letzai-api
Generate AI images and videos via the LetzAI API. Images with Nano Banana Pro, Seedream 5, Flux 2, GPT Image 2; videos with Veo 3.1, Kling V3, Seedance 2.0. Includes context editing, upscaling, asset uploads, and custom @model training. Use for content creation apps and automation.
clear-writing
Apply ISO 24495-1 to create text that helps readers easily find, understand, and use the information they need. Use this skill only to write, revise, or review practical documents that convey information, explain procedures, or support decision-making, and provide only the requested output.
code-review
Review Git changes for concrete defects and evidence-backed maintainability concerns. Use for code review of commits, ranges, staged changes, uncommitted changes, or selected files. With no target, review all staged, unstaged, and untracked changes; ask for a target if none exist. Trace behavior in the selected version, challenge suspected defects, exclude style-only preferences, and provide an approval verdict only when requested.
code-security-audit
Performs OWASP-based code security audits on any codebase. Analyzes source code against ASVS 5.0.0 verification requirements, API Security Top 10 2023 risk patterns, OWASP CheatSheet secure coding practices, and WSTG testing methodologies. Input is a codebase to review; output is a detailed Markdown security audit report. Use when the user requests a security audit, security review, vulnerability assessment, or code security analysis.
delegated-review-loop
Run a delegated build-review-improve loop when the user explicitly invokes this skill or explicitly asks to have sub-agents build and iteratively review the work. A worker sub-agent produces the artifact (with an optional scout sub-agent gathering context first), a task-matched panel of independent reviewer sub-agents critiques it in parallel, and the worker improves until the panel passes or the iteration cap is reached. All inter-agent content flows through documents in a per-session directory; the main agent orchestrates by passing file paths only and never writes the artifact itself. Applies to any deliverable: code changes, documents, designs, plans. Do not auto-trigger on ordinary requests; this is an explicit-invocation skill. Distinct from iterative-self-review, where the main agent holds the pen and a single blind verifier checks it.
document-writing
Create, update, rewrite, review, fact-check, or normalize durable human-readable documents. Use for software project READMEs and usage documentation, explanatory overviews, action guides, references or specifications, proposals, analysis reports, policies, troubleshooting runbooks, records or meeting notes, Feature Design Docs (FDDs), and Design System Documents for product UI or any digital storefront's visual assets, including the document portion of mixed document-and-production requests. Route by the requested artifact and load only its references. Do not use for implementation plans, task briefs, tickets, system or architecture design docs, source changes, pure UI or asset production, or short chat-only answers.
iterative-self-review
Use only when the user explicitly invokes this skill.
jetbrains-plugin-development
>-
jetbrains-vmoptions
>
kysely-converter
Convert raw SQL into type-safe Kysely TypeScript, write Kysely queries from requirements without source SQL, modify or refactor existing Kysely code, and diagnose Kysely type errors. Use for SELECT, INSERT, UPDATE, DELETE, joins, CTEs, expressions, and window functions with version-aware SQL dialect handling. Excludes migration operations and work on other query builders.
linear-issue-reviewer
>
linear-issue-worker
>
orchestration
Use only when the user explicitly invokes this skill.
react-guide
Use for explaining, designing, implementing, reviewing, refactoring, migrating, or diagnosing React 18/19 applications when React-specific judgment is needed for CSR, SSR, streaming, hydration, structure, APIs, Hooks, state/data, async UI, accessibility, performance, compatibility, or Compiler behavior. Covers React's own server-rendering APIs; excludes framework-specific APIs, RSC/Server Functions implementation, custom server-runtime construction, unsupported React majors, build-tool-only work, and styling/copy-only work.
release-it
>-
rust-guide
Use to explain Rust language characteristics and established practical patterns, and to apply that knowledge in Rust development. Covers ownership, borrowing, lifetimes, traits and API design, collections, memory allocation, error handling, async execution and CPU parallelism, synchronization, module and crate boundaries, Cargo workspaces and monorepos, library selection, performance and SIMD, WebAssembly, embedded/no_std, unsafe/FFI, compiler diagnostics, build configuration, and MSRV/edition compatibility. Use for questions about how Rust works, idiomatic ways to structure code, why a compiler constraint exists, when a pattern or library fits, and its costs and exceptions. Connects mechanisms to practical examples, including std/core approaches and curated ecosystem libraries. Uses stable Rust with explicit API, edition, and target requirements; explains relevant nightly alternatives separately.
skill-creator
Create, improve, and evaluate reusable agent skills. Use when the user wants to create a skill, revise its instructions or resources, measure its performance, or improve its triggering description. After a complete draft, run one independent-candidate refinement pass before the existing evaluation and feedback workflow.
system-prompt-creator
Generate system prompts from user requirements, with application guidance and request-derived evaluation materials. Use when asked to create, design, or draft a system prompt for an LLM bot, assistant, classifier, router, or explicitly requested multi-step pipeline (e.g. "create a system prompt", "시스템 프롬프트 만들어줘", "분류기 프롬프트 짜줘"). Defaults to a model-neutral single prompt; checks official guidance for a named model/provider. Supports revisions during the current creation task and current-agent simulations only after approval of concrete cases and scope. Not for standalone refinement/review of an existing prompt, one-off user prompts, agent definition files, CLAUDE.md/AGENTS.md, or skill definitions.
task-brief-creator-caveman
>
task-brief-creator
>
typst-creator
Create, update, review, migrate, or diagnose Typst (.typ) source for documents, reports, papers, and presentations. Use for Typst markup, styling, scripting, math, layout, bibliography, and compiler/export issues. Resolve the compiler and generate source for stable Typst 0.13.0 through 0.15.1, including source shared across supported releases.
vite-guide
Use for explaining, designing, implementing, reviewing, refactoring, migrating, or diagnosing Vite 7/8 applications when runtime, build, plugin, deployment, performance, or compatibility judgment is needed, including CSR SPA/MPA, backend-embedded clients, and Vite's own SSR development and production integration. Excludes framework-specific SSR APIs, RSC/Server Functions implementation, custom server-runtime construction, unsupported Vite majors, unrelated non-client bundling, and UI-framework-only decisions.
agents-md-generator
Analyze repository structure and generate or update standardized AGENTS.md files that serve as contributor guides for AI agents. Supports both single-repo and monorepo structures. Measures LOC to determine character limits and produces structured documents covering overview, optional ownership maps, patterns, conventions, and working agreements. Update mode refreshes only standard sections while preserving user-defined custom sections. Existing unmarked files require a concrete change preview and one-time user confirmation before adoption; heading matches alone never authorize rewriting. Use when the user wants an AGENTS.md generated or refreshed — setting one up for a new repository, onboarding AI agents to an existing codebase, updating an existing AGENTS.md after meaningful project changes, or when the user mentions AGENTS.md. Not for CLAUDE.md, README, or other documentation files.
biz-opportunity-scout
Identify and validate profitable business opportunities by analyzing market size (TAM/SAM/SOM), unit economics, competitive landscape, and PMF indicators. Generates comprehensive HTML reports with opportunity scorecards.
linear-issue-creator
>
laudex
Find the right MCP server, API, SaaS product, or developer tool for a task using the Laudex catalog (laudex.dev), then report back whether it actually worked. Use this whenever the user needs an external service or tool to get something done and hasn't settled on one — "is there an MCP server for X", "what API should I use to Y", "find me a tool that can Z", "I need something to scrape / automate a browser / store memory / query a database / send email" — or whenever you are about to pick a third-party service yourself. Also use it after you have installed, called, or integrated a service found through Laudex, to report the outcome so other agents benefit, and whenever the user asks to report on or rate a service.
writing-email-subjects
Use when an email draft exists but the subject line is unclear, too long, or needs options tailored to a specific audience and tone.
writing-meeting-notes
Use when a meeting just occurred and notes need to be turned into a clear summary with decisions, action items, owners, and dates.
triaging-bugs
Use when a bug report is ambiguous or incomplete and you need a consistent way to assess severity, impact, reproducibility, and the next investigative step.
writing-release-notes
Use when changes are ready to ship and you need to communicate what changed, who it affects, and any required actions without exposing internal-only details.
azure-devops
Interact with Azure DevOps repositories, pull requests, and APIs using the AZURE_DEVOPS_TOKEN environment variable. Use when working with code hosted on Azure DevOps or managing Azure DevOps resources.
ies-flox
FloxHub publication `bmorphism/ies` - a focused development environment
ies-triadic
IES Triadic Skill
ies
ies
ikea-varmblixt-smart-lamp
|
image-enhancer
Improves the quality of images, especially screenshots, by enhancing
implementing-aes-encryption-for-data-at-rest
AES (Advanced Encryption Standard) is a symmetric block cipher standardized by NIST (FIPS 197) used to protect classified and sensitive data. This skill covers implementing AES-256 encryption in GCM m
implementing-alert-fatigue-reduction
>
implementing-anti-phishing-training-program
Security awareness training is the human layer of phishing defense. An effective anti-phishing training program combines regular simulations, interactive learning modules, metric tracking, and positiv
implementing-anti-ransomware-group-policy
>
implementing-api-abuse-detection-with-rate-limiting
Implement API abuse detection using token bucket, sliding window, and adaptive rate limiting algorithms to prevent DDoS, brute force, and credential stuffing attacks.
implementing-api-gateway-security-controls
>
implementing-api-key-security-controls
>
implementing-api-rate-limiting-and-throttling
>
implementing-api-schema-validation-security
Implement API schema validation using OpenAPI specifications and JSON Schema to enforce input/output contracts and prevent injection, data exposure, and mass assignment attacks.
implementing-api-security-posture-management
Implement API Security Posture Management to continuously discover, classify, and score APIs based on risk while enforcing security policies across the API lifecycle.
implementing-api-security-testing-with-42crunch
Implement comprehensive API security testing using the 42Crunch platform to perform static audit and dynamic conformance scanning of OpenAPI specifications.
implementing-api-threat-protection-with-apigee
Implement API threat protection using Google Apigee policies including JSON/XML threat protection, OAuth 2.0, SpikeArrest, and Advanced API Security for OWASP Top 10 defense.
implementing-application-whitelisting-with-applocker
>
implementing-aqua-security-for-container-scanning
Deploy Aqua Security's Trivy scanner to detect vulnerabilities, misconfigurations, secrets, and license issues in container images across CI/CD pipelines and registries.
Page 465 of 1656 · 82774 results