Menu
SkillsMP has collected 41 skills from MoeenNehzati/famulus. Open a skill to review its source and details.
Showing 40 of 41 collected skills.
Use when the user asks to install, update, propagate, or repair the `assistant`, `collab`, `coauthor`, or workspace helper commands, including missing or stale launchers and shell integration. Do not use for unrelated software or plugin installation.
Use when the user asks to set up or manage a recurring AI job. Do not use for one-off commands or generic scheduler questions.
Use when the user needs to set up or restore Google authentication for Famulus. Do not use for ordinary Google-service operations.
Use when the user asks to view or change a persistent personal list. Do not use for an ad hoc generated list, repository inventory, or prose checklist.
Use when the user or another skill needs to read from or write to the configured LLM root of a remote. Do not use for local files or remote paths outside that LLM root.
Use when the user asks to view or change their Google Calendar. Do not use for daily planning.
Use when the user asks to create a personal skill or change an existing personal skill's intended behavior or public interface in the shared skills directory. Do not use for behavior-preserving refactoring, blueprint regeneration, certificate work, or…
Use when the user asks for inbox-level email triage or processing. Do not use for ordinary email access, sending, or analysis of a single message.
Use when `wrap-up` needs to identify recent work sessions that may still require a handoff. Do not invoke directly for transcript review, interpretation, or summarization.
Use when the user asks whether Officina node certificates are current or stale, or asks for canonical node hashes. Do not use to issue certificates.
Use when GitHub Actions CI is red, matrix failures need isolated repair, or repeated full reruns make remote diagnosis inefficient.
Use when the user asks for a direct assumptions-to-results dependency graph of a LaTeX mathematical document. Do not use for proof, notation, prose, or literature review.
Use when registered Officina nodes or their owned files must be moved while mechanically updating blueprint ownership, references, generated artifacts, and callers. Do not use for behavioral refactoring or certification.
Use when fresh certificates are requested for one or more Officina nodes. Do not use merely to check certificate currentness or canonical node hashes.
Use when the user asks to schedule or manage an automatic assistant-session wakeup after a usage reset or timeout.
Use when the user asks to send feedback, report a problem, or describe a failed Famulus workflow to its maintainer. Do not use for ordinary email or for reviewing document content.
Use when a user or another skill directs the agent to use a named compass.
Use when the user asks to audit a bibliography or apply corrections identified by a bibliography audit. Do not use for general LaTeX citation editing.
Use when the user asks to plan their day, decide what to work on today, or review an existing daily plan. Do not use for a standalone calendar or list request, or for an end-of-day wrap-up.
Use when the user asks to access or manage email or a registered email account. Do not use when the primary request is inbox triage or shared Google authentication setup.
Use when the user asks for sentence-level editing of technical prose while preserving its substance. Do not use for proof, notation, document-flow, or substantive review.
Use when the user asks about weather for the current location or a named location, including a specific day or date range.
Use when a task will edit a Git repository or the user asks to inspect or change Git state. Do not use solely because a read-only task happens inside a repository.
Use when the user asks to create or change an assistant lifecycle hook that must support multiple hosts or runtimes. Do not use for ordinary Git hooks or single-host automation.
Use when the user asks to initialize a brand-new TDD project. Do not use for adding TDD to an existing project.
Use when compiling or troubleshooting a LaTeX document inside a VS Code project whose build is governed by LaTeX Workshop. Do not use for LaTeX compilation outside a VS Code project.
Use when the user explicitly asks to enter or continue loose mode. Do not infer it from an ordinary request for ideas, options, strategy, or an overview.
Use when the user asks to create or standardize a TeX document-profile comment, or when a selected TeX task requires profile information that the document does not state clearly. Do not use merely because the target is a `.tex` file.
Use when the user asks to review, simplify, or standardize mathematical notation. Do not use for proof, prose, or document-flow review.
Use when research-paper analysis requires readable source or text that is not already available. Do not use for generic non-research PDFs.
Use when the user explicitly asks for a handoff, or when pausing, ending, or switching away from substantial project work that produced continuity-relevant knowledge. Do not use for ordinary remember-this requests, short clarifications, incidental switching,…
Use when the user asks to audit the soundness, coherence, or redundancy of a mathematical proof or claimed implication. Do not use to write a new proof or for notation, prose, computation, code, or LaTeX work.
Use when the user asks for a behavior-preserving audit or refactor of a registered Officina node or one of its owned sources. Do not use for feature work, bug fixes, generic code review, or files outside registered node ownership.
Use when an existing skill blueprint needs regeneration, whether requested directly or required by another skill. Do not use for ordinary blueprint editing or synchronization.
Use when integrating substantially diverged Git branches and merge or rebase is inadequate because it produces broad structural conflicts, or because mechanical application would place source changes into structures the target architecture has replaced and…
Use when the user asks for document-level review of technical structure, motivation, or reader flow. Do not use for sentence editing, proof review, or notation review.
Use when the user explicitly asks for tight mode or emphasizes that rigor, verification, or careful attention to detail should take priority over speed or breadth. Do not use for ordinary requests that merely expect baseline accuracy.
Use when the user asks whether a specific mathematical theorem, method, framework, or formalism applies to a target problem. Do not use for generic software tools, line-by-line proof review, or broad strategy without a candidate mathematical tool.
Use when the user asks to create, change, or audit a canonical repository standard. Do not use for generic policy or documentation work.
Use when the user explicitly asks to wrap up or formally close the workday or current session. Do not use for status or completeness questions such as “anything else remaining?” or “are we done here?”, ordinary task completion, or a handoff-only request.