# mikubaka88/CCFA-Skills

A skill family for shaping the research storyline of CCF-A papers.

Repository: https://github.com/mikubaka88/CCFA-Skills
Canonical: https://ross.abutalabs.com/products/ccfa-skills
Language: TeX
License: MIT
License Family: permissive
Last push: 2026-08-13T01:53:09+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 97, longevity 6
- inputs: {"age_days": 90, "days_push": 21, "days_rel": 21, "gap_med": 2, "n_releases_24m": 8}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1865, forks 84 (observed 2026-08-28T04:05:45.484545+00:00)

## What it is
A family of 17 agent skills for shaping the research storyline of CCF-A academic papers, covering ideation, literature retrieval, experiment design, writing, figure creation, review simulation, rebuttal, and submission. It installs into AI coding agents like Claude Code, Codex, Cursor, and Gemini CLI.

## Use cases
- write and revise a CCF-A conference paper with AI assistance
- critically review and rank research topic ideas before committing
- retrieve recent related work, benchmarks, and baselines for a research area
- design main experiments, ablations, and robustness evidence for a paper
- rewrite a methods section in CVPR style while preserving formulas and citations
- generate and refine method architecture figures as SVG, PDF, or PPTX
- simulate peer review and prepare rebuttals for submitted papers

## When to choose
- you are an academic researcher targeting top-tier (CCF-A) venues and use an AI coding agent
- you want specialized skills for each paper stage instead of one long generic prompt
- you need evidence-grounded literature retrieval, experiment protocols, and reviewer-style feedback

## When to avoid
- you need general-purpose writing help outside academic research
- you don't use an agent platform like Claude Code, Codex, or Cursor
- you expect a standalone GUI application rather than agent skills

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, prompt-engineering, documentation, llm-inference, search-engine, data-visualization
- domain: artificial-intelligence, large-language-models, documentation, education, developer-tools
- platform: cli, cross-platform, python
- tags: academic-writing, paper-writing, research-workflow, agent-skills, latex, peer-review, rebuttal, scientific-figures, claude-code, codex, cursor, ai-agents

## Member repositories
- mikubaka88/CCFA-Skills (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:45.484545+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:15:35.140029+00:00, confidence not recorded.
  - readme: https://github.com/mikubaka88/CCFA-Skills (fetched 2026-08-28T04:05:45.484545+00:00, sha d93ac1c573c4)
- Data as of 2026-08-30T08:39:29.467469+00:00.