premortem / CO-STAR-UI-CREATOR
Cursor rule2 starsChanged 5 months agoApache-2.0View on GitHub
CO-STAR UI Creator agent rules — follow CO-STAR-PROMPT for development; use CO-STAR-CREATOR to build custom CO STAR prompts from user goals.
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,183 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository168 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/CO-STAR-UI-CREATOR/CO-STAR-CREATOR.mdCursor rule
- .cursor/rules/CO-STAR-UI-CREATOR/CO-STAR-PROMPT.mdCursor rule
- .cursor/rules/CO-STAR-UI-CREATOR/README.mdCursor rule
- .cursor/rules/CO-STAR-UI-CREATOR/ui.mdCursor rule
- 401-403-bypass-techniquesSkill
- active-directory-acl-abuseSkill
- active-directory-certificate-servicesSkill
- active-directory-kerberos-attacksSkill
- agent-browserSkill
- ai-ml-securitySkill
- ai-seoSkill
- android-pentesting-tricksSkill
- anti-debugging-techniquesSkill
- api-auth-and-jwt-abuseSkill
- api-authorization-and-bolaSkill
- api-recon-and-docsSkill
- api-secSkill
- arbitrary-write-to-rceSkill
- arize-adminSkill
- arize-ai-provider-integrationSkill
- arize-annotationSkill
- arize-compliance-auditSkill
- arize-datasetSkill
- arize-evaluatorSkill
- arize-experimentSkill
- arize-instrumentationSkill
- arize-linkSkill
- arize-prompt-optimizationSkill
- arize-promptsSkill
- arize-traceSkill
- authbypass-authentication-flawsSkill
- auth-secSkill
- binary-protection-bypassSkill
- browser-exploitation-v8Skill
- building-nango-functions-locallySkill
- building-nango-functions-remotelySkill
- building-nango-functionsSkill
- business-logic-vulnerabilitiesSkill
- business-logic-vulnSkill
- classical-cipher-analysisSkill
- clickjackingSkill
- cmdi-command-injectionSkill
- code-obfuscation-deobfuscationSkill
- compliance-checkSkill
- compliance-trackingSkill
- container-escape-techniquesSkill
- core-engineeringSkill
- cors-cross-origin-misconfigurationSkill
- crlf-injectionSkill
- csp-bypass-advancedSkill
- csrf-cross-site-request-forgerySkill
- csv-formula-injectionSkill
- d3-visualizationSkill
- dangling-markup-injectionSkill
- defi-attack-patternsSkill
- dependency-confusionSkill
- deserialization-insecureSkill
- dns-rebinding-attacksSkill
- documentation-writerSkill
- The first 60 shown.
The file
We split this AGENT.mdc into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 15
Use it as the single source of truth for:
- Distinctive: line 18
Do not contradict or bypass the CO-STAR flow (e.g.
- Distinctive: line 22
Use CO-STAR-CREATOR.md: when the user wants to create their own CO STAR prompt from their desired outcome and goals.
≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule 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.
Files
--- alwaysApply: true description: CO-STAR UI Creator agent rules — follow CO-STAR-PROMPT for development; use CO-STAR-CREATOR to build custom CO STAR prompts from user goals. --- # CO-STAR UI Creator Agent This rule file defines how the AI agent behaves when working in the CO-STAR UI Creator context. **You must follow the instructions below.** ## Mandatory references ### When developing (implementation, code, UI work) - **You must follow** the instructions, structure, and response pattern defined in **CO-STAR-PROMPT.md**. - Use it as the single source of truth for: - Role and context (C), objective (O), style (S), tone (T), audience (A), and response pattern (R). - Discovery questions, library/registry choices, implementation plans, and code guidance. - Do not contradict or bypass the CO-STAR flow (e.g. scoped questions first, then plan, then implementation). ### When creating or customizing a CO STAR prompt - **Use CO-STAR-CREATOR.md** when the user wants to **create their own CO STAR prompt** from their desired outcome and goals. - CO-STAR-CREATOR.md is the guide for: - Defining a custom CO-STAR prompt tailored to the user’s product, design system, or use case. - Filling in Context, Objective, Style, Tone, Audience, and Response format from the user’s inputs. ## Summary | Document | Purpose | |-----------------------|--------| | **CO-STAR-PROMPT.md** | **Development** — follow mandatorily when building or implementing UI (React, components, design systems, integration). | | **CO-STAR-CREATOR.md**| **Prompt creation** — use when the user wants to author or adapt a CO STAR prompt based on their goals and preferences. | Adhere to these references so behavior stays consistent and aligned with the CO-STAR methodology.
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.