verify-against-reality
Skill0 starsChanged 3 months agoNo licenceView on GitHub
מוכיח שהקוד עובד מול המציאות ולא רק מול המסמך — הרצה כמו שהצרכן מריץ, אימות כתיבה בקריאה חוזרת של המצב, ובדיקה שמסוגלת להיכשל. Use whenever code writes, sends, deletes or otherwise changes state, and whenever you are about to tell the user that something works, is fixed, or is done. The verification half applies even when no external API is involved. Trigger it after a bug fix, after a tool call returned ok, before offering a passing test as evidence, and when a change touches anything a browser, a protocol client or another service consumes. Do NOT use for read-only code, for pure refactors that change no behaviour, for planning or spec discussion where nothing runs yet — or when the user explicitly asked for speed over verification. For choosing the correct signature, field name or endpoint in the first place, use source-driven-development. Citing a source is not running the code.
In this repository42 other files it gives its agents.
- brand-guidelinesSkill
- browser-measurementSkill
- built-in-browserSkill
- canvas-designSkill
- chrome-browserSkill
- click-to-convert-auditSkill
- codebase-explorerSkill
- code-reviewSkill
- coding-standardSkill
- computer-useSkill
- debug-like-expertSkill
- deep-researchSkill
- design-system-mdSkill
- doc-coauthoringSkill
- docsSkill
- docxSkill
- emotional-sharingSkill
- explanatory-writingSkill
- google-workspaceSkill
- hebrew-document-generatorSkill
- hebrew-landing-designSkill
- hebrew-rtl-best-practicesSkill
- import-memorySkill
- israeli-customer-support-automatorSkill
- israeli-social-contentSkill
- logo-designerSkill
- marketing-contentSkill
- mcp-analytics-pythonSkill
- mcp-builderSkill
- pdfSkill
- pptxSkill
- startup-hook-skillSkill
- skill-corner-postSkill
- skill-creatorSkill
- Skill DevelopmentSkill
- skill-forgeSkill
- skill-routerSkill
- source-driven-developmentSkill
- tech-guide-designSkill
- theme-factorySkill
- web-artifacts-builderSkill
- xlsxSkill
The file
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
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.