Syed Yasir
Community@syedyasir001 · Bengaluru
:]
Agent Skills by Syed Yasir
Showing 58 vetted skills indexed across 1 GitHub repositories.
Syedyasir001pptx
Create, edit, and inspect PowerPoint .pptx presentations using OOXML manipulation and PptxGenJS.
Syedyasir001planning-with-files
Creates and maintains markdown planning files to track multi-step task progress.
Syedyasir001ui-ux-pro-max
Searches a design database of styles, palettes, typography, and UX guidelines via BM25 CLI.
Syedyasir001using-git-worktrees
Creates isolated git worktrees with directory selection, ignore verification, and baseline test validation.
Syedyasir001multi-agent-patterns
Design and implement multi-agent architectures using supervisor, swarm, and hierarchical coordination patterns.
Syedyasir001defuddle
Extract clean markdown content from web pages using the Defuddle CLI.
Syedyasir001bdi-mental-states
Transform RDF context into BDI agent mental states using formal ontology patterns.
Syedyasir001context-degradation
Diagnose and mitigate context degradation patterns in LLM agent systems.
Syedyasir001test-driven-development
Enforces red-green-refactor test-driven development workflow before writing production code.
Syedyasir001systematic-debugging
Diagnose bugs through a four-phase root cause investigation process before proposing fixes.
Syedyasir001theme-factory
Applies curated color palettes and font pairings to slides, docs, and HTML artifacts.
Syedyasir001context-compression
Implement structured summarization and probe-based evaluation for compressing long agent conversation histories.
Syedyasir001memory-systems
Designs and implements agent memory architectures using vector stores, knowledge graphs, and temporal retrieval.
Syedyasir001doc-coauthoring
Guides collaborative document creation through context gathering, iterative drafting, and reader testing.
Syedyasir001web-design-guidelines
Review UI code files against fetched Web Interface Guidelines and report findings.
Syedyasir001advanced-evaluation
Implement LLM-as-judge pipelines with direct scoring, pairwise comparison, and bias mitigation.
Syedyasir001obsidian-markdown
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, and properties.
Syedyasir001using-superpowers
Enforces skill discovery and invocation before any AI response or action.
Syedyasir001dispatching-parallel-agents
Dispatches concurrent agents to investigate independent failures across separate problem domains.
Syedyasir001claude-api
Build, debug, and optimize applications using the Claude API and Anthropic SDKs.
Syedyasir001xlsx
Create, edit, and recalculate Excel spreadsheets with formulas using openpyxl and LibreOffice.
Syedyasir001Extract, merge, split, create, and fill PDF documents using Python libraries and command-line tools.
Syedyasir001executing-plans
Executes written implementation plans task-by-task with verification checkpoints and review gates.
Syedyasir001algorithmic-art
Generates seeded p5.js generative art with interactive HTML viewers and parameter controls.
Frequently Asked Questions About Syed Yasir
FAQPage SchemaWhat tasks can I accomplish with Syed Yasir's skill registry?▼
The 115 skills cover agent system design (multi-agent patterns, BDI mental states, memory frameworks like Mem0 and Zep), context engineering (compression, optimization, degradation diagnosis), document processing (PDF, DOCX, XLSX, PPTX), Obsidian vault management, React/Next.js optimization, Postgres tuning, and structured development practices like TDD and systematic debugging.
Who is the target audience for these skills?▼
The registry targets engineers building Claude Code and Anthropic SDK applications, agent system architects designing memory and context pipelines, frontend developers working with React 19, Next.js, and React Native, and technical writers producing documentation, internal communications, and Obsidian-based knowledge bases.
How are these skills installed and invoked at runtime?▼
Skills are invoked through the Skill tool in Claude Code, Copilot CLI, or Gemini CLI, with priority rules defined by the using-superpowers skill. Native frontmatter declares user-invocable triggers, allowed tools like Read, Write, Bash, and Glob, plus lifecycle hooks such as UserPromptSubmit, PreToolUse, and PostToolUse for session state management.
What licensing applies to these skills?▼
Licensing is mixed per skill. Vercel-authored skills (react-best-practices, composition-patterns, react-native-skills) and supabase-postgres-best-practices use MIT. Document skills (pdf, docx, xlsx, pptx) are proprietary with terms in LICENSE.txt. Many others reference complete terms in bundled LICENSE.txt files.
What prerequisites and dependencies do these skills require?▼
Dependencies vary by skill: pandas and LibreOffice for spreadsheets, pypdf and pdfplumber for PDFs, Playwright for webapp testing, p5.js for algorithmic art, PIL and imageio for Slack GIFs, FastMCP or the Node/TypeScript MCP SDK for server building, and Anthropic SDKs with prompt caching for Claude API integration.