Agent skill

Wiki Summary

by mohitagw15856 in mohitagw15856/pm-claude-skills

Fetch Wikipedia's current summary of any topic with zero API keys — the REST summary endpoint via curl, for answers that need today's article rather than training-data memory.

MITAuto-check passed

Install Wiki Summary

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill wiki-summary -a claude-code

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

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills wiki-summary --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/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/wiki-summary .claude/skills/wiki-summary && 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
wiki-summary
GitHub stars
1.4k
Token cost
~1.1k tokens
SKILL.md length
552 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Fetch Wikipedia's current summary of any topic with zero API keys — the REST summary endpoint via curl, for answers that need today's article rather than training-data memory.

  • Works in 5 steps: The call: curl -s… → Search first when the title is… → Attribution is the product: the extract… → …
  • Asked what does Wikipedia say about X
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: The Endpoint and… and Output Format, plus 3 more sections
  • Calls curl; reaches en.wikipedia.org

What it does

Wiki Summary is an agent skill from mohitagw15856/pm-claude-skills. Fetch Wikipedia's current summary of any topic with zero API keys — the REST summary endpoint via curl, for answers that need today's article rather than training-data memory. Use when asked what does Wikipedia say about X, get me the current summary of a topic, check a fact against Wikipedia, or has this article changed. Produces the live extract with the article link, disambiguation handling, and a clean separation between what Wikipedia says and what the model adds.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with Wikipedia. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked what does Wikipedia say about X
  • Get me the current summary of a topic
  • Check a fact against Wikipedia
  • Has this article changed

Example prompts

  • “/wiki-summary”

Workflow steps

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

  1. The call: curl -s "https://en.wikipedia.org/api/rest_v1/page/summary/Alan_Turing" → JSON: title, description, extract (the summary text)…
  2. Search first when the title is uncertain: curl -s "https://en.wikipedia.org/w/rest.php/v1/search/title?q=turing&limit=5" → candidate…
  3. Attribution is the product: the extract is quoted or clearly framed as "Wikipedia currently says…" with the link. Model elaboration goes…
  4. Freshness honesty both directions: fetched beats recalled for living facts — but Wikipedia itself lags and errs; for high-stakes facts the…
  5. The changed-since-training move: when the fetched extract contradicts what the model would have said, say so explicitly — "training-era…

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. 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:

    • curl

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • en.wikipedia.org

    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

Wiki Summary loads about 1.1k tokens when it runs. Until then it costs about 122 tokens; SKILL.md has 552 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
~1.1k

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 mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 552 words, ~1,129 tokens.

Download SKILL.mdSave it as .claude/skills/wiki-summary/SKILL.md (or your agent's skills folder).
name
wiki-summary
description
Fetch Wikipedia's current summary of any topic with zero API keys — the REST summary endpoint via curl, for answers that need today's article rather than training-data memory. Use when asked what does Wikipedia say about X, get me the current summary of a topic, check a fact against Wikipedia, or has this article changed. Produces the live extract with the article link, disambiguation handling, and a clean separation between what Wikipedia says and what the model adds.

Wiki Summary Skill

The model already knows what Wikipedia said at training time; this skill fetches what it says now — which matters for anything living: people's roles, company facts, ongoing events, populations, "current CEO" questions. Wikipedia's REST API serves a clean summary per article over keyless HTTPS. The skill's discipline is attribution: the fetched extract is Wikipedia's voice, dated today; anything the model adds around it gets labeled as such.

What This Skill Produces

  • The live extract — Wikipedia's current summary paragraph(s) for the topic, quoted as the source
  • The link and metadata — canonical URL, and the description line ("American computer scientist")
  • Disambiguation handling — when the title is ambiguous, the options, not a guess
  • The command — exact curl, rerunnable

Required Inputs

Ask for these if not provided:

  • The topic — resolved to an article title (spaces → underscores); ambiguous names get the disambiguation treatment, not a silent pick
  • Language edition — en default; the endpoint pattern works on any edition (de.wikipedia.org, ja.wikipedia.org) and the user's question may belong in one
  • Why they're asking — a fact-check wants the specific claim compared; a primer wants the extract; "has this changed" wants fetched-vs-recalled differences called out

Framework: The Endpoint and the Attribution Rules

  1. The call: curl -s "https://en.wikipedia.org/api/rest_v1/page/summary/Alan_Turing" → JSON: title, description, extract (the summary text), content_urls.desktop.page (canonical link), type. URL-encode the title; spaces become underscores.
  2. Search first when the title is uncertain: curl -s "https://en.wikipedia.org/w/rest.php/v1/search/title?q=turing&limit=5" → candidate titles. A type: "disambiguation" response means list the options and ask — a confident summary of the wrong John Smith is worse than a question.
  3. Attribution is the product: the extract is quoted or clearly framed as "Wikipedia currently says…" with the link. Model elaboration goes outside that frame, labeled. A fact-check answer states: the claim, what the live article says, and whether they match.
  4. Freshness honesty both directions: fetched beats recalled for living facts — but Wikipedia itself lags and errs; for high-stakes facts the answer notes it's one (good) source, and breaking-news topics may be mid-edit.
  5. The changed-since-training move: when the fetched extract contradicts what the model would have said, say so explicitly — "training-era memory said X; the live article now says Y" — that delta is often exactly what the user was probing for.
Show full SKILL.md (184 more words)Show less

Output Format

[Article title] — [description line]

[The live extract, as Wikipedia's voice]

[Fact-check mode: the claim vs. the extract, verdict stated] [Model additions, if any, under a labeled line]

Source: [canonical article URL] · fetched [date] · rerun: [exact curl] [Disambiguation case: the candidate list and the ask]

Quality Checks

  • The extract is attributed to Wikipedia and dated — never blended into model voice
  • Ambiguous titles produced options, not a guess
  • Fact-checks compare the specific claim to the specific sentence
  • Training-memory vs. live-article deltas are called out when found
  • The canonical URL appears

Anti-Patterns

  • Do not paraphrase the live extract into model voice — the fetch's value is the attribution
  • Do not silently pick among namesakes — disambiguate out loud
  • Do not treat Wikipedia as final authority for high-stakes facts — one good source, framed as such
  • Do not answer "what does Wikipedia say" from memory — that question is a fetch instruction by definition
  • Do not skip the URL — the link is the receipt

Example Trigger Phrases

  • "What does Wikipedia say about X?"
  • "Get me the current summary of a topic."
  • "Check a fact against Wikipedia."
  • "Has this article changed."

© mohitagw15856, 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/wiki-summary of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Wiki Summary 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.

Wiki Summary compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wiki Summary this skillmohitagw15856/pm-claude-skills1.4k—~1.1kAutomated safety check: PassMIT
HumanizerAzure-Samples/interview-coach-agent-framework17338 repos~5.8kAutomated safety check: PassMIT
AI Copywritermikiarlo3/ai-copywriter1.2k—~12kAutomated safety check: PassMIT
Renwei Writingorange2ai/renwei-writing1.1k—~684Automated safety check: PassProprietary
World Cup Predictormikobinbin/2026-world-cup-predictor657—~1.7kAutomated safety check: NotesNone
Humanizer Zh Academicredbaronyyyyy-eng/humanizer-zh-academic3081 repos~1.8kAutomated safety check: PassMIT

Similar skills

  • Humanizer

    Azure-Samples/interview-coach-agent-framework

    Official

    Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.

    173 GitHub starsUsed in 38 repos~5.8k tokens
    Writing & ContentAuto-check passed
  • AI Copywriter

    mikiarlo3/ai-copywriter

    Write copy that converts and doesn't sound like a robot. An agent skill from mikiarlo3/ai-copywriter.

    1.2k GitHub stars~12k tokensUpdated 2 mo ago
    Writing & ContentAuto-check passed
  • Renwei Writing

    orange2ai/renwei-writing

    人味儿写作 - 打磨、润色、改写别人的文字时,保住文字背后那个人的存在感. An agent skill from orange2ai/renwei-writing.

    1.1k GitHub stars~684 tokensUpdated 3 mo ago
    Writing & ContentAuto-check passed
  • World Cup Predictor

    mikobinbin/2026-world-cup-predictor

    世界杯冠军预测系统 — 基于球员成长周期模型、球队Elo评分、玄学因子的综合预测框架。预测2026年美加墨世界杯冠军,同时输出球队排行榜、球员系数矩阵、可视化看板。

    657 GitHub stars~1.7k tokensUpdated 2 mo ago
    Auto-check: notes
  • Humanizer Zh Academic

    redbaronyyyyy-eng/humanizer-zh-academic

    降低中文学术写作(论文、期刊文章、毕业论文等)AIGC检测率的专项 skill. An agent skill from redbaronyyyyy-eng/humanizer-zh-academic.

    308 GitHub starsUsed in 1 repo~1.8k tokens
    Writing & ContentAuto-check passed
  • Rival Search MCP

    damionrashford/RivalSearchMCP

    Deterministic deep research via RivalSearchMCP. An agent skill from damionrashford/RivalSearchMCP.

    132 GitHub stars~796 tokensUpdated today
    Research & ScienceAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Wiki Summary

What does Wiki Summary do?

Fetch Wikipedia's current summary of any topic with zero API keys — the REST summary endpoint via curl, for answers that need today's article rather than training-data memory. Wiki Summary is an agent skill from mohitagw15856/pm-claude-skills. Fetch Wikipedia's current summary of any topic with zero API keys — the REST summary endpoint via curl, for answers that need today's article rather than training-data memory.

When should I use Wiki Summary?

Wiki Summary fits situations like: asked what does Wikipedia say about X; get me the current summary of a topic; check a fact against Wikipedia; has this article changed.

How do I install Wiki Summary in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill wiki-summary -a claude-code`. Or copy the skill folder (skills/wiki-summary in mohitagw15856/pm-claude-skills) into .claude/skills/wiki-summary in your project. Claude Code loads it when a task matches its description.

How do I install Wiki Summary in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill wiki-summary -a codex`. Or copy the skill folder (skills/wiki-summary in mohitagw15856/pm-claude-skills) into .agents/skills/wiki-summary in your project. Codex loads it when a task matches its description.

Can I use Wiki Summary 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 mohitagw15856/pm-claude-skills --skill wiki-summary -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wiki-summary, .gemini/skills/wiki-summary, .github/skills/wiki-summary and .opencode/skills/wiki-summary in your project.

What does Wiki Summary need to run?

Going by SKILL.md and its folder, Wiki Summary needs the command-line tools its instructions call (curl).

Does Wiki Summary access the network?

SKILL.md names 1 domain. In commands or code: en.wikipedia.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Wiki Summary 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 Wiki Summary use?

Wiki Summary 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 Wiki Summary use?

About 1.1k tokens (SKILL.md is roughly 4.5k 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 Wiki Summary?

Skills that share tags, products or a category with Wiki Summary: Humanizer (Azure-Samples/interview-coach-agent-framework, 173 stars), AI Copywriter (mikiarlo3/ai-copywriter, 1.2k stars), Renwei Writing (orange2ai/renwei-writing, 1.1k stars) and World Cup Predictor (mikobinbin/2026-world-cup-predictor, 657 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Wiki Summary?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.