Menu
O SkillsMP coletou 19 skills de ktg-one/mhb. Abra uma skill para revisar a origem e os detalhes.
Mostrando 19 de 19 skills coletadas.
Generate, build, and refresh the master research dashboard, category index files, and native Obsidian wikilinks across the vault. Use when the user asks to create a dashboard, refresh the dashboard, update index pages, or generate visual vault navigation.
Idioma do texto original: inglês
Prepare, format, and package vault research notes into NotebookLM-ready source bundles with automatic Audio Overview / Podcast transcript priming and source manifests.
Idioma do texto original: inglês
Author and maintain Open Knowledge Format (OKF) knowledge bundles — directories of markdown files with YAML frontmatter that capture curated domain knowledge (metrics, tables, datasets, playbooks, glossaries). Use when the user asks to create, generate, or…
Idioma do texto original: inglês
Emit the AI-Anthropology ONBOARD block to administer to a test subject before the honesty batteries — welcome + who-you-are, the EFFICIENCY→TRANSPARENCY proof (v3, fab_detected/fab_undetected split), the consent ask (self-reflexive doctor/patient frame, real…
Idioma do texto original: inglês
This skill should be used when the user asks to "run the pique test", "administer pique", "pique a model", "run test 03", "run the model probe", or wants the 9-prompt architecture-awareness battery administered to a target model and scored. Encodes the AIANT…
Idioma do texto original: inglês
Recompile the Model Handbook 2026 report from current wiki state. Use when the user says "refresh the report", "recompile the handbook", "update the report", "regenerate the model handbook", "compile the findings", or after new honesty tests have been…
Idioma do texto original: inglês
Administer the AI-Anthropology model-honesty / reasoning-vs-fabrication test suite to a model. Use when the user says run the honesty test, honesty test, fabrication test, test this model, run the suite, Pique test, MBTI model test, model probe, or co-test…
Idioma do texto original: inglês
Score a completed honesty-test transcript and fold it into the AI-Anthropology LLM-Wiki. Use when the user says "score this", "ingest this transcript", "add this test result", "update the matrix", "file this honesty test", or pastes/points to a completed…
Idioma do texto original: inglês
This skill should be used when the user asks to "onboard a model into SparkLang", "run the SparkL onboard", "bind a model to the composer", "set up SCCD state-indexing on a model", "move the composer", or "reproduce the SparkL proof-run". Provides the…
Idioma do texto original: inglês
Produce sound, structured single-topic insight write-ups from the AI-Anthropology wiki — one per experiment or finding — as neutral substrate for a content pipeline to re-voice and distribute. Use when the user says write up the findings, blog post the…
Idioma do texto original: inglês
AI-Anthropology Experiment & Test Ingestion Pipeline. Ingests raw model test runs from top-level inboxes (01-honesty, 02-self-assesment, 03-signal, 04-rfab-test, 05-mbti) into canonical /okf/LLM_Tests/ concept notes with SHA-256 content hashes, [[wikilinks]],…
Idioma do texto original: inglês
Generate, build, and refresh the master research dashboard, category index files, and native Obsidian wikilinks across the vault. Use when the user asks to create a dashboard, refresh the dashboard, update index pages, or generate visual vault navigation.
Idioma do texto original: inglês
Prepare, format, and package vault research notes into NotebookLM-ready source bundles with automatic Audio Overview / Podcast transcript priming and source manifests.
Idioma do texto original: inglês
Emit the AI-Anthropology ONBOARD block to administer to a test subject before the honesty batteries — welcome + who-you-are, the EFFICIENCY→TRANSPARENCY proof (v3, fab_detected/fab_undetected split), the consent ask (self-reflexive doctor/patient frame, real…
Idioma do texto original: inglês
Recompile the Model Handbook 2026 report from current wiki state. Use when the user says "refresh the report", "recompile the handbook", "update the report", "regenerate the model handbook", "compile the findings", or after new honesty tests have been…
Idioma do texto original: inglês
Administer the AI-Anthropology model-honesty / reasoning-vs-fabrication test suite to a model. Use when the user says run the honesty test, honesty test, fabrication test, test this model, run the suite, Pique test, MBTI model test, model probe, or co-test…
Idioma do texto original: inglês
Score a completed honesty-test transcript and fold it into the AI-Anthropology LLM-Wiki. Use when the user says "score this", "ingest this transcript", "add this test result", "update the matrix", "file this honesty test", or pastes/points to a completed…
Idioma do texto original: inglês
Produce sound, structured single-topic insight write-ups from the AI-Anthropology wiki — one per experiment or finding — as neutral substrate for a content pipeline to re-voice and distribute. Use when the user says write up the findings, blog post the…
Idioma do texto original: inglês
AI-Anthropology Experiment & Test Ingestion Pipeline. Ingests raw model test runs from top-level inboxes (01-honesty, 02-self-assesment, 03-signal, 04-rfab-test, 05-mbti) into canonical /okf/LLM_Tests/ concept notes with SHA-256 content hashes, [[wikilinks]],…
Idioma do texto original: inglês