Overview
Skillarum turns selected public website pages into portable SKILL.md documents for agent harnesses such as Codex, Claude Code, and Hermes. Work is separated into five inspectable stages: acquire, prepare, process, parse, and render.
The crawler restricts acquisition to configured HTTP(S) origins, honours robots.txt, validates redirects, and records provenance for every page. Source text is delimited as untrusted data for LLM generation; generated code is never executed.
The deterministic backend is offline and source-extractive; optional OpenAI and Ollama backends provide provider generation with typed fallback traces. Rendered skills carry provenance manifests, and an evidence-gated research package aggregates run observations into descriptive statistics, figures, and a scholarly manuscript.
This release pairs the software source snapshot with the companion manuscript PDF.
Overview source: Curated paper metadata.
Methods and contributions
Read the source for the full argument, qualifications, and evidence.
Findings and contributions
- Across 7 completed observations from 2 source profiles, the package-valid rate was 100.0%, with 0 fallback observations and 5 truncated pages.
- The author stresses these rates are conditional on run completion and descriptive, not an end-to-end success probability or population estimate.
- Source coverage was 37 of 37 page mappings, with a 95% model reference interval of 90.5% to 100.0%.
- Human-review agreement is pending: the report contains no rater identifiers or shared cases, so no inter-rater statistic is reported.
- The paper states it does not establish improved semantic quality, lower latency, complete coverage or downstream safety; these remain hypotheses.
Methods
- Five-stage pipeline: acquisition, preparation, generation, parsing, rendering — Skillarum turns selected server-rendered pages into SKILL.md packages through separated stages that record page hashes, URLs, request events, provider attempts and integrity metadata.
- SHA-256 content-aware cache identities and provenance predicates — Defines a formal model with hashed cache identities and a provenance-completeness predicate combining package-level provenance with pagewise lineage.
- Interchangeable generators with deterministic default and fallback — Deterministic, OpenAI, Ollama, command and fallback generators with typed retry traces; all recorded backends in the reported runs were deterministic.
- Live case studies on two configured website source areas — Evaluation runs on Math 4 Wisdom and Active Inference Institute website profiles and their target bundles, alongside local fixture tests for redirects, robots, injection and caching.
- Clopper–Pearson reference intervals and planned weighted Cohen kappa — Reports rates with exact binomial reference intervals and a seeded bootstrap policy; human-review agreement is to use linear-weighted kappa once two raters exist.
Key concepts
- website extraction
- agent skills
- provenance
- reproducibility
- prompt injection
- static compilation
Summary sources: Paper metadata and evidence · Learning guide · Extracted source text.
PDF downloads
Archived files available directly from this site.
- Skillarum_combined.pdf PDF · 3.46 MiB · extracted-text source
Citation
Citation metadata follows the unified bibliography.
Catalog details and resources
Related in Computational
Other catalogued works in the same domain.