All authors
Claude Skills by tools-only
github.com/tools-only19,166 skills18 installs6,168 views
- 2605 2026 02 19 Echoes Of Ai Maintainability Study 2788489d**Date:** 2026-02-19 **Evaluator:** Claude Code (eval-resource skill) **Status:** Integrated (section Productivity Research) ---Votes: 0GitHub stars: 9
- 2605 Google Scholar Search D741455bComprehensive guide to searching Google Scholar for academic papers, including advanced search operators, filtering strategies, and metadata extraction.Votes: 0GitHub stars: 9
- 2606 Addy Osmani Linkedin Anthropic Study F7746b1f**Date**: 2026-02-01 **Evaluator**: Claude (Sonnet 4.5) **URL**: https://www.linkedin.com/posts/addyosmani_ai-programming-softwareengineering-activity-7423836698100416513-H0W4 **Author**: Addy Osmani (Engineering Leader, Google) **Publication Date**: February 1, 2026 **Reach**: 246,805 followers ---Votes: 0GitHub stars: 9
- 2607 Agents Md Empirical Study 2602 11988 D28bbbea- **Question de recherche** : Les fichiers de contexte de type AGENTS.md améliorent-ils réellement les performances des coding agents ? - **Résultat principal** : Les fichiers developer-written améliorent légèrement le taux de succès (+4%), mais LLM-generated les dégradent (-3%) — dans tous les cas, le coût d'inférence augmente de 20-23% - **AGENTbench** : Nouveau benchmark introduit, 138 instances, 12 repositories avec des context files écrits par des développeurs (bug fixes + feature additionsVotes: 0GitHub stars: 9
- 2607 Completeness Report Plugin Creator Bf91f9a2**Skill path**: `plugins/plugin-creator/skills/plugin-creator/SKILL.md` **Audit date**: 2026-02-26 **Rubric**: 8-category, 0–3 per category, 24 points total **Validator token count**: 6,979 tokens (SK006 warning: above 4,400 threshold; below 8,800 error threshold) ---Votes: 0GitHub stars: 9
- 2607 Pubmed Search 5b0933e6Comprehensive guide to searching PubMed for biomedical and life sciences literature, including MeSH terms, field tags, advanced search strategies, and E-utilities API usage.Votes: 0GitHub stars: 9
- 2608 Boris Cowork Video Eval C06b4f9e**Date**: 2026-01-26 **Evaluator**: Claude (Sonnet 4.5) **Status**: Partially integrated (high-priority items) ---Votes: 0GitHub stars: 9
- 2608 Evidence Synthesis 8b70f676Evidence synthesis involves systematically reviewing, analyzing, and integrating research findings to inform clinical recommendations. This guide covers guideline sources, evidence hierarchies, systematic reviews, meta-analyses, and integration of multiple evidence streams for clinical decision support.Votes: 0GitHub stars: 9
- 2608 Typing B1ef9c8bAlloy provides precise static types for commands and ask via `.pyi` stubs. - Use `@command(output=T)` for a typed result `T`. - If you omit `output`, the command returns `str` (and `Awaitable[str]` for async). - Parameters are preserved (ParamSpec), so your decorated command keeps the same args. - Streaming always yields text chunks (`str`). Basics ```python from alloy import command, ask @command(output=float) def extract_price(text: str) -> str: return f"Extract price from: {text}" price: f...Votes: 0GitHub stars: 9
- 2609 Jon Williams Dual Instance Pattern A728d19f**Evaluated**: 2026-02-04 **Evaluator**: Claude Sonnet 4.5 **Methodology**: Resource evaluation workflow v1.0 (fetch → analyze → challenge → fact-check) ---Votes: 0GitHub stars: 9
- 2610 Prompt Repetition Paper 7f42a4bf**Date**: 2026-01-25 **Paper**: "Prompt Repetition Improves Non-Reasoning LLMs" **Authors**: Yaniv Leviathan, Matan Kalman, Yossi Matias (Google Research) **Published**: 17 Dec 2025 **arXiv**: https://arxiv.org/abs/2512.14982 ---Votes: 0GitHub stars: 9
- 2611 Latex Poster Packages 564e45c3Three major LaTeX packages dominate research poster creation: beamerposter, tikzposter, and baposter. Each has distinct strengths, syntax, and use cases. This guide provides detailed comparisons and practical examples.Votes: 0GitHub stars: 9
- 2611 Se Cove Plugin D9e939fd**Date**: 2026-01-24 **Evaluator**: Claude Code Ultimate Guide (via /eval-resource skill) **Resource**: SE-CoVe (Chain-of-Verification) Claude Code PluginVotes: 0GitHub stars: 9
- 2612 Kaizen External Research 521a6a13**Status:** ALL 4 RESEARCH TRACKS COMPLETE **Date:** 2026-02-17 **Total sources verified:** 150+ (41 from Track 3 alone) > **CAVEAT**: This document was reconstructed from teammate messages in the orchestrator's conversation context. Some detail may have been lost during context compaction. Citations and URLs are preserved from the researcher's final report. The full per-track bibliographies (41 + 35 + 37 + 29 sources) were referenced but not fully transmitted before the researcher shut down....Votes: 0GitHub stars: 9
- 2612 Poster Design Principles D09d15ecEffective poster design balances visual appeal, readability, and scientific content. This guide covers typography, color theory, visual hierarchy, accessibility, and evidence-based design principles for research posters.Votes: 0GitHub stars: 9
- 2613 Kaizen Plugin Plan F282a64b**Status:** Phase 3 — Detailed Design (in progress) **Date:** 2026-02-18Votes: 0GitHub stars: 9
- 2613 Poster Layout Design 0f4e15b2Effective poster layout organizes content for maximum impact and comprehension. This guide covers grid systems, spatial organization, visual flow, and layout patterns for research posters.Votes: 0GitHub stars: 9
- 2614 Darpa Guidelines 547536ad**Mission**: Make pivotal investments in breakthrough technologies for national securityVotes: 0GitHub stars: 9
- 2616 Nih Guidelines 7cdbc861**Mission**: To seek fundamental knowledge about the nature and behavior of living systems and to apply that knowledge to enhance health, lengthen life, and reduce illness and disabilityVotes: 0GitHub stars: 9
- 2617 Build Spec F3072f59Конфигуратор 1С:Предприятия 8.3 поддерживает пакетный (безоконный) режим для автоматизации операций с конфигурациями, информационными базами и внешними обработками. Все операции выполняются через командную строку `1cv8.exe`.Votes: 0GitHub stars: 9
- 2617 Discuss Context 5f70a3ffDate: 2026-02-19Votes: 0GitHub stars: 9
- 2617 Nsf Guidelines 10523438**Mission**: To promote the progress of science; to advance the national health, prosperity, and welfare; to secure the national defenseVotes: 0GitHub stars: 9
- 2618 Nstc Guidelines 0e71e945> ⚠️ **IMPORTANT DISCLAIMER**: This guide is based on publicly available information and general academic writing principles. **Always consult the official NSTC website and your specific program's solicitation for the most accurate and up-to-date requirements.** Requirements may vary by field, program type, and year.Votes: 0GitHub stars: 9
- 2619 Beamer Guide 9084c4b9Beamer is a LaTeX document class for creating presentations with professional, consistent formatting. It's particularly well-suited for scientific presentations containing equations, code, algorithms, and citations. This guide covers Beamer basics, themes, customization, and advanced features for effective scientific talks.Votes: 0GitHub stars: 9
- 2637 Liquidity Planner 39a0a3d3Plan liquidity positions and generate deep links that open directly in the Uniswap interface with parameters pre-filled. Supports v2, v3, and v4 positions.Votes: 0GitHub stars: 9
- 2638 Swap Planner 5e8b8727Plan token swaps and generate deep links that open directly in the Uniswap interface with parameters pre-filled.Votes: 0GitHub stars: 9
- 264 Quickstart 8548c926Interactive onboarding guide — set up Weaviate Cloud, configure credentials, load data, and learn every commandVotes: 0GitHub stars: 9
- 2665 P1 Meta Process Capture Expert Panel Dataset Builder Eceaac36Document the multi-agent expert panel methodology as a reusable system for building datasets that inform skills and systems. The process — assign framework experts to repositories, ask structured questions, cross-examine, synthesize, map to requirements, validate — produced high-quality sourced findings. Capture this as a repeatable pattern.\n**Key elements to document**:\n- Expert assignment protocol (one agent per source repo, source-code-only evidence standard)\n- Question group design (th...Votes: 0GitHub stars: 9
- 2666 State Machine E67882d1Canonical state machine for backlog items. All skills that modify item state MUST reference this document and enforce only allowed transitions. SOURCE: Derived from GSD STATE.md patterns and comparative analysis of claude_skills backlog management (accessed 2026-02-26). ---Votes: 0GitHub stars: 9
- 2670 Saas F8f25394<!-- Updated: 2026-02-07 -->Votes: 0GitHub stars: 9
- 2670 Summary 64099e81| Pipeline | Topic 1 | Topic 2 | Topic 3 | Topic 4 | Topic 5 | **Average** | |----------|---------|---------|---------|---------|---------|------------| | | Claude Code | Seedance | MacBook | Rap Songs | React/Svelte | | | **CROSS** | **4.90** | **4.90** | **4.20** | **4.80** | **4.90** | **4.74** | | **HN** | 4.05 | 4.55 | 3.85 | 4.25 | 3.80 | **4.10** | | **Base** | 3.80 | 3.70 | 3.70 | 3.65 | 3.80 | **3.73** |Votes: 0GitHub stars: 9
- 2676 Csw Vs Aws Analysis 18b915fa> 分析日期：2026-02-27 > 分析对象：[claude-scientific-writer](https://github.com/K-Dense-AI/claude-scientific-writer) v2.12.0 (以下简称 **CSW**) 与本仓库 academic-writing-skills (以下简称 **AWS**) ---Votes: 0GitHub stars: 9
- 2677 Forbidden Terms 7219e9b9Protected terms and constructs that **must never be modified** without explicit user confirmation. These rules apply to all audit modes (self-check, review, gate, polish). ---Votes: 0GitHub stars: 9
- 2678 Polish Guide F2f26d02- Prefer active voice, sentences < 25 words avg - Eliminate hedge words: "somewhat", "rather", "quite" - Strong verbs: "demonstrate" > "show", "employ" > "use", "achieve" > "get" - Never start Introduction with "In this paper, we..." - Transformations: "In order to" → "To", "It can be seen that" → (delete)Votes: 0GitHub stars: 9
- 2679 Review Criteria D1ebf1b0Unified review criteria for paper audit, based on major conference standards (NeurIPS, ICLR, ICML, IEEE, ACM).Votes: 0GitHub stars: 9
- 2680 Scholar Eval Guide 2f229e2cBased on ScholarEval (arXiv:2510.16234), adapted for the Paper Audit skill.Votes: 0GitHub stars: 9
- 2690 Priors 65edf17f- [The Foundational Role of Priors](#the-foundational-role-of-priors) - [Hierarchy of Prior Informativeness](#hierarchy-of-prior-informativeness) - [Weakly Informative Defaults](#weakly-informative-defaults) - [Regression and GLM Priors](#regression-and-glm-priors) - [High-Dimensional and Sparse Priors](#high-dimensional-and-sparse-priors) - [Hierarchical Model Priors](#hierarchical-model-priors) - [Prior Predictive Checking](#prior-predictive-checking) - [Sensitivity Analysis](#sensitivity-analVotes: 0GitHub stars: 9
- 2708 2026 02 25 Feat Goat Synthesis Output Comparison Plan D93c4326The synthesis output - the "What I learned" / "I'm now an expert on X" narrative - is the ONLY thing that matters. All data collection, scoring, deduplication, and rendering exist solely to produce the best possible synthesis. This plan runs 15 synthesis comparisons (5 topics x 3 versions), judges which version produces the best final output, and creates concrete changes to make CROSS the GOAT.Votes: 0GitHub stars: 9
- 2709 2026 02 26 Feat Polymarket Smarter Synthesis Plan 30846fb4Polymarket data is one of the most powerful signals when relevant - real money on outcomes cuts through opinion. But the current system buries the most interesting markets and gives the LLM zero guidance on how to synthesize prediction market data.Votes: 0GitHub stars: 9
- 2710 Eval 3 Macbook 67832f5a**Query Type:** RECOMMENDATIONS **Label Map (REVEAL AFTER SCORING):** {'A': 'hn', 'B': 'base', 'C': 'cross'}Votes: 0GitHub stars: 9
- 2711 Eval 4 Rap 50c5bddc**Query Type:** RECOMMENDATIONS **Label Map (REVEAL AFTER SCORING):** {'A': 'hn', 'B': 'base', 'C': 'cross'}Votes: 0GitHub stars: 9
- 2712 Cross Synthesis Prompt B5346f04After all searches complete, internally synthesize (don't display stats yet):Votes: 0GitHub stars: 9
- 273 Overview 0dc3a895[Home](../README.md) > [Docs](README.md) > OverviewVotes: 0GitHub stars: 9
- 2766 Pandoc Server A65d4d68The Pandoc MCP Server provides powerful document conversion capabilities using the versatile pandoc tool. This Go-based server enables text conversion between 30+ document formats with support for standalone documents, table of contents generation, and custom metadata. It serves as a bridge between the MCP protocol and pandoc's extensive format conversion capabilities.Votes: 0GitHub stars: 9
- 2767 Latex Server E6f7093bThe LaTeX MCP Server provides comprehensive capabilities for LaTeX document creation, editing, and compilation. It supports creating documents from templates, adding content, and compiling to various formats including PDF, DVI, and PS. The server includes built-in templates for articles, letters, beamer presentations, reports, and books.Votes: 0GitHub stars: 9
- 572 Usage Guide 03d4d3b2Implement proper cross-validation strategies to get unbiased performance estimates on biomedical datasets and avoid overfitting during biomarker discovery.Votes: 0GitHub stars: 9
- 572 Usage Guide 08d4914cThis guide covers exporting publication-ready figures with proper resolution, sizing, and formatting.Votes: 0GitHub stars: 9
- 572 Usage Guide 1a0cd4bcPICRUSt2 predicts metagenome functional content from 16S/18S marker gene data by inferring gene content from phylogenetically related reference genomes.Votes: 0GitHub stars: 9
- 572 Usage Guide 1ba530fbThis skill enables AI agents to help you run BLAST searches locally using BLAST+ command-line tools, enabling fast unlimited searches against custom or downloaded databases.Votes: 0GitHub stars: 9
- 572 Usage Guide 3539c36eFCS (Flow Cytometry Standard) is the standard file format for cytometry data. flowCore provides comprehensive tools for reading, writing, and manipulating FCS files.Votes: 0GitHub stars: 9