assess-covariance-method
Provides a protocol for implementing, validating, benchmarking, and statistically evaluating new covariance, correlation, precision estimators, and covariance scoring rules.
Enables terminal-based browsing of PeerTube instances, including video search, details, comments, channels, accounts, instance statistics, and optional OAuth2 access to the user's account.
Browse PeerTube federated video from the terminal — instance stats, latest videos, video detail, comment threads, channels, accounts, instance-local search, and OAuth2 login with per-instance token persistence. Set PEERTUBE_SERVER to any instance; point it at sepiasearch.org for fediverse-wide search. Use when the user mentions PeerTube, federated video, SepiaSearch, or browsing a specific PeerTube instance. Do not use this skill for YouTube/Vimeo uploads, video editing, or installing and administering a PeerTube server.
evals/evals.json
JSON
Other
README.md
Markdown
Reference
references/auth-and-tokens.md
Markdown
Reference
references/endpoint-catalog.md
Markdown
Reference
references/gotchas-field-guide.md
Markdown
Reference
references/search-and-discovery.md
Markdown
Reference
references/worked-recipes.md
Markdown
Script
scripts/peertube
Script
scripts/test_peertube.py
Python
SKILL.md
SKILL.md
Markdown
Provides a protocol for implementing, validating, benchmarking, and statistically evaluating new covariance, correlation, precision estimators, and covariance scoring rules.
Extracts and organizes Douyin video data, transcripts, comments, metadata, and visual evidence into traceable notes, research briefs, scripts, fact-checks, and reusable knowledge …
Enforces a research workflow requiring source-grounded claims, citations, direct quotations from documents, and explicit acknowledgment when information cannot be verified.
Searches Project Gutenberg via Gutendex, downloads book editions, extracts clean text from TXT or EPUB files, and classifies books as fiction, non-fiction, or ambiguous.
Guides agents through rigorous research planning, evidence evaluation, analysis, synthesis, reporting, and durable preservation with traceable source-to-claim relationships.
Provides a methodology for formulating, comparing, validating, and auditing constrained optimization decisions using explicit variables, objectives, feasibility rules, tradeoffs, …
Provides rigorous guidance for statistical analysis, experimental design, causal inference, Bayesian methods, machine learning, reproducibility, and research methodology.
Analyzes persuasive messages by decomposing claims, tracing them to authoritative evidence, identifying misleading framing, and reporting calibrated verdicts while separating lite…