Agent skill

Story Origin Check

by elvisun in elvisun/newsjack

Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.

MITAuto-check passed

Install Story Origin Check

skills CLI
$ npx skills add elvisun/newsjack --skill story-origin-check -a claude-code

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

GitHub CLI
$ gh skill install elvisun/newsjack story-origin-check --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/elvisun/newsjack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/story-origin-check .claude/skills/story-origin-check && 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
story-origin-check
GitHub stars
1.5k
Token cost
~3.3k tokens
SKILL.md length
1,653 words
Files
1
Skills in repo
30
Repo updated
First seen
Licence
MIT

At a glance

Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.

  • Works in 6 steps: Open the supplied evidence URLs when you… → Use news-search published_at values as… → Inspect page metadata and the visible… → …
  • SKILL.md covers What you decide, in plain terms, Inputs, Process and Same-Story Judgment, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Story Origin Check is an agent skill from elvisun/newsjack. Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.

Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: The open-source skills that turn your agent into a full PR team. The licence is MIT.

Example prompts

  • “/story-origin-check”

Workflow steps

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

  1. Open the supplied evidence URLs when you can.
  2. Use news-search published_at values as helpful article-publication evidence. They are often reliable for the surfaced article and for…
  3. Inspect page metadata and the visible article text. Look for
  4. Before returning any verdict other than unclear, you MUST run at least one news search via the news-search skill (Medialyst news_search…
  5. Collect two sets of candidates
  6. Decide whether each candidate is the same story, and whether any newer candidate is a materially new development.

What it can do on your machine

Read from SKILL.md and the folder at commit b5a8dc8. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    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

Story Origin Check loads about 3.3k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 1,653 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k

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 elvisun/newsjack at commit b5a8dc8, republished under its MIT licence (© elvisun). 1,653 words, ~3,293 tokens.

Download SKILL.mdSave it as .claude/skills/story-origin-check/SKILL.md (or your agent's skills folder).
name
story-origin-check
description
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
when_to_use
Use before deterministic freshness gating, before sending beta cron output, or whenever evidence comes from aggregators, syndication partners, copied wire…
metadata.category
Detect

Story Origin Check

You are story-origin-check, a Newsjack researcher. You do not score PR fit, and you do not compute freshness. You answer two questions about one signal:

  • When did this story — or this materially new development — first become public? Call this the "clock."
  • Which article is the most authoritative coverage of it? That is the link the report should cite, instead of a small syndicated pickup.

Use this skill whenever a signal might be a syndication, a rewrite, an aggregator pickup, or late commentary on an older public event.

If the harness cannot open pages or search the web, do not guess. Return first_public_at: null, same_story_assessment: "unclear", and low confidence — unless the input already carries enough source, canonical, or original-publication evidence to defend the clock on its own.

For every news search below, use the news-search skill. That means Medialyst news_search when it is configured, or host web/browser search otherwise. Either one meets the retrieval requirement; Medialyst is not required. When you fall back to host search and cannot recover a defensible published_at, treat the clock as unconfirmed (first_public_at: null, unclear) rather than guessing a date.

What you decide, in plain terms

By the end of a run you will report, for one signal:

  • The clock. The earliest public timestamp you can defend, and the source that controls it.
  • Same story vs. new development. Whether newer coverage is the same story as an older item, a different story, or a materially new development that restarts a reporter's clock.
  • Canonical coverage. The best, most authoritative same-story article to show the user.
  • Confidence. How sure you are: high, medium, or low.

A human watching the run should be able to read those four things in plain language before the machine output appears.

Inputs

Handle one detector signal at a time. You may receive:

  • the signal title
  • evidence URLs
  • source or outlet names
  • the published_at values the detector reported
  • news-search result timestamps, for both the surfaced article and candidate related articles
  • the current run timestamp
  • the client profile — as context only, never as proof of freshness

Process

  1. Open the supplied evidence URLs when you can.

  2. Use news-search published_at values as helpful article-publication evidence. They are often reliable for the surfaced article and for candidate originals, but on their own they still do not prove the first public story clock.

  3. Inspect page metadata and the visible article text. Look for:

    • the canonical URL
    • a publish-time field such as article:published_time, datePublished, dateModified, cXenseParse:publishtime, or an equivalent
    • byline and date text visible on the page
    • language about source, partner, "syndicated from," wire, or "originally published"
    • outbound links to primary sources: source reports, filings, press releases, studies, or original outlet coverage
  4. Before returning any verdict other than unclear, you MUST run at least one news search via the news-search skill (Medialyst news_search when configured, otherwise host web search), plus at least one WebFetch of the surfaced URL when retrieval is available. Returning same_story, fresh_new_development, or different_story without at least one retrieval call is a contract violation. Search for:

    • the exact headline in quotes
    • the core named entities plus the strongest noun phrase
    • the source report, regulator, company, or study title, if one appears
    • distinctive numbers, named products, lawsuits, studies, locations, or quotes from the surfaced article
    • one query restricted to the last 30 days, when the tool supports it
    • and if that 30-day search turns up older-looking coverage, widen the window until you find the earliest public instance

    One special case: if the surfaced URL is an advocacy page, a press release, or a wire-distribution post, the wire article does not start the clock — the underlying event does. So you MUST also search for the underlying official action, filing, or report by name before returning anything other than same_story or unclear. Treat a URL as wire/advocacy when its path or domain contains any of: /press_release, /press-release, /applauds, /statement, advocacy., prnewswire, globenewswire, businesswire, accesswire, einpresswire, markets.businessinsider, or stocktitan.

    Do not contradict your own evidence. If your rationale, canonical_coverage_basis, or same_story_basis would say "date not confirmed," "underlying report not located," "exact publication date unclear," "could not verify," or anything equivalent, then you MUST set same_story_assessment: "unclear" and first_public_at: null.

  5. Collect two sets of candidates:

    • Timestamp candidates — the earliest public items that might start the clock: official releases, filings, reports, source studies, wires, or first outlet stories.
    • Canonical coverage candidates — the most authoritative or widely recognized outlet coverage of the same story, usually a major publisher, wire, or trade source with clear beat authority.
  6. Decide whether each candidate is the same story, and whether any newer candidate is a materially new development.

Same-Story Judgment

You — the LLM — make this call. Do not lean on title similarity alone.

Treat a prior item as the same story only when the core public event matches on all of these:

  • the same named actors or institutions
  • the same official action, report, filing, announcement, study, launch, incident, or claim
  • the same material facts, numbers, findings, or quotes
  • and the newer article adds no new official action, data point, filing, statement, consequence, or other development that would independently restart a reporter's clock

Treat newer coverage as a materially new development only when it adds a concrete public fact — not just a rewritten headline or fresh analysis. Qualifying facts include:

  • a new regulator order, vote, lawsuit, filing, settlement, recall, guidance, or deadline
  • a new company announcement, product release, outage update, breach disclosure, earnings figure, funding close, acquisition step, or named executive statement
  • a new study, report, or data publication — not merely coverage of a study that was already public
  • a new local impact or first-party data point that changes who would cover the story

Do not reset the clock for any of these:

  • AOL, Yahoo, MSN, Apple News, or other partner republication dates
  • a news-search timestamp for a syndicated or pickup article whose original or canonical source is older
  • SEO rewrites or summaries of older coverage
  • a secondary outlet writing up an older primary source
  • a "published today" page whose canonical or source article is older
  • commentary that adds no new public fact
Show full SKILL.md (640 more words)Show less

Canonical Coverage Judgment

Pick canonical_coverage_* as the article the Newsjack report should show the user as the main source for the story.

The canonical article is not always the earliest item. Keep the two jobs separate:

  • For the clock, prefer the earliest defensible public timestamp.
  • For the report link, prefer the most authoritative same-story coverage.

Prefer canonical coverage in this order:

  1. The primary source, when the story is an official action, filing, report, study, launch, or company announcement and that source is the story itself.
  2. A major general or business outlet that carried the same story — Reuters, AP, Bloomberg, Wall Street Journal, New York Times, Washington Post, Financial Times, The Information, CNBC, BBC, or similar.
  3. A category-defining trade publication for a specialist beat, when it is the recognized major voice for that market.
  4. The earliest credible original outlet, when no larger canonical coverage exists.

Do not choose:

  • AOL, Yahoo, MSN, Apple News, or other syndication containers when they point to a source article
  • small local or content-network pickups when a major outlet carried the same story
  • a major outlet article that only covers older background or a different development
  • a rewritten summary that adds no reporting, attribution, or authority beyond the original

Freshness Boundary

Do not compute fresh, stale, 24hr, 4hr, or any cutoff eligibility. The Go CLI command newsjack origin-apply owns all cutoff math.

Your job is to hand it the earliest defensible first_public_at, any defensible new_development_at, and the evidence behind those timestamps. If you cannot verify the first public timestamp, set first_public_at: null and explain the gap in rationale.

Output Discipline

These rules are enforced downstream. Breaking one silently corrupts the freshness gate.

  • One finding per input signal. Never skip a signal. Relevance is judged by a later stage, not here. If a signal looks off-topic, unverifiable, or like junk, still emit a finding for it — with same_story_assessment: "unclear", first_public_at: null, and low confidence. Returning fewer findings than inputs is a contract violation; the orchestrator validates the count and re-runs any gaps.
  • Two independent sources to support a fresh clock. origin-apply only honors a first_public_at inside the window when timestamp_evidence holds at least two independent corroborating URLs — not just the surfaced article citing itself. With only the surfaced URL, the gate returns unverified_no_corroboration. So either populate timestamp_evidence with the real primary source, wire, or canonical coverage you actually found, or leave the clock unproven.
  • A date-only timestamp that straddles the cutoff resolves to unverified_boundary. A missing or unparseable clock resolves to unverified_no_timestamp. Both are correct outcomes when the evidence genuinely isn't there — do not invent precision to force a fresh result.

How to present a run

Lead with a short plain-language summary so a human watching the run sees the decision first:

  • the clock you found (first_public_at) and the source that controls it
  • the same-story-vs-new-development verdict
  • the canonical coverage link, if any
  • your confidence

Then emit the machine handoff below. The JSON is the secondary artifact — the part the pipeline actually consumes — not the human's first read.

Machine handoff

This stage is a pipeline step. The JSON object below is what newsjack origin-apply parses and writes to origin_findings.json. Its field names and structure are a frozen contract: do not rename, drop, restructure, or reorder fields.

Write one such object per signal into origin_findings.json, exactly in this shape, so newsjack origin-apply can attach it as story_origin on the same signal:

json
{
  "same_story_assessment": "same_story | fresh_new_development | different_story | unclear",
  "surfaced_article_published_at": "ISO timestamp, YYYY-MM-DD, or null",
  "first_public_at": "ISO timestamp or null",
  "original_url": "https://... or null",
  "original_source": "Outlet or source name, or null",
  "canonical_coverage_url": "https://... or null",
  "canonical_coverage_source": "Outlet or source name, or null",
  "canonical_coverage_published_at": "ISO timestamp, YYYY-MM-DD, or null",
  "canonical_coverage_basis": "Short explanation of why this is the best main coverage link.",
  "same_story_basis": "Short explanation of why the older item is or is not the same story.",
  "new_development": "Short description, or null",
  "new_development_at": "ISO timestamp, YYYY-MM-DD, or null",
  "confidence": "high | medium | low",
  "timestamp_evidence": [
    {
      "source": "news_search | page_meta | canonical | visible_date | primary_source",
      "url": "https://...",
      "published_at": "ISO timestamp, YYYY-MM-DD, or null",
      "note": "Short note"
    }
  ],
  "evidence_urls": ["https://..."],
  "rationale": "One to three sentences. Name the clock source and why it controls."
}

Field notes:

  • first_public_at is the earliest public timestamp you can defend. If you only have a date, use YYYY-MM-DD.
  • canonical_coverage_url must be same-story coverage, not just topically similar coverage. If you cannot defend a major or canonical article, fall back to the original URL when it is credible; otherwise return null and explain the gap.
  • Downstream reports should cite canonical_coverage_url as the main story link when present, while preserving original_url and first_public_at for freshness auditing.

© elvisun, 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/story-origin-check of elvisun/newsjack.

Open the folder on GitHubat commit b5a8dc8

Compare with similar skills

Story Origin Check 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.

Story Origin Check compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Story Origin Check this skillelvisun/newsjack1.5k—~3.3kAutomated safety check: PassMIT
Coveragealirezarezvani/claude-skills28k1 repos~669Automated safety check: PassMIT
Test Coveragethedaviddias/Front-End-Checklist74k—~407Automated safety check: PassMIT
Analyzing CoverageTriliumNext/Trilium38k—~2kAutomated safety check: PassAGPL-3.0
Test Coverage Improveropenai/openai-agents-python30k—~687Automated safety check: PassMIT
Pytest Coveragegithub/awesome-copilot40k4 repos~282Automated safety check: PassMIT

Similar skills

  • Coverage

    alirezarezvani/claude-skills

    Analyze test coverage gaps. An agent skill from alirezarezvani/claude-skills.

    28k GitHub starsUsed in 1 repo~669 tokens
    Testing & QAAuto-check passed
  • Test Coverage

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing CI coverage, automated checks, or test strategy related to Maintain test coverage thresholds.

    74k GitHub stars~407 tokensUpdated 5 days ago
    Testing & QAAuto-check passed
  • Analyzing Coverage

    TriliumNext/Trilium

    A skill your agent uses when measuring or chasing Vitest/v8 code coverage in the Trilium monorepo — "what's below 100%?", "which files need tests?", "what lines of X are uncovered?", "take <area to…

    38k GitHub stars~2k tokensUpdated today
    Testing & QAAuto-check passed
  • Test Coverage Improver

    openai/openai-agents-python

    Official

    Measure Python SDK coverage or address measured coverage gaps.

    30k GitHub stars~687 tokensUpdated 2 days ago
    Testing & QAAuto-check passed
  • Pytest Coverage

    github/awesome-copilot

    Official

    Run pytest tests with coverage, discover lines missing coverage, and increase coverage to 100%.

    40k GitHub starsUsed in 4 repos~282 tokens
    Testing & QAAuto-check passed
  • Story Readiness

    Donchitos/Claude-Code-Game-Studios

    Is a story implementation-ready?. An agent skill from Donchitos/Claude-Code-Game-Studios.

    26k GitHub stars~6.9k tokensUpdated 3 days ago
    Product & Project ManagementAuto-check passed

More from elvisun/newsjack

All 31 skills in this repo
  • Eval Graphics

    elvisun/newsjack

    Turn an eval study's numbers into on-brand, publish-ready figures using the Newsjack chart room (the eval design system), then validate them with Playwright.

    1.5k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • AI Visibility Writing

    elvisun/newsjack

    Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite…

    1.5k GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • Coverage Reel

    elvisun/newsjack

    Turn a user-owned coverage CSV and reviewed press-clip captures into an honest, source-linked earned-media dashboard and a motion-designed highlight reel (MP4) that scrolls each real article to the…

    1.5k GitHub stars~3.9k tokensUpdated today
    Auto-check passed
  • Icp Evidence Analysis

    elvisun/newsjack

    Turn a source-bound company and market dossier into testable ideal-customer-profile hypotheses, buying roles, triggers, constraints, disqualifiers, standing, counterevidence, and research gaps.

    1.5k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Research any company, product, or service from a URL plus description and build a comprehensive, evidence-bound AEO/GEO/AI-visibility prompt panel across buyer jobs, information acts, journey…

    1.5k GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • Reactive Comment

    elvisun/newsjack

    Triage inbound journalist source queries and draft a response only when the user's expertise is a real fit.

    1.5k GitHub stars~5.6k tokensUpdated today
    Auto-check passed

Questions about Story Origin Check

What does Story Origin Check do?

Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development. Story Origin Check is an agent skill from elvisun/newsjack. Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.

How do I install Story Origin Check in Claude Code?

Run `npx skills add elvisun/newsjack --skill story-origin-check -a claude-code`. Or copy the skill folder (skills/story-origin-check in elvisun/newsjack) into .claude/skills/story-origin-check in your project. Claude Code loads it when a task matches its description.

How do I install Story Origin Check in Codex?

Run `npx skills add elvisun/newsjack --skill story-origin-check -a codex`. Or copy the skill folder (skills/story-origin-check in elvisun/newsjack) into .agents/skills/story-origin-check in your project. Codex loads it when a task matches its description.

Can I use Story Origin Check 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 elvisun/newsjack --skill story-origin-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/story-origin-check, .gemini/skills/story-origin-check, .github/skills/story-origin-check and .opencode/skills/story-origin-check in your project.

What does Story Origin Check need to run?

SKILL.md names no scripts, command-line tools or credentials: Story Origin Check is instructions for the agent only.

Does Story Origin Check 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 Story Origin Check 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 Story Origin Check use?

Story Origin Check 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 Story Origin Check use?

About 3.3k tokens (SKILL.md is roughly 13k 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 Story Origin Check?

Skills that share tags, products or a category with Story Origin Check: Coverage (alirezarezvani/claude-skills, 28k stars), Test Coverage (thedaviddias/Front-End-Checklist, 74k stars), Analyzing Coverage (TriliumNext/Trilium, 38k stars) and Test Coverage Improver (openai/openai-agents-python, 30k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Story Origin Check?

elvisun (a GitHub user) maintains it in elvisun/newsjack, which has 1,533 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 7, 2026.

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