a Lemonade collector, capturing agent/workflow/tool traces around Lemonade, avoiding duplicate LLM records, or validating privacy-safe Galileo ingestion from an AMD Ryzen AI host. Instrument Lemonade Server inference and OpenAI-compatible calling applications for Galileo Observe while preserving Splunk OpenTelemetry delivery, privacy policy, rollback, and end-to-end readback.

chambear2809 Bundle

Use when the user asks about Cisco Enterprise Networking app, cisco-catalyst-app, Catalyst dashboards, ISE dashboards, SD-WAN dashboards, or Cyber Vision dashboards. Automate Cisco Enterprise Networking for Splunk Platform (cisco-catalyst-app) setup. Configures index macros, sourcetype macros, saved searches, data model acceleration, and validates dashboards.

chambear2809 Bundle

Use when the user asks for AppDynamics SAP Agent, ABAP Agent, HTTP SDK, SNP CrystalBridge Monitoring, BiQ Collector, SAP NetWeaver transports, SAP authorization runbooks, local or gateway HTTP SDK deployment, or SAP release or metric validation. Render, validate, and hand off Splunk AppDynamics SAP Agent workflows, including SAP Agent, ABAP Agent, HTTP SDK, SNP CrystalBridge Monitoring, BiQ Collector, local and gateway HTTP SDK deployment, SAP NetWeaver transports, SAP authorization checks, Controller node registration, SAP Agent release notes, and SAP metric validation.

chambear2809 Bundle

Use when the user asks for AppDynamics Java dual-agent, Java Dual Signal mode, AGENT_DEPLOYMENT_MODE=dual, -Dagent.deployment.mode=dual, Java OTLP export to a local collector, or coordinated collector-first then Java restart rollout on local or SSH hosts. Render, validate, preflight, apply, and rollback production Java Dual Signal AppDynamics agent configuration.

chambear2809 Bundle

Use when the user asks for AppDynamics Database Visibility, Database Agent, database collector creation or updates, Database Visibility API payloads, DB credential redaction, DB server validation, DB node validation, or database event checks. Render and validate Splunk AppDynamics Database Visibility workflows, including Database Agent readiness, Database Visibility API collector CRUD, file-backed database secrets, DB server, node, metric, and event validation.

chambear2809 Bundle

Use when instrumenting Codex itself for Splunk Observability or AI Agent Monitoring. Render, validate, diagnose, and safely apply Splunk Observability instrumentation for Codex CLI profiles, OTel destinations, JSONL runtime helpers, and optional hooks.

chambear2809 Bundle

Use when planning Splunk Observability instrumentation for Codex or future coding agents without applying agent-specific config. Route coding-agent telemetry requests to the right child skill and render a non-mutating orchestration plan.

jagones84 Skill

Use when auditing disk usage on Windows or Linux and suggesting what a human should review to reclaim space without changing files automatically, especially for caches, model files, trash, and partial downloads.

wundercorp Bundle

Join a Google Meet call, transcribe live captions, optionally speak in realtime, and do the followup work afterwards. Use when the user asks the agent to sit in on a meeting, take notes, summarize, respond in-call, or action items from it.

cesiumgs Skill

CesiumJS spatial math - Cartesian3, Cartographic, Matrix4, Quaternion, Transforms, Ellipsoid, BoundingSphere, projections, coordinate conversions. Use when converting between coordinate systems, computing positions on the ellipsoid, performing spatial intersection tests, building model matrices, or working with geographic projections.

elevenlabs Bundle

Build voice AI agents with ElevenLabs. Use when creating voice assistants, customer service bots, interactive voice characters, or any real-time voice conversation experience, and when configuring an agent's tools, workflows, or procedures, including creating, editing, compiling, and publishing procedure drafts on an agent branch over the SDKs or REST API.

elevenlabs Bundle

Add real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine. Use when building Speech Engine servers, WebSocket handlers, WebRTC browser clients, conversation token endpoints, interruption-aware streaming responses, or voice-enabled chat agents that connect developer-owned server logic to ElevenLabs speech-to-text and text-to-speech.

wundercorp Skill

Karpathy's LLM Wiki: build/query interlinked markdown KB.

wundercorp Bundle

Fine-tune large LLMs with LoRA on limited GPU memory.

elevenlabs Skill

Update ElevenLabs agent skills from a merged weekly changelog in elevenlabs-dx, then open a pull request in elevenlabs/skills. Trigger after a changelog merges to main on elevenlabs-dx, or when asked to update skills from changelog YYYY-MM-DD.

wundercorp Skill

List, auth, and call MCP servers/tools from the terminal.

wundercorp Bundle

Embedding database for RAG and semantic search.