Loading...
Loading...
Found 1,131 Skills
Guides the agent through upgrading an Ionic Framework app to a newer major version. Supports upgrades from Ionic 4 through 8, including multi-version jumps. Covers framework-specific migration steps for Angular, React, and Vue, component breaking changes, CSS variable updates, and browser support changes. Do not use for Capacitor version upgrades (use capacitor-app-upgrades instead), for plugin library upgrades, or for non-Ionic UI frameworks.
Use when generating or reasoning over text with Alibaba Cloud Model Studio Qwen flagship text models (`qwen3-max`, `qwen3.5-plus`, `qwen3.5-flash`, snapshots, and compatible open-source variants). Use when building chat, agent, tool-calling, or long-context text generation workflows on Model Studio.
Vercel Marketplace expert guidance — discovering, installing, and building integrations, auto-provisioned environment variables, unified billing, and the vercel integration CLI. Use when consuming third-party services, building custom integrations, or managing marketplace resources on Vercel.
Assess investment suitability obligations under FINRA Rules 2111 and 2090 across all three suitability prongs. Use when the user asks about reasonable-basis, customer-specific, or quantitative suitability, product-specific concerns for complex products, leveraged ETFs, variable annuities, or alternatives, household-level suitability, hold recommendations, or the institutional suitability exemption. Also trigger when users mention 'is this investment suitable', 'turnover ratio is too high', 'cost-to-equity ratio', 'churning metrics', 'suitability questionnaire design', 'complex product due diligence', 'customer refused to provide their risk tolerance', or ask whether a recommendation fits a customer's profile.
Create a complete, actionable design system for any project (website, app, product) grounded in physical/sensory anchoring rather than design trends. Delivers CSS tokens, typography scale, component patterns, accessibility checklist, and absolute rules as a single developer-ready markdown document. Use this skill whenever the user asks to create a design system, theme, color palette, visual identity, CSS tokens, theme variables, or propose an art direction. Also triggers on "style guide", "site colors", "choose fonts", "look and feel", "visual branding", "charte graphique", "identite visuelle", "direction artistique", "refonte visuelle", or any new project where design isn't yet defined — propose this skill proactively.
Retrieve, inject, and manage secrets from Keeper Vault using KSM CLI (ksm). Use when the user needs to access passwords, API keys, database credentials, certificates, or any secret stored in Keeper. Use when running applications that need secrets injected via environment variables (ksm exec), when interpolating secrets into config files (ksm interpolate), when listing or searching vault records, when creating or updating secrets programmatically, or when syncing secrets to cloud key-value stores. Also use when the user mentions 'keeper', 'ksm', 'keeper secrets', 'keeper vault', 'keeper notation', 'keeper://', or asks about retrieving credentials for CI/CD, Docker, Kubernetes, or any DevOps pipeline. Prefer this skill over hardcoding credentials. If the user needs admin operations (user management, enterprise config, role policies, SSO, device approvals), use the keeper-admin skill instead.
Translate PRD intent, roadmap asks, or product discussions into an implementation-ready capability plan that exposes constraints, invariants, interfaces, and unresolved decisions before multi-service work starts. Use when the user needs an ECC-native PRD-to-SRS lane instead of vague planning prose.
Audit MCP (Model Context Protocol) server configurations for security issues. Use this skill when: - Reviewing .mcp.json files for security risks - Checking MCP server args for hardcoded secrets or shell injection patterns - Validating that MCP servers use pinned versions (not @latest) - Detecting unpinned dependencies in MCP server configurations - Auditing which MCP servers a project registers and whether they're on an approved list - Checking for environment variable usage vs. hardcoded credentials in MCP configs - Any request like "is my MCP config secure?", "audit my MCP servers", or "check .mcp.json" keywords: [mcp, security, audit, secrets, shell-injection, supply-chain, governance]
Validates .env files and environment variable configurations against project requirements. Checks for missing required variables, type mismatches, insecure defaults, unreferenced variables, and common configuration errors. Compares .env against .env.example, code references, and deployment manifests. Produces a structured validation report with severity-ranked findings. Triggers on: "validate env file", "check environment variables", "env file audit", "missing env vars", "env validation", "check .env", "environment config check", "validate configuration", "env file review", "dotenv validation". Use this skill when verifying environment configuration completeness and correctness before deployment or after onboarding. NOT for secret scanning (use repo-sentinel or secret-scanner). NOT for general config file editing (use filesystem skill).
Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated panel, evolves winners through multiple rounds, outputs optimized version + full experiment log. Use when optimizing landing pages, email sequences, ad copy, headlines, form pages, CTA text, or any conversion-focused content. Triggers on "optimize this page", "run autoresearch", "score these variants", "A/B test this copy".
Adversarial thinking partner for founders and executives. Stress-tests plans, prepares for board meetings, dissects decisions with no good options, forces honest post-mortems, and identifies blind spots before competitors or board members do. Use when you need plan validation, board preparation, hard decision frameworks, assumption stress-testing, failure analysis, or when user mentions stress test, challenge, board prep, hard decision, pre-mortem, post-mortem, devil's advocate, plan review, or executive coaching.
Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before retrying — a failed verification always considers whether a new §V invariant would prevent recurrence. Triggers when the user asks to build, implement, execute the spec, or tackle a specific §T task (`build §T.3`, `build --next`, `implement next task`, `run the build`). Expects SPEC.md to exist; if not, defers to the spec skill.