Agent skill

Skill Article

by aeonfun in aeonfun/aeon

Turn any skill in this instance into a publish-ready launch article - proof-stat headline, one contrarian thesis, mechanics, war stories from real run history, a mental-model reframe, and the full…

MITAuto-check passedEducation

Install Skill Article

skills CLI
$ npx skills add aeonfun/aeon --skill skill-article -a claude-code

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

GitHub CLI
$ gh skill install aeonfun/aeon skill-article --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/aeonfun/aeon.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-article .claude/skills/skill-article && 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
skill-article
GitHub stars
767
Token cost
~2k tokens
SKILL.md length
1,105 words
Files
1
Skills in repo
82
Repo updated
First seen
Licence
MIT

At a glance

Turn any skill in this instance into a publish-ready launch article - proof-stat headline, one contrarian thesis, mechanics, war stories from real run history, a mental-model reframe, and the full…

  • Works in 6 steps: Mine the track record (real numbers only) → Find the thesis → Collect war stories → …
  • Tasks that involve Essays and academic help
  • SKILL.md covers Shared preamble, Step 1 — Mine the track record…, Step 2 — Find the thesis and Step 3 — Collect war stories, plus 5 more sections
  • Calls gh and git

What it does

Skill Article is an agent skill from aeonfun/aeon. Turn any skill in this instance into a publish-ready launch article - proof-stat headline, one contrarian thesis, mechanics, war stories from real run history, a mental-model reframe, and the full SKILL.md embedded verbatim so readers can steal it. Optional Higgsfield title banner with --banner.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Education, covering Essays and academic help. The repository describes itself as: The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing skills, drives Claude Code, Grok, Codex & more. No approval loops. Configure once, forget… The licence is MIT.

When your agent uses it

  • Tasks that involve Essays and academic help

Example prompts

  • “/skill-article”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Mine the track record (real numbers only)
  2. Find the thesis
  3. Collect war stories
  4. Write the article
  5. Title banner (only with --banner)
  6. Deliver

What it can do on your machine

Read from SKILL.md and the folder at commit f252074. 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

    Shell commands in SKILL.md call:

    • gh
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.

    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

Skill Article loads about 2k tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 1,105 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from aeonfun/aeon at commit f252074, republished under its MIT licence (© aeonfun). 1,105 words, ~2,041 tokens.

Download SKILL.mdSave it as .claude/skills/skill-article/SKILL.md (or your agent's skills folder).
name
skill-article
description
Turn any skill in this instance into a publish-ready launch article - proof-stat headline, one contrarian thesis, mechanics, war stories from real run history, a mental-model reframe, and the full SKILL.md embedded verbatim so readers can steal it. Optional Higgsfield title banner with --banner.
metadata.title
Skill Article
metadata.category
basics
metadata.tags
content, meta

${var} — Selector: <skill-name> [--brand <handle>] [--banner].

  • <skill-name> → announce that skill (must exist under skills/<skill-name>/).
  • empty → pick the most article-worthy skill from the last 14 days of memory/logs/: prefer a skill that shipped recently, produced verified output, or hit a milestone. If nothing qualifies, log SKILL_ARTICLE_NO_TARGET, send no notification, and exit clean.
  • --brand <handle> anywhere → byline/handle for the outreach footer (default: this instance's public identity from soul/, else the repo's org).
  • --banner anywhere → also generate one 16:9 title banner through the Higgsfield MCP (spends credits; see Step 5). Off by default - a blank run never spends.

Examples: "aeon-update", "rug-scan --brand @myproject --banner".

Today is ${today}. Write a launch article for one skill, modeled on the security-industry "skill announcement" format: the article sells the insight the skill encodes, not the file - and then gives the file away.

Shared preamble

  1. Read memory/MEMORY.md and the last 14 days of memory/logs/ - know what this skill has actually done.
  2. If a soul/ directory exists, read soul/SOUL.md and soul/STYLE.md for voice. Default voice: terse, declarative, builder-wrote-this-fast.
  3. Read the target's full skills/<name>/SKILL.md. Every claim in the article must trace to a line in it.

Step 1 — Mine the track record (real numbers only)

Hunt for countable proof before writing a word:

  • memory/logs/ entries under the skill's ### <name> headings: runs, OK/error statuses, notable outcomes.
  • output/ files the skill produced; PRs or issues it opened (gh pr list --search).
  • git log -- skills/<name>/ for ship date and iteration history.

A real stat ("84 verified findings", "31 runs, 0 false alarms") becomes the headline. If no real count exists, the headline uses the mechanism instead. Never invent a number - a fabricated stat is the one thing that kills this format.

Step 2 — Find the thesis

Answer: what does this skill see that the default workflow throws away? That gap is the thesis.

Write 3 candidate contrast pairs (two-sided sentences like "production code shows what the system does; tests show what its developers thought it did") and keep the sharpest. Everything in the article hangs on this one insight.

Step 3 — Collect war stories

1-3 concrete moments where the skill caught or produced something a naive approach would miss - pulled from memory/logs/ and output/, anonymized where needed, mechanism kept visible.

If the skill has no run history yet, write "how it plays out" scenarios and label them as scenarios. Never dress a hypothetical as a case study.

Step 4 — Write the article

Structure, in order:

  1. Headline: <Skill Name>: <proof stat or mechanism claim>. Bold claim, not a setup.
  2. Provenance (2 short paragraphs): what it is, where it runs, ship date, track record if real.
  3. Thesis section with a punchy heading (a claim, never a label): what everyone else's workflow misses.
  4. Mechanics (2-4 short paragraphs) built around the contrast pair.
  5. War stories: one mini-heading per story, 2-4 sentences each, ending with the generalized pattern ("The same blind spot appears when...").
  6. Reframe section: the mental-model shift the reader keeps even if they never run the skill.
  7. Ship it: where it lives + one-line CTA (star the upstream repo).
  8. CODENAME: <Skill Name>: the target SKILL.md embedded verbatim in a fenced block (use a 4-backtick fence - skill files contain 3-backtick fences). Do not paraphrase or trim it.
  9. Outreach footer: 1-2 sentences, DMs-open style, pointing at the brand handle.

Voice rules (the anti-tells)

  • Short declarative sentences. Cut every sentence that only sets up the next one.
  • Banned: "revolutionary", "game-changing", "unleash", "delve", "Let's dive in".
  • No parallel-structure trios, no "not X, but Y" scaffolding.
  • Section headings are claims or scenes ("There is an alpha in the test folder"), never labels ("Overview").
  • Verify the repo/link in the CTA exists this run before naming it.
  • Never reference private forks or internal accounts - describe this instance generically and point at the upstream/public repo.
Show full SKILL.md (476 more words)Show less

Step 5 — Title banner (only with --banner)

Skip this step entirely unless --banner was passed. When it was:

  1. Check the connection first. If no mcp__higgsfield__* tool is callable, the banner is skipped, not the article: note banner: HIGGS_NOT_CONNECTED for the log, point the operator at the dashboard → MCP → Connect Higgsfield in the notify, and continue to Step 6. Same on 401/stale auth (banner: HIGGS_AUTH_STALE) or insufficient credits (banner: HIGGS_NO_CREDITS). The article never fails because the banner did.
  2. Build the prompt from the thesis, not the feature list. The banner is a visual metaphor for the Step 2 contrast pair - the scene that makes the insight visible. Image models garble long text, so the only text allowed in the prompt is the skill's short name (or none); the headline lives in the article, not the pixels. Match soul/ aesthetic if it defines one; otherwise: clean, high-contrast, one focal object, no collage.
  3. Generate exactly one image, --ar 16:9, following the higgsfield skill's spend rules: one generation per run, one retry at most on a transient error, never re-submit a job that already succeeded. Poll to completion with a bounded number of polls; on timeout record banner: HIGGS_FAILED and move on.
  4. Capture the asset URL verbatim. Never fabricate one. Banner asset URLs may be time-limited signed URLs - flag that in the notify so the operator saves it.

Embed the result at the top of the article file, next to the alts block:

markdown
<!-- banner: <asset-url> · model: <model> · job: <id> -->

Step 6 — Deliver

  1. Write the article to output/skill-articles/${today}-<skill-name>.md (shell redirection; mkdir -p first). Include an <!-- alts --> comment block at the top with 2 alternative headline + thesis-heading pairs so the operator can iterate without a rewrite.

  2. Notify with ./notify -f /tmp/skill-article-notify.md (write the body under /tmp/): the headline, the thesis in one line, whether the stats are real or the headline fell back to mechanism, the banner URL when one was generated (with a save-it note if the URL is signed/expiring), and a clickable link built from the run's environment:

    bash
    ARTICLE_URL="${GITHUB_SERVER_URL:-https://github.com}/${GITHUB_REPOSITORY}/blob/main/output/skill-articles/<file>.md"
  3. Log to memory/logs/${today}.md under a ### skill-article heading: target skill, headline, thesis pair, stats-real-or-mechanism, output path, and - when --banner was passed - a banner: line (HIGGS_OK <url> | HIGGS_NOT_CONNECTED | HIGGS_AUTH_STALE | HIGGS_NO_CREDITS | HIGGS_FAILED | skipped). Status codes: SKILL_ARTICLE_OK on success, SKILL_ARTICLE_NO_TARGET when ${var} was empty and nothing article-worthy exists, SKILL_ARTICLE_NOT_FOUND when the named skill has no SKILL.md.

Limits

  • This writes the article; it does not post it. Publishing is the operator's call (or a posting skill's, explicitly chained).
  • The banner is opt-in and spends real Higgsfield credits - one image per run, hard cap, and its failure never blocks the article.
  • Track-record mining is only as good as memory/logs/ - a skill that runs but never logs will read as unproven, and the article will say so rather than guess.
  • One skill per run. Announcing a pack is a different article; run once per skill instead.

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

Files

Just SKILL.md in skills/skill-article of aeonfun/aeon.

Open the folder on GitHubat commit f252074

Compare with similar skills

Skill Article 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.

Skill Article compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Article this skillaeonfun/aeon767—~2kAutomated safety check: PassMIT
Academic Paper StrategistAAASS554/codex-academic-paper-skills5391 repos~2.7kAutomated safety check: PassMIT
Modeling Paper Rubric and Model Selectoryushui2022/MathModel-Skill4521 repos~1.8kAutomated safety check: PassMIT
Humanities Thesisganzhi-black/humanities-thesis-skill627—~1.7kAutomated safety check: PassMIT
Skill Thesis Writeryanlin-cheng/skill-thesis-writer207—~1.6kAutomated safety check: PassCustom licence
Thesis CreatorStars-OC/thesis-creator227—~2.8kAutomated safety check: PassMIT

Similar skills

  • Academic Paper Strategist

    AAASS554/codex-academic-paper-skills

    A skill your agent uses when the user needs to plan, de-risk, or ground a software engineering / computer science undergraduate thesis from a real codebase before final writing.

    539 GitHub starsUsed in 1 repo~2.7k tokens
    EducationAuto-check passed
  • Builds a scoring-aligned outline for a mathematical modeling paper and a model selection plan with baseline, improvement and validation experiments.

    452 GitHub starsUsed in 1 repo~1.8k tokens
    EducationAuto-check passed
  • Humanities Thesis

    ganzhi-black/humanities-thesis-skill

    人文社科论文写作全流程指导。适用于文学、历史、哲学、社会学、传播学、新闻学、文化研究等领域的中文学术论文。当用户提到"论文""写论文""选题""文献综述""论文修改""论文结构""摘要翻译""帮我查文献""参考文献格式""论文没有新意""理论和文本脱节""章节之间缺乏逻辑""帮我检查论文""摘要翻译成英文""投稿准备""脚注格式"等场景时触发。覆盖从选题到投稿的全流程,包含防幻觉规则、学术数据库…

    627 GitHub stars~1.7k tokensUpdated 5 mo ago
    EducationAuto-check passed
  • Skill Thesis Writer

    yanlin-cheng/skill-thesis-writer

    跨学科AI论文写作助手,专为本科生/研究生论文写作提供全方位支持。当用户需要撰写论文内容、设计论文框架结构、优化学术语体风格、处理参考文献格式(GB/T 7714-2015)、生成统计分析表格、或降低AI生成文本痕迹时使用此技能。支持工科(计算机/电子/机械等)、心理学、教育学、管理学等多学科领域,符合中国学术论文写作规范。

    207 GitHub stars~1.6k tokensUpdated 5 mo ago
    EducationAuto-check passed
  • Thesis Creator

    Stars-OC/thesis-creator

    Walks Chinese undergraduates through writing a graduation thesis from topic to Word export, with text-similarity reduction and AI-text rate rewriting and checks.

    227 GitHub stars~2.8k tokensUpdated 4 mo ago
    EducationAuto-check passed
  • Aigc Detector

    free-revalution/AIGC-Detector-Pro

    Academic paper AI content detection, rewriting, and thesis writing assistant.

    141 GitHub stars~2.8k tokensUpdated 4 mo ago
    EducationAuto-check passed

More from aeonfun/aeon

All 82 skills in this repo
  • Browses open tasks on the TaskMarket agent-worker market and, with explicit operator approval, creates tasks, tracks submissions and submits finished work.

    767 GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Sets up and manages an Aeon agent instance that runs skills on a schedule through GitHub Actions: starting, rescheduling, debugging, editing skills and mining chat history.

    767 GitHub stars~8.8k tokensUpdated today
    Auto-check: warnings
  • Reads a Base Account's address, portfolio and transaction history through the Base MCP server, and stays strictly read-only in unattended Aeon runs, reporting only changes.

    767 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Audits every page of a site each day from its sitemap, scores on-page and technical SEO, checks duplicates across pages and reports what changed since the last run.

    767 GitHub stars~5.1k tokensUpdated today
    Auto-check passed
  • Action Converter

    aeonfun/aeon

    5 concrete real-life actions, leverage-scored against open loops with specificity and anti-fluff gates

    767 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Aeon Config Doctor

    aeonfun/aeon

    Static linter for an Aeon instance's configuration that catches silent failures such as unquoted schedules, duplicate keys, unconfigured skills and broken MCP references.

    767 GitHub stars~3.3k tokensUpdated today
    Auto-check passed

Categories

Questions about Skill Article

What does Skill Article do?

Turn any skill in this instance into a publish-ready launch article - proof-stat headline, one contrarian thesis, mechanics, war stories from real run history, a mental-model reframe, and the full…. Skill Article is an agent skill from aeonfun/aeon.md embedded verbatim so readers can steal it.

When should I use Skill Article?

Skill Article fits situations like: tasks that involve Essays and academic help.

How do I install Skill Article in Claude Code?

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

How do I install Skill Article in Codex?

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

Can I use Skill Article 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 aeonfun/aeon --skill skill-article -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-article, .gemini/skills/skill-article, .github/skills/skill-article and .opencode/skills/skill-article in your project.

What does Skill Article need to run?

Going by SKILL.md and its folder, Skill Article needs the command-line tools its instructions call (gh and git).

Does Skill Article access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Skill Article 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. Review the folder before installing.

What licence does Skill Article use?

Skill Article 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 Skill Article use?

About 2k tokens (SKILL.md is roughly 8.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Skill Article?

Skills that share tags, products or a category with Skill Article: Academic Paper Strategist (AAASS554/codex-academic-paper-skills, 539 stars), Modeling Paper Rubric and Model Selector (yushui2022/MathModel-Skill, 452 stars), Humanities Thesis (ganzhi-black/humanities-thesis-skill, 627 stars) and Skill Thesis Writer (yanlin-cheng/skill-thesis-writer, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Article?

aeonfun (a GitHub organization) maintains it in aeonfun/aeon, which has 767 GitHub stars. The repository holds 82 skills in this directory. The repository was last updated on October 6, 2026.

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