witi-projects

57 mods across 1 repository, 2 stars between them.

domain-model

25

witi-projects/Skills

Skill Claude CodeCodex

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions. Use when the user says "/domain-model"…

2 4mo ago A 73 tokens copy · 91% MIT

edit-article

26

witi-projects/Skills

Skill Claude CodeCodex

Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft. Use when the user says "/edit-article", "edit article", or asks about edit article.

2 4mo ago A 54 tokens copy · 88% MIT

exporting-to-png

27

witi-projects/Skills

Skill Claude CodeCodex

Export code, terminal output, diagrams, or UI components to PNG images using headless browser rendering or CLI tools. Use when the user says "/exporting-to-png", "exporting to png", or asks about exporting to png.

2 4mo ago A 54 tokens copy · 89% MIT

witi-projects/Skills

Skill Claude CodeCodex

Scan running terminals for dev server URLs (localhost ports), report them, and optionally open the app in Cursor's built-in browser. Use when the user says "/finding-dev-server-url", "finding dev server url", or asks about finding dev server url.

2 4mo ago A 56 tokens copy · 92% MIT

fixing-broken-links

29

witi-projects/Skills

Skill Claude CodeCodex

Crawl all links in a file or project, test each for a valid HTTP response, report broken ones, and fix or remove them. Use when the user says "/fixing-broken-links", "fixing broken links", or asks about fixing broken links.

2 4mo ago A 59 tokens copy · 92% MIT

form-testing

30

witi-projects/Skills

Skill Claude CodeCodex

Use Cursor's browser to fill and submit every form in the app with valid and invalid data, verifying validation, error states, and success flows. Use when the user says "/form-testing", "form testing", or asks about form testing.

2 4mo ago A 51 tokens copy · 92% MIT

generating-images

31

witi-projects/Skills

Skill Claude CodeCodex

Generate or edit images using the OpenAI Image API (gpt-image-2). Use when the user asks to generate, create, draw, render, illustrate, mock up, or edit an image, icon, logo, mockup, illustration, OG image, blog hero, marketing asset, or similar visual. Also use when the user supplies a reference image and asks to…

2 4mo ago A 159 tokens copy · 92% MIT

witi-projects/Skills

Skill Claude CodeCodex

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code. Use when the user says "/git-guardrails-claude-code", "git guardrails…

2 4mo ago B 95 tokens copy · 84% MIT

github-triage

33

witi-projects/Skills

Skill Claude CodeCodex

Triage GitHub issues through a label-based state machine. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow. Use when the user says "/github-triage", "github triage", or asks about github triage.

2 4mo ago A 73 tokens copy · 98% MIT

grill-me

34

witi-projects/Skills

Skill Claude CodeCodex

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me". Use when the user says "/grill-me", "grill me", or asks about grill me.

2 4mo ago A 70 tokens copy · 89% MIT

grinding-until-pass

35

witi-projects/Skills

Skill Claude CodeCodex

Keep iterating on code changes until the tests pass, the build succeeds, or linting is clean. Runs in a tight loop of fix → run → check → repeat. Use when you want the agent to autonomously grind through test failures or build errors. Use when the user says "/grinding-until-pass", "grinding until pass", or asks about…

2 4mo ago A 83 tokens copy · 94% MIT

witi-projects/Skills

Skill Claude CodeCodex

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable. Use when the user says…

2 4mo ago A 96 tokens copy · 72% MIT

incident-response

37

witi-projects/Skills

Skill Claude CodeCodex

Handle production incidents — triage, mitigate, communicate, and write postmortems. Use when the user says "/incident-response", "incident response", or asks about incident response.

2 4mo ago A 39 tokens copy · 92% MIT

witi-projects/Skills

Skill Claude CodeCodex

Deploy applications to Kubernetes — Deployments, Services, Ingress, ConfigMaps, Secrets, health checks, and scaling. Use when the user says "/kubernetes-deploying", "kubernetes deploying", or asks about kubernetes deploying.

2 4mo ago A 55 tokens copy · 91% MIT

migrate-to-shoehorn

39

witi-projects/Skills

Skill Claude CodeCodex

Migrate test files from as type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace as in tests, or needs partial test data. Use when the user says "/migrate-to-shoehorn", "migrate to shoehorn", or asks about migrate to shoehorn.

2 4mo ago A 76 tokens copy · 94% MIT

witi-projects/Skills

Skill Claude CodeCodex

Watch running terminal processes for crashes and stack traces. When an error appears, navigate to the failing file and line, diagnose, and fix it automatically. Use when the user says "/monitoring-terminal-errors", "monitoring terminal errors", or asks about monitoring terminal errors.

2 4mo ago A 59 tokens copy · 86% MIT

witi-projects/Skills

Skill Claude CodeCodex

After navigating and interacting in Cursor's built-in browser, use browsernetworkrequests to audit every fetch/XHR for failures, slowness, duplicate calls, and suspicious payloads. Use for API-heavy pages and after backend or client networking changes. Use when the user says "/network-request-auditing", "network…

2 4mo ago A 79 tokens copy · 95% MIT

obsidian-vault

42

witi-projects/Skills

Skill Claude CodeCodex

Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian. Use when the user says "/obsidian-vault", "obsidian vault", or asks about obsidian vault.

2 4mo ago A 66 tokens copy · 88% MIT

parallel-ci-triage

43

witi-projects/Skills

Skill Claude CodeCodex

When GitHub Actions fails, fetch failing job logs and assign each failing job to a separate subagent that fixes its slice of the problem in parallel. Use for multi-job CI failures where jobs are independent. Use when the user says "/parallel-ci-triage", "parallel ci triage", or asks about parallel ci triage.

2 4mo ago A 73 tokens copy · 97% MIT

witi-projects/Skills

Skill Claude CodeCodex

Run four parallel read-only subagents that each review the same diff from a different lens — security, performance, correctness, and readability — then merge findings into one report. Use before merging large or risky PRs. Use when the user says "/parallel-code-review", "parallel code review", or asks about parallel…

2 4mo ago A 69 tokens copy · 92% MIT

parallel-exploring

45

witi-projects/Skills

Skill Claude CodeCodex

Explore a large codebase in parallel by launching multiple explore subagents that each investigate a different area simultaneously. Use when onboarding onto a new project, understanding architecture, or investigating a cross-cutting concern. Use when the user says "/parallel-exploring", "parallel exploring", or asks…

2 4mo ago A 66 tokens copy · 94% MIT

witi-projects/Skills

Skill Claude CodeCodex

When multiple tests fail, assign each failing test file to a separate subagent that fixes it independently in parallel. Use when the user says "/parallel-test-fixing", "parallel test fixing", or asks about parallel test fixing.

2 4mo ago A 50 tokens original MIT

witi-projects/Skills

Skill Claude CodeCodex

Profile a running web application's CPU performance using Cursor's built-in browser profiler. Captures call stacks, identifies slow functions, and suggests optimizations. Use when a page feels slow or janky. Use when the user says "/profiling-performance", "profiling performance", or asks about profiling performance.

2 4mo ago A 64 tokens copy · 98% MIT

prompt-engineering

48

witi-projects/Skills

Skill Claude CodeCodex

Write effective prompts for LLMs — structure, few-shot examples, chain-of-thought, system prompts, and output parsing. Use when the user says "/prompt-engineering", "prompt engineering", or asks about prompt engineering.

2 4mo ago A 50 tokens original MIT