Menu
SkillsMP has collected 32 skills from nicsuzor/academicOps. Open a skill to review its source and details.
Showing 32 of 32 collected skills.
Standing experiment protocol for the academicOps project — every piece of real work is also evidence about the framework. Use when starting framework work of any type, testing instructions blind, trialling a runtime mechanism, or reviewing how well the…
Creating diagrams in any style — Mermaid flowcharts (structured, code-based) or Excalidraw (hand-drawn, organic). Use style parameter to select.
Use when driving a framework run you intend to score — choosing a surface, dispatching a worker, or when asked to "debug a polecat", "run a polecat container interactively", "attach to a polecat session", "check polecat logs", or to verify that a change to…
Turn an ask — a captured node or a raw note handed straight to you — into one unit a cold agent can be dispatched onto and judged against — placed, valued, wired, its assumptions sorted into tested and hopes, its forks named with the probe that settles each;…
Turn something that went wrong into a lesson that lands somewhere useful. Diagnoses the incident back to the structural cause that invited it, then routes the lesson to the one destination its scope actually claims — task record, project rule, PKB, framework…
Write knowledge into the PKB and keep it worth trusting. Capture mode persists facts, decisions, and state as they emerge; consolidation mode turns episodic records into durable knowledge and repairs what has drifted. Every write integrates into what is…
Triage a corpus, classify, and dispatch outputs. Three modes: retro (transcript review → issues), trend (longitudinal performance analysis), sweep (GitHub issue triage → fix-epics). Delegates execution to pauli for all three modes to keep main context clean.
Fast disambiguation index — take the ambiguous words in an ask, run a few differently-worded semantic searches, and hand back a shortlist of ids with one-line snippets the caller can then ask more about, flagging any unfinished task that may already cover the…
The return channel. Establish what is actually true about work the graph still claims is in flight and about work that finished while nobody was watching, write those facts back, and return the tasks a landed wave touched to `inbox` for re-planning. Truth…
Coordinator-side pathway to a worker surface — a supervised in-session team or an isolated polecat container. The mandatory route to `polecat run`; a raw invocation outside this skill bypasses the delivery-guard and image-freshness obligations below.
Session exit — one skill, four paths. Bare `/dump` is the emergency bail: resume task plus a short handover, nothing committed. `/dump full` is the canonical close: commit, push, PR, release. `/dump partial` hands back attempted work with the refused…
The thinking pass for "plan this", "what should I do next", and "where does this work go" — fix the altitude, test the plan against the effectual commitments, and route each piece to the stage that owns it.
Multi-agent review of any artifact — a document, plan, proposal, or pull request. James deploys rbg, pauli, and marsha in parallel, then reconciles their findings into one verdict. Pass `comment` and/or `fix` to write the result back to the review surface.
Judgement-based QA pass. Does this artifact meet its goal and serve its user? Demands excellence, not compliance.
Procedural guide for validating a framework change end to end — audit the instruction surface, then prove the behaviour where it actually runs. Use when changing instructions, hooks, or execution plumbing; when certifying a release; or when a change has…
Support academic research data analysis with technology-agnostic principles — research-data immutability, a versioned/tested/reproducible transformation layer, statistical methodology, and self-documenting research. Use this skill for any computational…
General extraction/ingestion skill that routes to specific workflows based on input type. Extracts structured information from documents, emails, reviews, feedback, and other sources.
Turn a captured ask into ONE task that is placed, valued, wired, and actually actionable — assumptions sorted into tested and hopes, open forks named with the probe that would settle each, and a decision list for the user. Promotes `inbox` to `ready`. Runs…
dbt (data build tool) implementation of the analyst transformation layer. Use when a project has a dbt/ directory or you need to build, test, or document SQL transformations as version-controlled, reproducible dbt models. This is the dbt-specific HOW for the…
Python plotting and statistical-modelling libraries (matplotlib, seaborn, statsmodels) for the analyst presentation and statistical-methodology layers. Use when producing publication-quality figures or fitting statistical models in Python. Library-specific…
Streamlit implementation of the analyst presentation layer. Use when building or updating a Streamlit dashboard that displays pre-computed research data. This is the Streamlit-specific HOW for the tech-agnostic principles in the aops-tools analyst skill —…
Claim a queued task, execute it, record the result on the task, and hand over.
Author high-quality deep-research prompts (Gemini / ChatGPT Pro / Perplexity Deep Research), then capture the resulting documents into the PKB — including figure extraction, agent-transcribed alt-text for load-bearing images, frontmatter, and wikilink wiring…
Scaffold research project repositories with smart defaults — repo creation, directory structure, CI/CD, documentation, and PKB integration in one pass.
Keep the PKB graph structurally sound — wire weighted contributes_to edges from work to targets, and run garden passes over parentage, wikilinks, duplicates, and orphans. Fires on graph-hygiene asks, never on valuation or decomposition. Bound to pauli, the…
Instruction quality gate — reviews agent instructions (task bodies, workflow steps, skill procedures, self-test protocols, agent definition files) for shallow-execution vulnerabilities before deployment. Two modes: author (pre-hoc review) and audit (trace a…
Design-stage fitness rubric — persona immersion, scenario design, dimensions that define what excellence looks like for the people a feature serves. Two modes — author (produce a rubric for a new spec) and critique (red-team an existing spec). Output lives on…
Convert markdown documents to professionally formatted PDFs with academic-style typography, Roboto fonts, proper page layouts, and styling suitable for research documents, reviews, reports, and academic writing.
Peer review of research funding applications and academic submissions. Scheme-agnostic — fetches current criteria from the relevant handbook each round, since weights and language change. Covers Detailed Assessor and College-of-Experts / General Assessor…
A basic example skill. Use when you need a template for a new skill.
Analyze writing samples and create a comprehensive personal writing style guide
Fixture skill for build system tests.
Source text: Undetermined