Borrowing it
Nothing to install: this file belongs to kirill-markin/flashcards-open-source-app. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kirill-markin/flashcards-open-source-app/main/.agents/skills/publish-public-flashcard-deck/SKILL.mdgit clone --depth 1 https://github.com/kirill-markin/flashcards-open-source-appWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kirill-markin/flashcards-open-source-app/publish-public-flashcard-deck)<a href="https://agentmods.dev/skills/kirill-markin/flashcards-open-source-app/publish-public-flashcard-deck"><img src="https://agentmods.dev/badge/skills/kirill-markin/flashcards-open-source-app/publish-public-flashcard-deck/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kirill-markin/flashcards-open-source-app/publish-public-flashcard-deck"><img src="https://agentmods.dev/badge/skills/kirill-markin/flashcards-open-source-app/publish-public-flashcard-deck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 11 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 14 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 17 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00090 | $0.05570 |
| Opus 5 | $0.00045 | $0.02785 |
| Sonnet 5 | $0.00018 | $0.01114 |
| Haiku 4.5 | $0.00009 | $0.00557 |
Grade A, and why
publish-public-flashcard-deck scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Before drafting, inspect one published deck. `GET https://api.flashcards-open-source-app.com/v1/catalog` now redirects to an immutable CDN artifact holding the complete public JSON snapshot, so a plain `curl` needs `-L` How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish a public flashcard deck
Reference
Before drafting, inspect one published deck. GET https://api.flashcards-open-source-app.com/v1/catalog now redirects to an immutable CDN artifact holding the complete public JSON snapshot, so a plain curl needs -L to follow it; do not use that endpoint for reference and do not use it for per-deck verification. The only sanctioned read of that snapshot is the one step 8 names. Read one deck and at most five of its cards through bounded endpoints:
package_json="$(curl --fail --silent --show-error 'https://api.flashcards-open-source-app.com/v1/catalog/packages?limit=1')"
printf '%s\n' "$package_json" | jq '.catalogPackages[0]'
package_version_id="$(printf '%s\n' "$package_json" | jq -r '.catalogPackages[0].latestVersion.packageVersionId')"
curl --fail --silent --show-error "https://api.flashcards-open-source-app.com/v1/catalog/package-versions/${package_version_id}/cards?limit=5" | jq '.cards'
Product defaults
- For a standardized full-course deck, do not block on the learner's current topic or school textbook. Confirm the curriculum edition, level, language, and exam session only when they change scope, then build a complete internal coverage ledger.
- Optimize title, slug, and description strongly for the exact learner query while remaining accurate, useful, and rights-safe. Put the primary course or exam query first when it accurately identifies the content. Verify applicable naming and trademark rules before using a third party's course, exam, or standard name; never use its logo or trade dress or imply official status, affiliation, or endorsement. Keep the public title and canonical slug evergreen for a stable curriculum; use the current year only in separate SEO metadata or a visible
Reviewed for <year>line after an annual compatibility check. Preserve one package and URL across compatible years. - For an independently authored common-knowledge deck intended for unrestricted reuse, default the license field to
Common knowledge · CC0 1.0and keep it label-only. Apply CC0 to original questions, answers, organization, metadata, and original or LLM-generated media to the extent applicable rights exist. Put scope, provenance, and non-affiliation language in the description. Do not claim ownership of facts or license rights the publisher does not hold. - When a course or examination owner is named, end the description with an independent, unofficial, non-affiliation notice; state that no examination questions, mark schemes, or curriculum text were copied when true; and link the owner's official requirements page. Keep these statements outside the license field.
- Default to no third-party media. Create original or LLM-generated visuals from facts with an independent composition; do not trace or redraw a specific source image. Use third-party media only when the user explicitly requests it and its provenance, license, attribution, and intended reuse are verified.
- Public catalog cards support optional images and LaTeX math; use either only when it materially improves the content. Write
$...$inline for a short expression inside a sentence, with no space just inside either$and no digit right after the closing$; write a standalone display formula as its own block, with$$alone on the opening and closing lines and a blank line before and after it or the start or end of the card side, because a$$block that does not stand alone stays literal. Escape a currency$as\$(\\$inside JSON such ascards.json). Put math only in a plain paragraph that holds no link, image, bold, italic, strikethrough, or code anywhere in it, and keep it out of headings, lists, tables, blockquotes, code blocks, and raw HTML, and off any card side using reference-style link or image definitions; anywhere else it stays literal. - Default to one short, recognizable root tag on every card. For a large deck, allow one coarse group tag in addition to the root; never exceed two tags per card or create a deeper public hierarchy by default. Use clear abbreviations, merge small topics into broader groups, and keep fine topics, difficulty, source-specific syllabus codes, and production statuses internal. Before drafting a large deck, state every public tag and the target card count for each group.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed a5171a970191
- yesterday Changed · +18 lines 00066c7b5c7c
- 12d ago First seen · 48 lines · 90 tokens per session scan A a348f1971f58
publish-public-flashcard-deck is a skill published in the GitHub repository kirill-markin/flashcards-open-source-app (65 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 5,570 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
minddory-language-partner
Use when the user has connected the MindDory MCP connector and wants to learn or practice a language. Turns the conversation into a tutoring session — captures new words into spaced-repetition flashcards, tracks grammar mistakes, and quizzes the user on what is due, scoped to their CEFR level.
prowler-docs
Prowler documentation style guide and writing standards. Trigger: When writing documentation for Prowler features, tutorials, or guides.
book-to-skill
Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns. Use when the user wants to study a document through GitHub Copilot CLI, Amp, Claude Code, or Hermes…
education-expert
Expert-level education technology, learning management systems, and ed-tech platforms. Use when the user mentions edtech, lms, e learning, or assessment, or when the task involves Educational Technology or Standards.
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…