发现 Skills

This skill should be used when the user asks to "create a plan", "organize project plans", "setup planning structure", "initialize docs/plans", or when the plan agent needs to manage planning artifacts. Provides guidance for creating and maintaining Kanban-style planning directory structures.

Operate Burp Suite Community and Professional for web application penetration testing. Use when intercepting HTTP/S traffic, fuzzing parameters, testing authentication bypasses, scanning for vulnerabilities, or performing advanced web application assessments. Covers proxy setup, Intercept, Repeater, Intruder (all attack types), Scanner, Sequencer, Decoder, Comparer, Logger, Collaborator, BApp Store extensions (Autorize, Param Miner, JWT Editor, Turbo Intruder, ActiveScan++), scope control, session handling, macros, REST API, and Bambda filters.

Unity Catalog system tables for lineage, audit logs, billing, compute, jobs, and query history. Use when querying system.access.audit, system.access.table_lineage, system.billing.usage, system.compute.clusters, system.lakeflow.jobs, system.lakeflow.job_run_timeline, or system.query.history.

Automate container image updates for Kubernetes workloads managed by Argo CD. Use when configuring Argo CD Image Updater, setting up automatic image updates, configuring update strategies (semver, digest, newest-build, alphabetical), implementing git write-back, troubleshooting image update issues, or working with ImageUpdater CRDs. Covers installation, configuration, authentication, and best practices.

Integration of Azure Key Vault with the Secrets Store CSI Driver for Kubernetes secrets management. Use this when creating SecretProviderClass resources, mounting secrets from Key Vault, troubleshooting 403/permission errors, syncing secrets into Kubernetes, or configuring applications to consume Key Vault secrets.

Run an existing AI crew/committee workflow. Use when the user wants to execute a KaibanJS crew, pass inputs, or invoke a crew script (e.g. prd-review).

Define and configure OpenCode agents with proper permissions, tools, and behaviors. Use for agent creation, tool access control, permission patterns, and mode selection. Use proactively when user says 'create an agent', 'agent permissions', 'tool access', 'subagent', 'restrict agent', or asks about agent configuration. Examples: - user: 'Create a security reviewer agent' → design agent with read-only permissions, appropriate skills - user: 'How do I restrict bash access?' → explain permission.bash patterns with allow/ask/deny - user: 'Make an agent use the question tool' → configure tools.question: 'enabled' or ensure no tools restrictions - user: 'What's the difference between primary and subagent?' → explain mode options

Generate publication-quality academic figures, framework diagrams, and pipeline illustrations from paper method text and figure captions. Use when the user asks to draw a figure for a paper, create a method overview diagram, or visualize a research pipeline/framework/architecture.

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Automatically generate test scaffolding when a user writes new code without tests or mentions needing tests. Supports unit, integration, end-to-end (E2E), and data tests for PHP and JavaScript. Invoke when the user mentions tests, testing, coverage, write tests, or shows new untested code.

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.

Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis.

Query gnomAD (Genome Aggregation Database) for population allele frequencies, variant constraint scores (pLI, LOEUF), and loss-of-function intolerance. Essential for variant pathogenicity interpretation, rare disease genetics, and identifying loss-of-function intolerant genes.

Query Reactome REST API for pathway analysis, enrichment, gene-pathway mapping, disease pathways, molecular interactions, expression analysis, for systems biology studies.

Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.

Replace with a description of the skill and when Claude should use it.

Clone and replicate live website UI into the current project stack. Uses agent-browser to capture screenshots of target and dev sites, zai-vision MCP for visual diffing, and codebase analysis to produce a pixel-perfect implementation plan. Outputs structured plans to .agent/plans/ ready for execution via PRD loops. Trigger when asked to replicate, clone, copy, match, or rebuild the look/feel/UI of an external website or specific page/section.

Parses Apache and Nginx access logs to detect SQL injection attempts, local file inclusion (LFI), directory traversal, web scanner fingerprints, and brute-force patterns. Uses regex-based pattern matching against OWASP attack signatures, enriches sources with GeoIP, and performs statistical anomaly detection for abnormal request frequency and response size.

Conduct systematic access reviews and certifications to ensure users have access rights appropriate to their roles. Covers review program design, reviewer selection, risk-based prioritization, micro-certification strategies, and remediation tracking to meet SOX, HIPAA, and PCI DSS requirements.

Test for path traversal vulnerabilities that allow reading or writing arbitrary files on the server by manipulating file path parameters in a web application.

SOC 2 Type II audit readiness involves designing, implementing, and demonstrating the operational effectiveness of controls aligned with the AICPA Trust Services Criteria (TSC) over the specified audit period (typically 6–12 months).

SC2 Data Editor — Units, Abilities, Movers, Turrets, Requirements, and Races in XML. Use when creating or modifying units (CUnit/CUnitHero), abilities (CAbilEffectTarget, CAbilEffectInstant, CAbilResearch, etc.), movement (CMover), turrets (CTurret), or tech requirements in GameData XML files. Do not use for Actors/visuals (use sc2data-actors-visuals), damage/effects (use sc2data-effects-weapons), or Galaxy scripting (use the galaxy-* skills).

Ultra-compressed communication mode. Slash token usage ~75% by speaking like caveman while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Reference and apply IEEE, ISO/IEC, and other software engineering standards for development, quality assurance, and project management. Use when selecting standards for specific activities, formatting standard references, establishing project frameworks, or creating documentation templates.