OSS Projects by multiset
Official@BTreeMap · Canada
OSS Projects by multiset enables @MinecraftFuns to fork open-source projects and contribute without cluttering personal repositories.
Agent Skills by OSS Projects by multiset
Showing 18 vetted skills indexed across 1 GitHub repositories.
BTreeMapauthor-skill
Distills procedures and task histories into reusable SKILL.md files for agents.
BTreeMapgit-commit
Drafts and reviews Conventional Commits messages with tiered effort levels and optional push.
BTreeMapadvisor
Analyzes research papers and proposals to judge composition, currency, feasibility, and next experiments.
BTreeMappl-theorist
Applies programming-language theory to design, refactor, review, and test code across thirteen languages.
BTreeMapponytail
Enforces minimal code solutions by prioritizing stdlib and native features over dependencies.
BTreeMapread-pdf
Extracts text and metadata from PDF files or URLs with page-cited evidence.
BTreeMapreframe
Converts planning discussions into testable strategic direction judgments with costed options.
BTreeMapfact-check
Verifies document claims against retrieved sources and applies only user-approved corrections.
BTreeMapponder
Answers open questions through sourced research rounds tracked in a verified ledger.
BTreeMapaesthete
Designs, builds, and reviews WCAG 2.2-compliant web interfaces across marketing and product surfaces.
BTreeMapthematic-analysis
Develops themes from qualitative text under one named methodological school with coded evidence.
BTreeMapsetup-env
Provisions isolated userspace development toolchains per project using uv, conda-forge, and publisher archives.
BTreeMapsearch-web
Searches the web, Wikipedia, and scholarly indexes and extracts readable page text.
BTreeMaphumanize
Rewrites AI-sounding prose to remove AI writing patterns while preserving every claim and citation.
BTreeMaplit-review
Produces literature reviews with citations traced to OpenAlex, arXiv, and Crossref records.
BTreeMapsummon
Delegates tasks to subagents with structured briefs, disjoint fanout, and return review.
BTreeMapcaveman
Compresses replies into terse phrasing while preserving exact technical facts, code, and error strings.
BTreeMappeer-review
Reviews academic papers as an adverse referee with page-anchored objections and derived verdicts.
Frequently Asked Questions About OSS Projects by multiset
FAQPage SchemaWhat tasks can I accomplish with BTreeMap's skill collection?▼
You can draft Conventional Commits, extract and query PDF text with page citations, run adverse peer reviews of papers, build literature reviews from OpenAlex/arXiv/Crossref, fact-check documents against retrieved sources, design WCAG 2.2 web interfaces, code qualitative data thematically, and provision userspace dev toolchains.
Who are these skills designed for?▼
Researchers, software engineers, and technical writers. The advisor, peer-review, and lit-review skills target academics reviewing papers and proposals; pl-theorist, ponytail, and git-commit serve developers across Python, Rust, Go, Haskell, and more; aesthete and humanize serve designers and writers.
What are the installation and runtime requirements?▼
Most skills require uv on PATH and a full SKILLs repository checkout. Retrieval-dependent skills (search-web, lit-review, ponder) also need network access. setup-env runs on Linux and macOS x86_64/arm64, with Windows x86_64 as best effort, using 1-6 GB under a disposable environment root.
Are these skills free and open source?▼
Yes. Every skill in the manifest is released under the MIT license, permitting free use, modification, and redistribution. The collection is maintained as public OSS forks under the BTreeMap organization, with the project site at oss.joefang.org.
Can these skills verify facts and citations reliably?▼
Yes. fact-check verifies claims only against retrieved sources with verbatim quotes, URLs, and access dates; lit-review traces every citation to a retrieved paper, never memory; ponder marks inferred conclusions and reports unsettled points openly. No skill changes text until the user approves corrections.