Agent skill

Cds Method Innovation

by haibarazz in haibarazz/awesome-codex-research

Guide a complete baseline-first ML or computational data-science method-innovation project, from workspace and direction discovery through finding and running common and recent baselines, diagnosing…

No licenceAuto-check passedResearch & Science

Install Cds Method Innovation

skills CLI
$ npx skills add haibarazz/awesome-codex-research --skill cds-method-innovation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install haibarazz/awesome-codex-research cds-method-innovation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/haibarazz/awesome-codex-research.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cds-method-innovation .claude/skills/cds-method-innovation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cds-method-innovation
GitHub stars
100
Token cost
~715 tokens
SKILL.md length
94 words
Files
21 (incl. scripts, references, assets)
Skills in repo
9
Repo updated
First seen
Licence
None found

At a glance

Guide a complete baseline-first ML or computational data-science method-innovation project, from workspace and direction discovery through finding and running common and recent baselines, diagnosing…

  • This integrated workflow
  • SKILL.md covers 开始与接续, 按研究进展选择阶段, 贯穿全程的约束 and 每次收口, plus 1 more section
  • Resume one of its stages

What it does

Cds Method Innovation is an agent skill from haibarazz/awesome-codex-research. Guide a complete baseline-first ML or computational data-science method-innovation project, from workspace and direction discovery through finding and running common and recent baselines, diagnosing failures, interrogating candidate novelty, designing and executing experiments, and preserving research history. Use for this integrated workflow or to resume one of its stages. Does not include full literature review, manuscript writing, or unattended autoresearch.

Its SKILL.md is about 720 tokens, which your agent loads only when the skill is triggered. The skill folder holds 23 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/experiment-design-brief-template.md` and `assets/paper-entry-template.md`).

It sits in Research & Science, covering Autonomous loops and Literature review.

When your agent uses it

  • This integrated workflow
  • Resume one of its stages

Example prompts

  • “/cds-method-innovation”

What it can do on your machine

Read from SKILL.md and the folder at commit e3ca125. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cds Method Innovation loads about 715 tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 122 tokens; SKILL.md has 94 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~122
When it runs · the whole SKILL.md, loaded when a task matches
~715
With references · SKILL.md plus every file in references/, read only if the agent opens them
~14k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 94 words (~715 tokens).

“一个独立 Skill 完成这条研究工作流。相关指引、初始化、方向日志和实验日志都在本包内;无需安装其他研究 Skill。baseline 指作为比较起点的现有方法,benchmark 指本项目约定的数据、指标和评价协议。”

— opening of SKILL.md by haibarazz
name
cds-method-innovation

Read the full SKILL.md on GitHub

Files

SKILL.md and 20 other files (scripts, references, assets) in skills/cds-method-innovation of haibarazz/awesome-codex-research.

  • SKILL.md
  • agents/openai.yaml
  • assets/experiment-design-brief-template.md
  • assets/paper-entry-template.md
  • assets/project-template.md
  • assets/run-template.md
  • references/baseline-benchmark.md
  • references/benchmark-protocol.md
  • references/benchmark-records.md
  • references/direction-discovery.md
  • references/execution-and-feedback.md
  • references/experiment-design.md
  • references/innovation-grill.md
  • references/innovation-review.md
  • references/project-init.md
  • references/research-records.md
  • references/sources.md
  • scripts
  • … and 3 more

Open the folder on GitHubat commit e3ca125

Compare with similar skills

Cds Method Innovation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cds Method Innovation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cds Method Innovation this skillhaibarazz/awesome-codex-research100—~715Automated safety check: PassNone
Deli Autoresearchrongxinzy/RongxinAI154—~3.2kAutomated safety check: PassAGPL-3.0
Nature Paper CardYuan1z0825/nature-skills47k2 repos~2.1kAutomated safety check: PassApache-2.0
Systematic Review ScreenerImbad0202/academic-research-skills51k—~8.4kAutomated safety check: PassCustom licence
Literature Reviewneflibata-feng/MyArxiv-Agent12620 repos~5.9kAutomated safety check: NotesMIT
Preprint Search on bioRxivLigphiDonk/Oh-my--paper73812 repos~3.7kAutomated safety check: PassMIT

Similar skills

  • Deli Autoresearch

    rongxinzy/RongxinAI

    A protocol framework for long-horizon autonomous research tasks.

    154 GitHub stars~3.2k tokensUpdated today
    Research & ScienceAuto-check passed
  • Nature Paper Card

    Yuan1z0825/nature-skills

    Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.

    47k GitHub starsUsed in 2 repos~2.1k tokens
    Research & ScienceAuto-check passed
  • Systematic Review Screener

    Imbad0202/academic-research-skills

    Screens records for systematic, scoping and rapid reviews against fixed eligibility rules, using two blinded AI reviewers and a third adjudicator, with traceable PRISMA counts.

    51k GitHub stars~8.4k tokensUpdated today
    Research & ScienceAuto-check passed
  • Literature Review

    neflibata-feng/MyArxiv-Agent

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).

    126 GitHub starsUsed in 20 repos~5.9k tokens
    Research & ScienceAuto-check: notes
  • Preprint Search on bioRxiv

    LigphiDonk/Oh-my--paper

    Searches bioRxiv life sciences preprints by keyword, author, date range or category with a Python script, returning JSON metadata and optional PDF downloads.

    738 GitHub starsUsed in 12 repos~3.7k tokens
    Research & ScienceAuto-check passed
  • Academic Paper Writing Pipeline

    Imbad0202/academic-research-skills

    Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.

    51k GitHub stars~16k tokensUpdated today
    Research & ScienceAuto-check passed

More from haibarazz/awesome-codex-research

All 9 skills in this repo
  • Autoresearch

    haibarazz/awesome-codex-research

    Run rigorous end-to-end autonomous ML and AI research after a user provides a dataset, target, and research budget.

    100 GitHub stars~2.2k tokensUpdated 16 days ago
    Auto-check passed
  • Autodl Remote

    haibarazz/awesome-codex-research

    A skill your agent uses when the host coding agent should control an AutoDL or SSH server from the local machine, run remote commands, and explicitly upload or download selected files.

    100 GitHub stars~2.7k tokensUpdated 16 days ago
    Auto-check passed
  • Autodl Remote Tmux

    haibarazz/awesome-codex-research

    A skill your agent uses when AutoDL Remote should run or monitor long remote jobs through tmux panes.

    100 GitHub stars~666 tokensUpdated 16 days ago
    Auto-check passed
  • Auto Exp

    haibarazz/awesome-codex-research

    Plan, execute, monitor, verify, compare, and document reproducible machine-learning experiments.

    100 GitHub stars~1.4k tokensUpdated 16 days ago
    Auto-check passed
  • Research Literature Review

    haibarazz/awesome-codex-research

    面向信息系统计算设计科学(CDS)研究,根据用户的数据、研究情境与研究问题,分别识别问题/理论视角和技术/算法两条文献对话线,检索并核验全文,制作可追溯的文献对话地图,最终澄清研究的最近邻、理论祖先、方法缺口与可辩护定位。适用于选题定位、相关工作规划、方法定位和后续综述;核心不是代写文献综述。

    100 GitHub stars~558 tokensUpdated 16 days ago
    Auto-check passed
  • Review Comment Decomposer

    haibarazz/awesome-codex-research

    结合论文原文拆解审稿意见为最小可回应原子问题,规划补实验与回复构思两条工作线,归组共同关切,并输出带忠实中文翻译注释、每条 comment 一份建议逻辑和原子点英文小标题的可编译 LaTeX 回复骨架。用于返修规划、review decomposition、atomic concerns、rebuttal strategy 和回复信模板生成;完整回复正文留待作者后续撰写。

    100 GitHub stars~1.1k tokensUpdated 16 days ago
    Auto-check: warnings

Questions about Cds Method Innovation

What does Cds Method Innovation do?

Guide a complete baseline-first ML or computational data-science method-innovation project, from workspace and direction discovery through finding and running common and recent baselines, diagnosing…. Cds Method Innovation is an agent skill from haibarazz/awesome-codex-research. Guide a complete baseline-first ML or computational data-science method-innovation project, from workspace and direction discovery through finding and running common and recent baselines, diagnosing failures, interrogating candidate novelty, designing and executing experiments, and preserving research history.

When should I use Cds Method Innovation?

Cds Method Innovation fits situations like: this integrated workflow; resume one of its stages.

How do I install Cds Method Innovation in Claude Code?

Run `npx skills add haibarazz/awesome-codex-research --skill cds-method-innovation -a claude-code`. Or copy the skill folder (skills/cds-method-innovation in haibarazz/awesome-codex-research) into .claude/skills/cds-method-innovation in your project. Claude Code loads it when a task matches its description.

How do I install Cds Method Innovation in Codex?

Run `npx skills add haibarazz/awesome-codex-research --skill cds-method-innovation -a codex`. Or copy the skill folder (skills/cds-method-innovation in haibarazz/awesome-codex-research) into .agents/skills/cds-method-innovation in your project. Codex loads it when a task matches its description.

Can I use Cds Method Innovation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add haibarazz/awesome-codex-research --skill cds-method-innovation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cds-method-innovation, .gemini/skills/cds-method-innovation, .github/skills/cds-method-innovation and .opencode/skills/cds-method-innovation in your project.

What does Cds Method Innovation need to run?

SKILL.md names no scripts, command-line tools or credentials: Cds Method Innovation is instructions for the agent only.

Does Cds Method Innovation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cds Method Innovation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Cds Method Innovation use?

No licence was found for Cds Method Innovation or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Cds Method Innovation use?

About 715 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 13k tokens, read only when the agent opens those files.

What are the alternatives to Cds Method Innovation?

Skills that share tags, products or a category with Cds Method Innovation: Deli Autoresearch (rongxinzy/RongxinAI, 154 stars), Nature Paper Card (Yuan1z0825/nature-skills, 47k stars), Systematic Review Screener (Imbad0202/academic-research-skills, 51k stars) and Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cds Method Innovation?

haibarazz (a GitHub user) maintains it in haibarazz/awesome-codex-research, which has 100 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 23, 2026.

Source: haibarazz/awesome-codex-research on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.