每个推荐都保留与其仓库、审计和安装路径的明确关联。
This MATLAB and Simulink Challenge Project Hub contains a list of research and design project ideas. These projects will help you gain practical experience and insight into technology trends and industry directions.
Turn project work into reusable knowledge — an AI-agent skill for Claude Code & Codex
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
Generate highly simplified personified IP mascot logos with Flat-first geometry, rounded heavy forms, two IP colors plus one background color by default, and extremely subtle neo-skeuomorphic shading. Use when creating an animal, creature, robot, ghost, plant, object, or other character as a minimal square logo or app-icon artwork, including when the agent should infer three distinct IP directions from product-repository context.
A self-interrogation skill packaging 697 senior-engineer questions as a portable Claude/Codex skill and prompt to improve agent reasoning before writing code.
Python library for cleaning and regularising building footprints in geospatial data, aligning edges to principal directions and simplifying polygons for more accurate analysis.
Develop art direction for image generation with curated style cards distilled from Open Image Prompts. Use when choosing or comparing visual directions, improving an existing generation prompt, or translating a subject, use case, or supplied image into a compact creative spec. Use img-gen-prompts for real archive examples, exact source prompts, or gallery browsing.
Generates, optimizes, and validates Cypher 25 queries for Neo4j 2025.x and 2026.x.
Use when a user wants applicant-facing diagnosis and revision advice on a Chinese NSFC (国自然) application draft — asks for 本子把脉, 本子体检, 国自然申请书修改建议, NSFC benzi audit, 帮我看国自然本子, 标书逻辑诊断, 青年/面上/地区基金申请书修改, 对照已中本子, 从中标样本提炼写法规律, 选题撞题核查, or 申请代码选得对不对 — or wants critique of the title, abstract, key scientific questions, rationale, research contents, innovation, feasibility, research basis, 代表作/代表性论著 quality and support, or cross-section consistency. Accepts PDF/DOCX/Markdown/text or extracted draft text. This is applicant revision advice, not formal communication-review opinions; for expert review forms use nsfc-review.
Create visual identity systems: color palettes, font pairings, style direction, and rendered preview PDFs. Use when the user needs a cohesive design system before building a deck, presentation, document, or any visual project. Works for consulting engagements, product pitches, personal brands, or any context requiring a unified visual language. Produces a markdown design brief, a JS config, and a preview PDF.
DORMANT (ADR-0017, 2026-07-20) - the TERMINAL VELOCITY scroll-film was retired and apps/landing is a static site with no GL surface; this skill is preserved for any future WebGL rebuild (conventions, verified version pins, playhead/scroll-rig/VAT/Gerstner/post-chain patterns, budgets, gate + semantic-layer machinery). Do not load for current apps/landing work - the static site routes to project-steward.
Shared read-side contract every read-only CRITIC imports — adversarial stance, empirical verification of runtime-behavior claims, the mandatory self-red-team before APPROVE, spec-UB sweeps, and the miss-ledger mechanism. The review-side mirror of author-contract. Load at the start of any review task.
每个推荐都保留与其仓库、审计和安装路径的明确关联。
This MATLAB and Simulink Challenge Project Hub contains a list of research and design project ideas. These projects will help you gain practical experience and insight into technology trends and industry directions.
Turn project work into reusable knowledge — an AI-agent skill for Claude Code & Codex
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
Generate highly simplified personified IP mascot logos with Flat-first geometry, rounded heavy forms, two IP colors plus one background color by default, and extremely subtle neo-skeuomorphic shading. Use when creating an animal, creature, robot, ghost, plant, object, or other character as a minimal square logo or app-icon artwork, including when the agent should infer three distinct IP directions from product-repository context.
A self-interrogation skill packaging 697 senior-engineer questions as a portable Claude/Codex skill and prompt to improve agent reasoning before writing code.
Python library for cleaning and regularising building footprints in geospatial data, aligning edges to principal directions and simplifying polygons for more accurate analysis.
Develop art direction for image generation with curated style cards distilled from Open Image Prompts. Use when choosing or comparing visual directions, improving an existing generation prompt, or translating a subject, use case, or supplied image into a compact creative spec. Use img-gen-prompts for real archive examples, exact source prompts, or gallery browsing.
Generates, optimizes, and validates Cypher 25 queries for Neo4j 2025.x and 2026.x.
Use when a user wants applicant-facing diagnosis and revision advice on a Chinese NSFC (国自然) application draft — asks for 本子把脉, 本子体检, 国自然申请书修改建议, NSFC benzi audit, 帮我看国自然本子, 标书逻辑诊断, 青年/面上/地区基金申请书修改, 对照已中本子, 从中标样本提炼写法规律, 选题撞题核查, or 申请代码选得对不对 — or wants critique of the title, abstract, key scientific questions, rationale, research contents, innovation, feasibility, research basis, 代表作/代表性论著 quality and support, or cross-section consistency. Accepts PDF/DOCX/Markdown/text or extracted draft text. This is applicant revision advice, not formal communication-review opinions; for expert review forms use nsfc-review.
Create visual identity systems: color palettes, font pairings, style direction, and rendered preview PDFs. Use when the user needs a cohesive design system before building a deck, presentation, document, or any visual project. Works for consulting engagements, product pitches, personal brands, or any context requiring a unified visual language. Produces a markdown design brief, a JS config, and a preview PDF.
DORMANT (ADR-0017, 2026-07-20) - the TERMINAL VELOCITY scroll-film was retired and apps/landing is a static site with no GL surface; this skill is preserved for any future WebGL rebuild (conventions, verified version pins, playhead/scroll-rig/VAT/Gerstner/post-chain patterns, budgets, gate + semantic-layer machinery). Do not load for current apps/landing work - the static site routes to project-steward.
Shared read-side contract every read-only CRITIC imports — adversarial stance, empirical verification of runtime-behavior claims, the mandatory self-red-team before APPROVE, spec-UB sweeps, and the miss-ledger mechanism. The review-side mirror of author-contract. Load at the start of any review task.
每个推荐都保留与其仓库、审计和安装路径的明确关联。
This MATLAB and Simulink Challenge Project Hub contains a list of research and design project ideas. These projects will help you gain practical experience and insight into technology trends and industry directions.
Turn project work into reusable knowledge — an AI-agent skill for Claude Code & Codex
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
Generate highly simplified personified IP mascot logos with Flat-first geometry, rounded heavy forms, two IP colors plus one background color by default, and extremely subtle neo-skeuomorphic shading. Use when creating an animal, creature, robot, ghost, plant, object, or other character as a minimal square logo or app-icon artwork, including when the agent should infer three distinct IP directions from product-repository context.
A self-interrogation skill packaging 697 senior-engineer questions as a portable Claude/Codex skill and prompt to improve agent reasoning before writing code.
Python library for cleaning and regularising building footprints in geospatial data, aligning edges to principal directions and simplifying polygons for more accurate analysis.
Develop art direction for image generation with curated style cards distilled from Open Image Prompts. Use when choosing or comparing visual directions, improving an existing generation prompt, or translating a subject, use case, or supplied image into a compact creative spec. Use img-gen-prompts for real archive examples, exact source prompts, or gallery browsing.
Generates, optimizes, and validates Cypher 25 queries for Neo4j 2025.x and 2026.x.
Use when a user wants applicant-facing diagnosis and revision advice on a Chinese NSFC (国自然) application draft — asks for 本子把脉, 本子体检, 国自然申请书修改建议, NSFC benzi audit, 帮我看国自然本子, 标书逻辑诊断, 青年/面上/地区基金申请书修改, 对照已中本子, 从中标样本提炼写法规律, 选题撞题核查, or 申请代码选得对不对 — or wants critique of the title, abstract, key scientific questions, rationale, research contents, innovation, feasibility, research basis, 代表作/代表性论著 quality and support, or cross-section consistency. Accepts PDF/DOCX/Markdown/text or extracted draft text. This is applicant revision advice, not formal communication-review opinions; for expert review forms use nsfc-review.
Create visual identity systems: color palettes, font pairings, style direction, and rendered preview PDFs. Use when the user needs a cohesive design system before building a deck, presentation, document, or any visual project. Works for consulting engagements, product pitches, personal brands, or any context requiring a unified visual language. Produces a markdown design brief, a JS config, and a preview PDF.
DORMANT (ADR-0017, 2026-07-20) - the TERMINAL VELOCITY scroll-film was retired and apps/landing is a static site with no GL surface; this skill is preserved for any future WebGL rebuild (conventions, verified version pins, playhead/scroll-rig/VAT/Gerstner/post-chain patterns, budgets, gate + semantic-layer machinery). Do not load for current apps/landing work - the static site routes to project-steward.
Shared read-side contract every read-only CRITIC imports — adversarial stance, empirical verification of runtime-behavior claims, the mandatory self-red-team before APPROVE, spec-UB sweeps, and the miss-ledger mechanism. The review-side mirror of author-contract. Load at the start of any review task.
每个推荐都保留与其仓库、审计和安装路径的明确关联。
This MATLAB and Simulink Challenge Project Hub contains a list of research and design project ideas. These projects will help you gain practical experience and insight into technology trends and industry directions.
Turn project work into reusable knowledge — an AI-agent skill for Claude Code & Codex
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
Generate highly simplified personified IP mascot logos with Flat-first geometry, rounded heavy forms, two IP colors plus one background color by default, and extremely subtle neo-skeuomorphic shading. Use when creating an animal, creature, robot, ghost, plant, object, or other character as a minimal square logo or app-icon artwork, including when the agent should infer three distinct IP directions from product-repository context.
A self-interrogation skill packaging 697 senior-engineer questions as a portable Claude/Codex skill and prompt to improve agent reasoning before writing code.
Python library for cleaning and regularising building footprints in geospatial data, aligning edges to principal directions and simplifying polygons for more accurate analysis.
Develop art direction for image generation with curated style cards distilled from Open Image Prompts. Use when choosing or comparing visual directions, improving an existing generation prompt, or translating a subject, use case, or supplied image into a compact creative spec. Use img-gen-prompts for real archive examples, exact source prompts, or gallery browsing.
Generates, optimizes, and validates Cypher 25 queries for Neo4j 2025.x and 2026.x.
Use when a user wants applicant-facing diagnosis and revision advice on a Chinese NSFC (国自然) application draft — asks for 本子把脉, 本子体检, 国自然申请书修改建议, NSFC benzi audit, 帮我看国自然本子, 标书逻辑诊断, 青年/面上/地区基金申请书修改, 对照已中本子, 从中标样本提炼写法规律, 选题撞题核查, or 申请代码选得对不对 — or wants critique of the title, abstract, key scientific questions, rationale, research contents, innovation, feasibility, research basis, 代表作/代表性论著 quality and support, or cross-section consistency. Accepts PDF/DOCX/Markdown/text or extracted draft text. This is applicant revision advice, not formal communication-review opinions; for expert review forms use nsfc-review.
Create visual identity systems: color palettes, font pairings, style direction, and rendered preview PDFs. Use when the user needs a cohesive design system before building a deck, presentation, document, or any visual project. Works for consulting engagements, product pitches, personal brands, or any context requiring a unified visual language. Produces a markdown design brief, a JS config, and a preview PDF.
DORMANT (ADR-0017, 2026-07-20) - the TERMINAL VELOCITY scroll-film was retired and apps/landing is a static site with no GL surface; this skill is preserved for any future WebGL rebuild (conventions, verified version pins, playhead/scroll-rig/VAT/Gerstner/post-chain patterns, budgets, gate + semantic-layer machinery). Do not load for current apps/landing work - the static site routes to project-steward.
Shared read-side contract every read-only CRITIC imports — adversarial stance, empirical verification of runtime-behavior claims, the mandatory self-red-team before APPROVE, spec-UB sweeps, and the miss-ledger mechanism. The review-side mirror of author-contract. Load at the start of any review task.