Results for “tec”

Provides the single source of truth for brand guidelines, design tokens, technology choices, and voice/tone. Use this skill whenever generating UI components, styling applications, writing copy, or creating user-facing assets to ensure brand consistency.

China LLM Gateway - Unified interface for Chinese LLMs including Qwen, DeepSeek, GLM, Baichuan. OpenAI compatible, one API Key for all models. Use when: the user needs model routing, provider setup, or Chinese LLM access guidance.

Agent profile for write developer docs, user docs, API docs, tutorials, changelogs, and concise implementation notes. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Analyze draft prompts to identify intent, scope, and missing context, then generate an optimized prompt with ECC component recommendations. Advisory only — never executes the task.

Creates detailed technical implementation plans for features based on a Feature PRD, including system architecture, database schema, API design, and frontend component hierarchy.

Embody the voice and methodology of AI researcher Fei-Fei Li to enhance technical content with data-centric and human-centered perspectives.

Professional US stock analysis with financial data, news, social sentiment, and multi-model AI. Comprehensive reports at $0.02-0.10 per analysis. Use when: the user needs market data, stock analysis, watchlists, or portfolio workflows.

Unified LLM Gateway - One API for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a single API key. Use when: the user needs model routing, provider setup, or Chinese LLM access guidance.

Provides production-grade techniques for evaluating LLM outputs using LLMs as judges, covering direct scoring, pairwise comparison, bias mitigation, rubric generation, and confidence calibration.

Co-author structured documents (specs, PRDs, RFCs) through a 3-stage workflow: context gathering, drafting, and reader testing. Use when writing proposals, technical specs, or similar structured content. Repo decision-memory system (INDEX.md, rejected alternatives, agent rules) → docs-adr.

Compress large language models by 40-60% with minimal accuracy loss using one-shot pruning techniques like Wanda and SparseGPT, enabling faster inference and deployment on constrained hardware.

Manages AI model retention and machine unlearning requirements. Covers training data deletion verification, model versioning for compliance, machine unlearning techniques (SISA, gradient-based), and retraining triggers. Keywords: AI retention, machine unlearning, model versioning, training data deletion, retraining, storage limitation.

Strategic search planning for agent-driven research. Generates structured search-term matrices with tiered fallback strategies, engine-specific operators, and grading criteria before executing any searches. Use this skill whenever research requires more than a single search query — comparing technologies, verifying claims across sources, surveying a landscape, investigating a multi-faceted question, or building evidence for a decision. Do NOT use for quick factual lookups, fetching a single known URL, or questions answerable from a single source. Covers tech, academic, regulatory, and general domains. Think of it as "research planning" — the matrix is the plan, execution comes after.

Use when creating a new skill under .agents/skills/, editing an existing one, or deciding whether a technique deserves to become a skill at all - covers SKILL.md structure, the description field, and how to keep a skill discoverable and token-efficient.

Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.

Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.

Critically audit agent skills and remove content that is outdated, disproven, model-specific, or based on poorly cited sources. Load when improve-skills runs its per-skill cycle, when the user asks to prune skills, remove outdated techniques, check if skills are still valid, verify citations in skills, audit skill sources, or update skills for a new model release. Also triggers on "are these skills still valid", "check for obsolete techniques", "verify skill citations", or "update skills for GPT-5/Claude 4/Gemini 2". Runs before split-skill and compress-skill — removing bad content first means the remaining content is worth preserving.

Provides advisory guidance for the Adobe Dispatcher Apache HTTP Server module and related HTTPD configuration in AEM 6.5 / AMS workflows, with public-doc citations and AMS-specific MCP verification plans.

Design and implement network segmentation in Operational Technology environments using VLANs, industrial firewalls, data diodes, and software-defined networking, following the Purdue Model and IEC 62443 standards.

Guides AI agents to apply advanced mathematical and probabilistic techniques (Bloom filters, HyperLogLog, FFT, etc.) for large-scale data problems where classical algorithms are optimal but math offers better asymptotic bounds.

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

Conduct comprehensive security assessments of Operational Technology (OT) networks including SCADA systems, DCS architectures, and industrial control system communication paths, addressing the Purdue Reference Model layers and identifying IT/OT convergence risks.

Composite skill — full project health check across testing, config, hooks, performance, security, MCP, and plugins. Runs the audit skills in parallel and reconciles into one severity-ranked report with prioritized remediation plan. Use weekly per active project, before major releases, or as part of quarterly tech-debt review.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Classifies data as pseudonymised or anonymised using Recital 26 reasonably likely test, Breyer ruling C-582/14, motivated intruder test, and WP29 Opinion 05/2014 on anonymisation techniques. Covers singling out, linkability, and inference tests. Keywords: pseudonymisation, anonymisation, Recital 26, re-identification, k-anonymity, differential privacy, WP29 Opinion 05/2014.

A library of reusable, production-tested prompt engineering patterns for building AI-powered features. Use when designing system prompts for apps, building AI pipelines, selecting the right prompting technique for a use case, or reviewing prompts for common failure modes. Complements the prompt-engineering skill (which covers the optimization framework); this skill covers the pattern library itself.

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

Generate images and videos with AIsa. Supports Gemini, Wan, and Seedream image generation plus Wan text-to-video and image-to-video models. One API key; the bundled client routes each model to the correct endpoint automatically. Use when: you need a neutral AIsa media-generation skill that spans multiple model families without changing credentials or request flow.

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.

Generate images and videos with AIsa. Four image models (Google Gemini 3 Pro Image, Alibaba Wan 2.7 image + image-pro, ByteDance Seedream) and four Wan video variants (wan2.6/2.7 × t2v/i2v). One API key; the client routes each model to the correct endpoint automatically. Use when: the user needs AI image or video generation workflows.

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.