Loading...
Loading...
Found 2,026 Skills
Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or discussing skill capabilities.
Use when an agent needs to operate the user's real Chrome session — listing tabs, reading the page, clicking, filling, typing into rich editors, pressing keys, evaluating JS, capturing screenshots, and reading console/network buffers. All actions go through CDP and run on backgrounded tabs without stealing focus.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Use this skill when working with Brain Imaging Data Structure (BIDS) datasets: organizing neuroscience and biomedical data (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, motion capture, EMG, MR spectroscopy, behavioral), querying BIDS layouts, validating compliance, converting DICOM to BIDS, writing metadata sidecars, or creating BIDS derivatives.
Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.
Explain ABAP objects with full dependency context (via SAPContext) and optional ATC code quality analysis — replicates SAP Joule's "Explain Code" capability, including behavior definitions (BDEF — CRUD graph, determinations/validations, bound handler class). Use when asked to "explain this ABAP", "what does ZCL_X do", "walk me through this class/CDS view/behavior definition", or "review this object's quality".
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the codebase or domain is unfamiliar, the user will "know it when they see it", a reference implementation must be understood before porting, mid-build deviations from the plan need capturing, or a finished change needs buy-in or verified understanding before merge. Pairs with [write-spec](../write-spec/SKILL.md) — walk the quadrants to burn off fog before slicing, and feed the finished map into the spec.
Trigger on mention of GKE cluster autoscaler, node autoscaling, node pool auto-creation / node auto-provisioning. Provides guidance on enabling and optimizing cluster autoscaler, best practices, and troubleshooting issues such as nodes not scaling up or down, zonal stockouts, or capacity buffers. Do not use for ComputeClass-specific YAML generation or priority configuration (defer to gke-compute-classes skill).
Use this skill for live web tasks where WebFetch or curl would fail or be insufficient: JavaScript-rendered pages, forms, screenshots, PDFs, login flows, CAPTCHA/bot-protection flows, and multi-step navigation. It runs a real Steel cloud browser through the Steel CLI. Use when the agent should visit, click, type, scrape, screenshot, or extract now. Do not use for writing reusable Steel SDK/API code; use steel-developer for code. If a live task fails, hand off to steel-session-debugging; if evidence points to bot detection, proxies, CAPTCHA, or identity, hand off to steel-reliability.
Drives a disciplined explore → plan → implement → verify loop for changing an AI agent's behavior with confidence — whether fixing a reported failure or introducing a new requirement, business rule, or policy. Grounds the diagnosis in MLflow traces, codifies the desired behavior as a regression test suite (`mlflow.genai.evaluate` assertions in `@mlflow.test` pytest tests), and iterates the agent — not the test — until green, resisting quick system-prompt patches when the real fix is upstream (missing tool, retrieval source, or capability). Use whenever the user wants to fix or change how an agent behaves — e.g. "fix this issue in my agent", "this answer is wrong", "the agent is hallucinating", "improve my agent based on this trace", "make the agent do X instead of Y", "I want the agent to lead with/prioritize/recommend X", "new business rule: the agent should X", "always/never do X", "change the agent's default behavior" — or shares a trace they want addressed.
Authoritative field/schema reference for 2130 STANDARD Salesforce objects — use to look up standard sObject and Tooling field API names, types, properties (filterable/sortable/groupable/updateable), and relationship names for Account, Contact, Opportunity, Lead, Case, ApexClass, ApexCodeCoverage, TraceFlag, and more. Load this alongside a SOQL/query/Apex skill when the field names, types, or Filter/Sort/Group capabilities are unverified — not when the fields are already known and only query syntax or optimization is needed. TRIGGER when verifying, validating, or debugging fields in a SOQL/SOSL query or DML against a standard object — capabilities, relationship/subquery paths, or what fields an object has — so the query runs instead of guessing. Custom __c objects and __c fields are NOT in these assets; describe the live org for those (sf sobject describe). DO NOT TRIGGER for authoring/deploying *-meta.xml or sfdx source (use the Metadata API skill).
Audit and govern Skills, plugins, and MCP servers across Codex, Claude Code, and compatible Agent hosts. This tool applies when users request to inventory, deduplicate, classify, scope, archive, or reduce the context cost of Agent capabilities; ask why there are so many Skills; need to make global/project/trigger-related decisions; or use phrases like "Skill Slimming", "Inventory Skills", "Organize Skills", "Skill Governance", "Too Many Skills", "Which Skills Take Effect Globally", "Analyze Plugins and MCP", "Context Occupancy", "Generate Skill Review Page", "I'm Done Selecting", or "Read My Skill Settings". Default to a read-only evidence audit and a locally persisted review draft. Never install, enable, copy, archive, disable, delete, or execute a plan without separate explicit authorization for the exact phase and target set.