Agent skill

Ieee Summarize

by CloudWave818 in CloudWave818/ieee-skills

Summarize, organize, and normalize messy research materials into an IEEE-ready writing brief before manuscript drafting.

MITAuto-check passedResearch & Science

Install Ieee Summarize

skills CLI
$ npx skills add CloudWave818/ieee-skills --skill ieee-summarize -a claude-code

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

GitHub CLI
$ gh skill install CloudWave818/ieee-skills ieee-summarize --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/CloudWave818/ieee-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ieee-summarize .claude/skills/ieee-summarize && 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
ieee-summarize
GitHub stars
355
Token cost
~924 tokens
SKILL.md length
322 words
Files
6 (incl. scripts, references)
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Summarize, organize, and normalize messy research materials into an IEEE-ready writing brief before manuscript drafting.

  • Works in 9 steps: Read manifest.yaml. → Read every file listed under always_load. → Detect the request axes → …
  • Codex needs to process a folder
  • SKILL.md covers Routing Protocol, Output Contract and Red Lines
  • Runs Python scripts from its folder; calls rg

What it does

Ieee Summarize is an agent skill from CloudWave818/ieee-skills. Summarize, organize, and normalize messy research materials into an IEEE-ready writing brief before manuscript drafting. Use when Codex needs to process a folder or collection of experiment logs, code files, AI chat exports, idea notes, literature summaries, related-work notes, copied introduction excerpts, Zotero-derived paper summaries, tables, figures, or scattered Markdown/text records and convert them into structured inputs for ieee-writing, ieee-experiment, ieee-citation, ieee-reviewer, or ieee-response.

Its SKILL.md is about 920 tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `agents/openai.yaml`, `manifest.yaml` and `references/folder-ingestion.md`).

It sits in Research & Science, covering Citation management and Literature review. It works with Zotero. The repository describes itself as: 面向 IEEE 风格论文写作、润色、审稿、实验、图表、LaTeX、引用和论文阅读的 Codex skills。 The licence is MIT.

When your agent uses it

  • Codex needs to process a folder
  • Collection of experiment logs
  • AI chat exports
  • Literature summaries

Example prompts

  • “/ieee-summarize”

Requirements

  • Python 3

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. Read manifest.yaml.
  2. Read every file listed under always_load.
  3. Detect the request axes
  4. State the detected axes in one short line.
  5. If a folder path is provided, inventory first
  6. Map raw material into IEEE evidence slots
  7. Preserve provenance. Every important extracted point should include a file path, heading, filename, or note source when available.
  8. Mark solid, partial, unclear, or missing for each evidence block.
  9. Hand off to the next skill explicitly: ieee-writing, ieee-experiment, ieee-citation, ieee-reviewer, or ieee-polishing.

What it can do on your machine

Read from SKILL.md and the folder at commit ee30fda. 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/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • rg

    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

Ieee Summarize loads about 924 tokens when it runs, and up to ~1.9k if it reads all its reference files. Until then it costs about 133 tokens; SKILL.md has 322 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~133
When it runs · the whole SKILL.md, loaded when a task matches
~924
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.9k

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

The full file from CloudWave818/ieee-skills at commit ee30fda, republished under its MIT licence (© CloudWave818). 322 words, ~924 tokens.

Download SKILL.mdSave it as .claude/skills/ieee-summarize/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
ieee-summarize
description
Summarize, organize, and normalize messy research materials into an IEEE-ready writing brief before manuscript drafting. Use when Codex needs to process a folder or collection of experiment logs, code files, AI chat exports, idea notes, literature summaries, related-work notes, copied introduction excerpts, Zotero-derived paper summaries, tables, figures, or scattered Markdown/text records and convert them into structured inputs for ieee-writing, ieee-experiment, ieee-citation, ieee-reviewer, or ieee-response.

IEEE Summarize Router

Use this skill before ieee-writing when the user's research materials are scattered, chronological, duplicated, or not yet in manuscript structure. The output is not final prose; it is an evidence-grounded research brief that later writing skills can use.

Do not turn messy notes into polished claims by guessing. Preserve uncertainty, source paths, missing evidence, and contradictions.

Routing Protocol

  1. Read manifest.yaml.
  2. Read every file listed under always_load.
  3. Detect the request axes:
    • material_scope: folder / pasted-notes / code-and-logs / literature-pack / mixed.
    • output_target: research-brief / writing-input / experiment-summary / related-work-seed / claim-evidence-seed.
    • cleanup_level: inventory / standard / deep.
  4. State the detected axes in one short line.
  5. If a folder path is provided, inventory first:
    • Prefer scripts/inventory_research_folder.py <folder>.
    • If the script is unsuitable, use rg --files <folder>.
    • Do not read every large file blindly. Select representative and high-signal files by category.
  6. Map raw material into IEEE evidence slots:
    • problem object and operating condition,
    • engineering harm or practical motivation,
    • method idea and implementation clues from notes/code,
    • datasets, baselines, metrics, ablations, robustness, complexity, and reproducibility,
    • related-work families and closest-prior-work candidates,
    • contribution candidates and conclusion candidates.
  7. Preserve provenance. Every important extracted point should include a file path, heading, filename, or note source when available.
  8. Mark solid, partial, unclear, or missing for each evidence block.
  9. Hand off to the next skill explicitly: ieee-writing, ieee-experiment, ieee-citation, ieee-reviewer, or ieee-polishing.

Output Contract

Default output:

text
Detected axes: material_scope=..., output_target=..., cleanup_level=...

Material inventory
- Notes:
- Code:
- Experiments:
- Literature:
- Figures/tables:
- Unknown / skipped:

IEEE Research Brief
- Working title:
- Research object:
- Operating condition / constraints:
- Engineering harm:
- Core method:
- Implementation clues:
- Experiment evidence:
- Related-work seed:
- Contribution candidates:
- Conclusion candidates:
- Missing evidence:
- Contradictions / risks:

Next skill handoff
- Recommended next skill:
- Prompt-ready brief:

For folder-level work, create or update a Markdown file only when the user asks for a file. Suggested filename: ieee-research-brief.md.

Red Lines

Do not invent paper titles, citations, datasets, numerical results, code behavior, reviewer comments, or experiment outcomes.

Do not treat AI chat exports as verified evidence. Label them as ideation unless confirmed by code, logs, data, or papers.

Do not summarize copied paper introductions into plagiarism-ready text. Extract reusable background logic, domain motivation, and citation roles instead.

Do not remove negative results or failed experiments; classify them as limitation, ablation clue, or future-work evidence.

© CloudWave818, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts, references) in skills/ieee-summarize of CloudWave818/ieee-skills.

  • SKILL.md
  • agents/openai.yaml
  • manifest.yaml
  • references/folder-ingestion.md
  • references/research-brief-template.md
  • scripts/inventory_research_folder.py

Open the folder on GitHubat commit ee30fda

Compare with similar skills

Ieee Summarize 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.

Ieee Summarize compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ieee Summarize this skillCloudWave818/ieee-skills355—~924Automated safety check: PassMIT
Systematic Review ScreenerImbad0202/academic-research-skills51k—~8.4kAutomated safety check: PassCustom licence
NSFC Literature Review WriterHuiyuLi-2000/Chinese-Grant-Writer-Skills4321 repos~1.4kAutomated safety check: NotesMIT
Social Science Paper Writingfakerqwq/social-science-paper-writing-skill375—~7kAutomated safety check: PassNone
Zotero Taxonomy Curatorganzoth/zotero-taxonomy-curator159—~2.3kAutomated safety check: PassMIT
Zotero Obsidian BridgeGalaxy-Dawn/claude-scholar5.7k—~514Automated safety check: PassMIT

Similar skills

  • 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 5 days ago
    Research & ScienceAuto-check passed
  • NSFC Literature Review Writer

    HuiyuLi-2000/Chinese-Grant-Writer-Skills

    Writes the research-status literature review and critique section of an NSFC grant proposal, backed by a bundled multi-source literature search.

    432 GitHub starsUsed in 1 repo~1.4k tokens
    Research & ScienceAuto-check: notes
  • Social Science Paper Writing

    fakerqwq/social-science-paper-writing-skill

    Helps draft, diagnose, review and revise social science papers, from topic and research question to literature review, citation risks and pre-submission checks.

    375 GitHub stars~7k tokensUpdated 4 mo ago
    Research & ScienceAuto-check passed
  • Zotero Taxonomy Curator

    ganzoth/zotero-taxonomy-curator

    Domain-configurable Zotero-to-Obsidian literature curation and paper close-reading skill.

    159 GitHub stars~2.3k tokensUpdated 5 mo ago
    Research & ScienceAuto-check passed
  • Zotero Obsidian Bridge

    Galaxy-Dawn/claude-scholar

    Moves papers from Zotero into an Obsidian project knowledge base as source notes, literature synthesis and writing outputs, with evidence records behind every promoted claim.

    5.7k GitHub stars~514 tokensUpdated 15 days ago
    Research & ScienceAuto-check passed
  • Scholar RAG

    joshzyj/open-scholar-skill

    Build and query a local vector database + GraphRAG over your entire reference library (Zotero or a PDF folder) for literature review.

    168 GitHub stars~7.4k tokensUpdated 20 days ago
    Research & ScienceAuto-check: notes

More from CloudWave818/ieee-skills

All 10 skills in this repo
  • Ieee Figure Table

    CloudWave818/ieee-skills

    Audit, redesign, generate, and improve IEEE manuscript figures, tables, captions, result presentation, plotting scripts, visual polish, hybrid Python/R plus vector-editor workflows…

    355 GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed
  • Ieee Citation

    CloudWave818/ieee-skills

    Check, clean, verify, and improve IEEE citations, references, BibTeX entries, citation positioning, related-work logic, DOI metadata, venue names, and reference formatting using routed citation and…

    355 GitHub stars~580 tokensUpdated 1 mo ago
    Auto-check passed
  • Ieee Experiment

    CloudWave818/ieee-skills

    Design, audit, and strengthen experimental validation for IEEE manuscripts using routed claim-evidence checks.

    355 GitHub stars~577 tokensUpdated 1 mo ago
    Auto-check passed
  • Ieee Latex

    CloudWave818/ieee-skills

    Diagnose, fix, and improve IEEEtran LaTeX manuscripts using routed template, layout, float, equation, algorithm, table, bibliography, and PDF-compliance guidance.

    355 GitHub stars~541 tokensUpdated 1 mo ago
    Auto-check passed
  • Ieee Paper Reader

    CloudWave818/ieee-skills

    Read, decompose, and analyze IEEE-style papers using routed technical-reading workflows.

    355 GitHub stars~591 tokensUpdated 1 mo ago
    Auto-check passed
  • Ieee Response

    CloudWave818/ieee-skills

    Draft, diagnose, and improve IEEE rebuttals, revision plans, cover letters, response letters, and point-by-point replies using routed reviewer-comment handling.

    355 GitHub stars~707 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Ieee Summarize

What does Ieee Summarize do?

Summarize, organize, and normalize messy research materials into an IEEE-ready writing brief before manuscript drafting. Ieee Summarize is an agent skill from CloudWave818/ieee-skills. Summarize, organize, and normalize messy research materials into an IEEE-ready writing brief before manuscript drafting.

When should I use Ieee Summarize?

Ieee Summarize fits situations like: Codex needs to process a folder; collection of experiment logs; AI chat exports; literature summaries.

How do I install Ieee Summarize in Claude Code?

Run `npx skills add CloudWave818/ieee-skills --skill ieee-summarize -a claude-code`. Or copy the skill folder (skills/ieee-summarize in CloudWave818/ieee-skills) into .claude/skills/ieee-summarize in your project. Claude Code loads it when a task matches its description.

How do I install Ieee Summarize in Codex?

Run `npx skills add CloudWave818/ieee-skills --skill ieee-summarize -a codex`. Or copy the skill folder (skills/ieee-summarize in CloudWave818/ieee-skills) into .agents/skills/ieee-summarize in your project. Codex loads it when a task matches its description.

Can I use Ieee Summarize 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 CloudWave818/ieee-skills --skill ieee-summarize -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ieee-summarize, .gemini/skills/ieee-summarize, .github/skills/ieee-summarize and .opencode/skills/ieee-summarize in your project.

What does Ieee Summarize need to run?

Going by SKILL.md and its folder, Ieee Summarize needs Python for the scripts in its folder and the command-line tools its instructions call (rg). Our summary lists: Python 3.

Does Ieee Summarize 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 Ieee Summarize 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 Ieee Summarize use?

Ieee Summarize is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ieee Summarize use?

About 924 tokens (SKILL.md is roughly 3.7k 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 1k tokens, read only when the agent opens those files.

What are the alternatives to Ieee Summarize?

Skills that share tags, products or a category with Ieee Summarize: Systematic Review Screener (Imbad0202/academic-research-skills, 51k stars), NSFC Literature Review Writer (HuiyuLi-2000/Chinese-Grant-Writer-Skills, 432 stars), Social Science Paper Writing (fakerqwq/social-science-paper-writing-skill, 375 stars) and Zotero Taxonomy Curator (ganzoth/zotero-taxonomy-curator, 159 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ieee Summarize?

CloudWave818 (a GitHub user) maintains it in CloudWave818/ieee-skills, which has 355 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on August 12, 2026.

Source: CloudWave818/ieee-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.