agentleFS
jgamaraalvjgamaraalv/delivery-loop/.claude/skills/cypress-docs/SKILL.md

cypress-docs

Skill0 starsChanged 4 months agoMITView on GitHub

Search and extract Cypress information from official documentation (docs.cypress.io, cypress.io); prefer LLM markdown under /llm/* and refuse unverified API or behavior claims.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search before you claim: Never assert "Cypress can / cannot…" from memory — search the docs first, retrying with alternate terminology …

    line 13
  2. Distinctive:

    Never invent: If the docs can't verify a claim, say "I could not verify this in Cypress docs," offer the closest documented alternative, …

    line 20
  3. Distinctive:

    Be version-aware: Use the version if given, else assume latest stable.

    line 23
  4. Distinctive:

    Read on demand (progressive disclosure):

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Cypress Documentation

Retrieve accurate, verifiable Cypress information by treating the official docs as the source of truth — never memory.

Core rules

  • Search before you claim. Never assert "Cypress can / cannot…" from memory — search the docs first, retrying with alternate terminology before concluding a feature is missing.
  • Prefer the LLM-optimized docs. On docs.cypress.io, fetch /llms.txt, then read the Markdown mirror under /llm/* — every page has one (e.g. …/app/faq → …/llm/markdown/app/faq.md). Fall back to the HTML page only if the /llm version is incomplete.
  • Primary sources only: https://docs.cypress.io and https://www.cypress.io (plus /changelog/ and the cypress.io blog for version/update questions).
  • Never invent. If the docs can't verify a claim, say "I could not verify this in Cypress docs," offer the closest documented alternative, and never guess an API, signature, or default. Prefer "unknown" over incorrect.
  • Be version-aware. Use the version if given, else assume latest stable; when behavior differs by version, call it out explicitly.

References

Read on demand (progressive disclosure):

  • references/search-strategy.md — query-type → doc-section routing table, the /llm/* → standard → changelog → blog search flow, error-message routing, and /llms.txt auto-discovery · read when locating the right doc page.
  • references/extraction-rules.md — how to extract commands / concepts / configuration, response style and confidence annotation, caching, safety rules, and a worked example · read when structuring an answer from a fetched page.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.