GitHub user
Agent skills by iusztinpaul
- skills
- 42
- repositories
- 3
Repositories by iusztinpaul
- designing-real-world-ai-agents-workshopHands-on workshop: Build a multi-agent AI system from scratch — Deep Research Agent + Writing Workflow served as MCP servers. Includes code, slides, and video513 stars · 23 skills
- squidThe Software Factory203 stars · 13 skills
- ai-research-os-workshopHow to turn your Second Brain into a living research memory that your agents maintain. Workshop with slides, video and code.179 stars · 6 skills
Skills by iusztinpaul, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Builds bidirectional Streamlit Custom Components v2 (CCv2) using st.components.v2.component. | iusztinpaul/ | 513 | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 2 | Health-check a research directory produced by /research. An agent skill from iusztinpaul/ai-research-os-workshop. | iusztinpaul/ | 179 | — | ~2.3k | Automated safety check: Pass | MIT | 3 mo ago |
| 3 | Expert guide for the NotebookLM CLI (nlm) and MCP server - interfaces for Google NotebookLM. | iusztinpaul/ | 179 | 1 repo | ~6.9k | Automated safety check: Pass | MIT | 3 mo ago |
| 4 | Building chat interfaces in Streamlit. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. | iusztinpaul/ | 513 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 5 | Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the human a validated, ready-to-squash-merge PR. | iusztinpaul/ | 203 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 6 | 6.Research Build, extend, AND query a persistent LLM-maintained wiki for any research topic. | iusztinpaul/ | 179 | — | ~17k | Automated safety check: Pass | MIT | 3 mo ago |
| 7 | Building dashboards in Streamlit. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. | iusztinpaul/ | 513 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 8 | Implement one task — or a whole list / an approved Tasks Plan — via the inner SWE↔Tester loop, committing each task on PASS. | iusztinpaul/ | 203 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 9 | Building multi-page Streamlit apps. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. | iusztinpaul/ | 513 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 10 | 10.Squid Review Push the committed feature branch, create or update its PR, then run Product Architect acceptance and PR-Reviewer on it. | iusztinpaul/ | 203 | — | ~873 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 11 | Distill a research directory (produced by /research) into a single compact research.md containing a guideline-relative distillation of only the sources that were actually used in a piece of content. | iusztinpaul/ | 179 | — | ~4.4k | Automated safety check: Pass | MIT | 3 mo ago |
| 12 | Choosing the right Streamlit selection widget. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. | iusztinpaul/ | 513 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 13 | Drive CI green on a pushed, review-clean feature PR — On-Call diagnoses failures and hands fix tasks to the SWE. | iusztinpaul/ | 203 | — | ~607 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 14 | Generate a multi-form answer (Marp slide deck, matplotlib chart, Obsidian Canvas, or social content brief) from one or more wiki pages in a research directory and file the output back into… | iusztinpaul/ | 179 | — | ~3.7k | Automated safety check: Pass | MIT | 3 mo ago |
| 15 | Connecting Streamlit apps to Snowflake. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. | iusztinpaul/ | 513 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 16 | Write and evaluate effective Python tests using pytest. An agent skill from iusztinpaul/squid. | iusztinpaul/ | 203 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 17 | Creating and customizing Streamlit themes. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. | iusztinpaul/ | 513 | — | ~3.7k | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 18 | 18.Readwise CLI How to use the Readwise CLI — access highlights, documents, and your entire reading library from the command line | iusztinpaul/ | 179 | — | ~2.3k | Automated safety check: Pass | MIT | 3 mo ago |
| 19 | [REQUIRED] Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit applications. | iusztinpaul/ | 513 | — | ~3k | Automated safety check: Pass | MIT | 4 mo ago |
| 20 | Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings shaped as refactor proposals /squid-refactor can consume directly. | iusztinpaul/ | 203 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 21 | Displaying charts, dataframes, and metrics in Streamlit. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. | iusztinpaul/ | 513 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 22 | Shrink an agent harness (.agents/ skills + resources) to the minimum tokens that keep the exact same logic. | iusztinpaul/ | 203 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 23 | Improving visual design in Streamlit apps. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. | iusztinpaul/ | 513 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 24 | 24.Squid Plan Turn a raw feature spec into an approved Tasks Plan — grill the spec, have the Product Architect groom draft tasks (+ optional ADR and glossary additions), then run ONE human gate that decides… | iusztinpaul/ | 203 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 25 | Optimizing Streamlit app performance. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. | iusztinpaul/ | 513 | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 26 | Plan a refactor as an ordered, commit-grain Tasks Plan with structural acceptance criteria (suite green at every step, no behaviour diff) that /squid-implement-night can execute end-to-end. | iusztinpaul/ | 203 | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 27 | Organizing Streamlit code for maintainability. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. | iusztinpaul/ | 513 | — | ~606 | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 28 | Bootstrap a new repo or component from the opinionated spec library (mode=create), or audit an existing scaffolded repo for drift against the scaffold rules (mode=evaluate, report-only). | iusztinpaul/ | 203 | — | ~2.8k | Automated safety check: Notes | Apache-2.0 | 1 mo ago |
| 29 | End-to-end workflow: research a topic and then write a LinkedIn post about it. | iusztinpaul/ | 513 | — | ~660 | Automated safety check: Pass | MIT | 4 mo ago |
| 30 | Setting up Python environments for Streamlit apps. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. | iusztinpaul/ | 513 | — | ~787 | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 31 | Documents Streamlit CLI commands for running apps, managing configuration, and diagnostics. | iusztinpaul/ | 513 | — | ~1.1k | Automated safety check: Pass | MIT | 4 mo ago |
| 32 | Using third-party Streamlit custom components. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. | iusztinpaul/ | 513 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 33 | Structuring Streamlit app layouts. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. | iusztinpaul/ | 513 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 34 | Covers all Markdown features in Streamlit including GitHub-flavored syntax plus Streamlit extensions like colored text, badges, Material icons, and LaTeX. | iusztinpaul/ | 513 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 35 | Using st.sessionstate to manage state across Streamlit reruns. | iusztinpaul/ | 513 | — | ~1k | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 36 | Bug intake — localise the suspected code, capture a deterministic reproducer, and emit a groomed bug task with a regression-test acceptance criterion, ready for /squid-implement-task or the full… | iusztinpaul/ | 203 | — | ~2k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 37 | 37.Implement Drive a single workshop ticket through the inner SWE↔Tester loop. | iusztinpaul/ | 513 | — | ~5.8k | Automated safety check: Pass | MIT | 4 mo ago |
| 38 | Harness-agnostic version of /implement. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. | iusztinpaul/ | 513 | — | ~5.6k | Automated safety check: Pass | MIT | 4 mo ago |
| 39 | 39.Write Post Generate a LinkedIn post using the LinkedIn Writer MCP server. | iusztinpaul/ | 513 | — | ~455 | Automated safety check: Pass | MIT | 4 mo ago |
| 40 | 40.Research Run deep research on any topic using the Deep Research MCP server. | iusztinpaul/ | 513 | — | ~336 | Automated safety check: Pass | MIT | 4 mo ago |
| 41 | Strip redundancy from prose — docs, READMEs, code comments, docstrings — keeping behaviour identical. | iusztinpaul/ | 203 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 42 | Shrink the memory files sessions load — the root AGENTS.md plus every nested AGENTS.md / CLAUDE.md — to the minimum words that state the same rules: compress wording, delete duplicates and… | iusztinpaul/ | 203 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
Questions, answered from the data.
What is the best skill by iusztinpaul?
Building Streamlit Custom Components V2 from iusztinpaul/designing-real-world-ai-agents-workshop ranks first of the 42 skills by iusztinpaul listed here, with the highest score: its repository has 513 GitHub stars, its SKILL.md loads about 2.8k tokens and it passes the automated safety check with no findings. Next come Research Lint and Nlm Skill.
Are iusztinpaul's skills official?
None yet. All 42 skills by iusztinpaul listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.