emaballarin

emaballarin/ccplugins

Plugin Claude Code

Plugin marketplace listing 5 plugins: mf, ccsci, ar, tml, ws.

emaballarin/ccplugins

Instructions file CodexOpenCode

Instructions for emaballarin/ccplugins, covering agents.md and project-specific guidance.

emaballarin/ccplugins

Instructions file

Instructions for emaballarin/ccplugins, a project described as: ✨ Personal plugins for Claude Code (& friends)... maybe worth sharing!

emaballarin/ccplugins

Plugin Claude Code

ar — autoresearch: a skill-only autonomous experiment loop. Propose → measure → keep winners → repeat, against any numeric objective, with noise-floor gating so nothing is banked on noise. Five skills: /ar:start opens a run (dedicated branch + baseline noise floor), /ar:resume advances it, /ar:status prints read-only…

emaballarin/ccplugins

Skill Claude CodeCodex

Write the final summary of an autoresearch run to ./.ar/finalreport.md — trajectory, best commit and its diff, what worked, what failed, and what to try next. Use for /ar:report, "write up the autoresearch results", or "summarise the experiment loop". Reads ./.ar/ar.jsonl from disk, so it works in a fresh session.…

emaballarin/ccplugins

Skill Claude CodeCodex

Run the autoresearch experiment loop — propose one change, measure it, keep it only if it beats the noise floor, repeat. Use to resume or continue an autoresearch run, for /ar:resume, for "keep iterating", "next experiment", "continue optimising", or whenever ./.ar/ar.jsonl exists and the loop should advance.…

emaballarin/ccplugins

Skill Claude CodeCodex

Open a new autoresearch experiment loop — dedicated ar/… git branch, ./.ar/ state, and a measured baseline noise floor so later gains can be told apart from run-to-run scatter. Invoke ONLY when explicitly asked to start an autoresearch run, open an experiment loop, or /ar:start — e.g. "autoresearch this", "start an ar…

emaballarin/ccplugins

Skill Claude CodeCodex

Print the current autoresearch run's state — goal, baseline, noise floor, best-so-far, run tallies, budget, branch, and the last few iterations. Use for /ar:status, "how is the loop doing", "what's the best so far", or any read-only check on an autoresearch experiment. Reconstructs everything from ./.ar/ar.jsonl on…

emaballarin/ccplugins

Skill Claude CodeCodex

End the current autoresearch run — append a status:stopped sentinel to ./.ar/ar.jsonl, which is also what halts the external ar-loop.sh driver. Use for /ar:stop, "stop the loop", "halt autoresearch", or "that's enough iterations". Writes the sentinel and the final report, then prints (does not run) the command to…

emaballarin/ccplugins

Plugin Claude Code

ccsci — research & scientific-computing skills adapted from Claude Science for stock Claude Code. Skills: literature-review (DOI-grounded, all-STEM, BibTeX export), pdf-explore (parse-once big-PDF navigation, table extraction, native-resolution figures), figure-style / figure-composer / paper-narrative (publication…

emaballarin/ccplugins

Agent

Scientific-computing specialist for data analysis, modelling, simulation, numerical experiments, dataset processing, and running scientific code. Works in its own context, produces real artifacts (figures, tables, reports, processed data), and returns a structured summary with file paths. Use proactively for any…

emaballarin/ccplugins

Agent

Deep research specialist for literature audits, technical comparisons, and open-ended questions that need many sources synthesised into one answer. Investigates in its own context and returns only a structured Markdown summary with sources. Use proactively for any request to "research", "do a literature review"…

emaballarin/ccplugins

Skill Claude CodeCodex

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

emaballarin/ccplugins

Skill Claude CodeCodex

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers.…

emaballarin/ccplugins

Skill Claude CodeCodex

Compose one publication-grade multi-panel figure. Entry from a one-line claim + data refs, OR from an existing figure via deriveoutlinetask(png). Runs a per-figure loop: outline (12-col grid, per-panel ask + labelbudget) → fan-out one Task subagent per panel (each loads figure-style) → tile + stamp letters →…

emaballarin/ccplugins

Skill Claude CodeCodex

Publication-grade figure correctness and legibility rules. Load before drawing any plot and call applyfigurestyle() — sets a role-mapped font-size ladder, outward ticks, frameless legends, and 300-dpi output. The skill is a checklist, not a house look: data fidelity (claim-titles tested against every row, excluded…

emaballarin/ccplugins

Skill Claude CodeCodex

Find, verify, and synthesize STEM literature across every field — from "what's the seminal paper for X" through full multi-source reviews. Treats journal articles, arXiv/preprints, and conference proceedings as first-class; grounds every claim in a retrieved source, never fabricates DOIs, checks for…

emaballarin/ccplugins

Skill Claude CodeCodex

Judge and reshape the STORY a paper's figures tell. Input is the work itself — manuscript (or abstract) + figure deck — no hand-written brief. derivepaperbrieftask(abstract, captions) builds the prompt whose JSON is pitch/vision/per-figure-claims; a handling-editor reviewer on the full deck returns hookverdict (would…

emaballarin/ccplugins

Skill Claude CodeCodex

Use this skill when the user has attached or pointed to a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section, compare sections, find where a topic is discussed, read a value or label off a figure or chart, pull tables out as…

emaballarin/ccplugins

Skill Claude CodeCodex

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

emaballarin/ccplugins

Plugin Claude Code

mindfunnel — project-agnostic Claude Code session management. Five slash-command skills: /mf:setup seeds /.mindfunnel/ (AGENTS, SOUL, USER, PROJECT templates) and the /.claude/ + /.codex/ symlinks to the user-global personal files; /mf:prime stamps a committed project-scoped AGENTS.md + intra-repo CLAUDE.md symlink.

emaballarin/ccplugins

Skill Claude CodeCodex

Reference for writing documents an agent reads — skills, AGENTS.md / CLAUDE.md, and the files they point at. Use when authoring or editing a SKILL.md, writing or pruning an AGENTS.md / CLAUDE.md, deciding whether a skill should be model- or user-invoked, choosing what to inline versus push behind a pointer, or…

emaballarin/ccplugins

Skill Claude CodeCodex

Consolidate the current session's progress into the project's auto-memory directory — the "log everything, update state, prepare for resumption" drill. Use when the user says "log everything", "checkpoint", "save progress", "update memory", "dump state", or autonomously when a long session is approaching context…

emaballarin/ccplugins

Skill Claude CodeCodex

Prime the current project for the mindfunnel workflow — stamp a project-scoped AGENTS.md from the bundled stub (if absent), create a project-local CLAUDE.md symlink to ./AGENTS.md, touch an empty PROJECT.md if absent, clean up legacy SOUL.md / CLAUDE.md / AGENTS.md symlinks left behind by pre-0.3.0 primings, and strip…