vvedantb

96 mods across 1 repository, 101 stars between them.

eva-tweet

73

vvedantb/eva

Skill Claude Code

Write launch/announcement tweets in Vedant's style — terse dev-tool shipping posts built from a one-line hook, an optional positioning line, an arrow bullet list of capabilities, and a punchy close. Use whenever drafting or editing a tweet, X post, thread, or launch/changelog post announcing a feature, release…

not rated 101 today A SkillSpector: pass 85 tokens original MIT

fable-mode

74

vvedantb/eva

Skill Claude Code

Delegate all implementation to Opus sub agents, then review their output yourself. Use when the user says "fable mode", "delegate to opus", or wants the main agent to plan and review while sub agents write the code.

not rated 101 changed 11d ago A SkillSpector: pass 50 tokens original MIT

how

75

vvedantb/eva

Skill Claude Code

Explain how something works in this codebase by exploring code and producing a clear architectural explanation. Optionally critique the architecture for issues.

not rated 101 today A 28 tokens copy · 100% MIT

i-have-adhd

76

vvedantb/eva

Skill Claude Code

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

not rated 101 today C 62 tokens copy · 97% MIT

write-a-prd

77

vvedantb/eva

Skill Claude Code

Create a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.

not rated 101 today A SkillSpector: pass 51 tokens original MIT

zoom-out

78

vvedantb/eva

Skill Claude Code

Explain an area of the codebase to the user until reaching shared understanding. Use when user wants to under an area of a code better, or mentions "zoom out".

not rated 101 today A SkillSpector: pass 37 tokens original MIT

libraries-dev

79

vvedantb/eva

Skill Claude CodeCodex

Use the Libraries.dev UI effect libraries correctly and find where they fit in a project. Covers Border beam (border-beam), Thinking orbs (thinking-orbs), Gooey (liquid-gooey), Voice (voice-glow), Bot avatars (bot-avatars), Liquid metal (metal-fx) and Image (img-fx). Use when adding an AI thinking or loading state, a…

not rated 101 today A 171 tokens original MIT

test-audit

80

vvedantb/eva

Skill Claude CodeCodex

Invoke whenever writing, changing, reviewing, or sweeping tests. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only production seams they demand.

not rated 101 today A 47 tokens copy · 100% MIT

vvedantb/eva

Skill Claude Code

Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.

not rated 101 today A 42 tokens copy · 95% MIT

vvedantb/eva

Skill Claude Code

Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.

not rated 101 today A 42 tokens copy · 95% MIT

vvedantb/eva

Skill Claude Code

Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.

not rated 101 today A 46 tokens copy · 89% MIT

vvedantb/eva

Skill Claude Code

Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.

not rated 101 today A 39 tokens copy · 97% MIT

vvedantb/eva

Skill Claude Code

Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'.

not rated 101 today A 50 tokens copy · 89% MIT

vvedantb/eva

Skill Claude Code

Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.

not rated 101 today A 68 tokens copy · 92% MIT

grab-proof

87

vvedantb/eva

Skill Claude Code

Grab a screenshot of the current work as proof. Seed mock data if needed, then clean it up.

not rated 101 today A 24 tokens original MIT

brag-slim

88

vvedantb/eva

Skill Claude Code

Turn a project directory or a website URL into a short, shareable launch video with music, motion, and share copy. One file, no bundled assets — built entirely by the model with the tools already on the machine. Use when someone says "/brag-slim", "let's /brag about this", "brag about a website", "make a launch…

not rated 101 today A 121 tokens copy · 100% MIT

brag

89

vvedantb/eva

Skill Claude Code

Turn the current project website into a short, polished, shareable launch video using Hyperframes. Use when someone says "/brag", "let's brag about this", "make a launch video", "turn this into a video", or wants to share what they built. Reads the project code directly — no live URL or screenshots needed.

not rated 101 today A 71 tokens original MIT

security-audit

90

vvedantb/eva

Skill Claude CodeCodex

Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pen tests. Run the complete workflow only for explicit codebase audit or pen-test requests, full/comprehensive/end-to-end…

not rated 101 today A 72 tokens copy · 100% MIT

vvedantb/eva

Skill Claude CodeCodex

Turn a screen recording of a UI (page load, navigation, redirect/auth flow, app startup) into an interactive paint timeline page. You get a full-window video, a timeline of each visual paint with timestamps and durations, and on-video flashes of what was painted (pink) versus what only moved (blue). Use when the user…

not rated 101 today A 118 tokens original MIT

e2e

92

vvedantb/eva

Skill Claude Code

Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change…

not rated 101 today A 175 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: