AkshitIreddy

18 mods across 1 repository, 1 stars between them.

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Run a persistent adversarial research, critique, implementation, and verification loop until the user stops it. Invoke only when the user explicitly asks for this skill or an indefinite refinement loop.

1 4d ago A 43 tokens original MIT

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Write large, thorough implementations instead of minimal ones. Use for UI, animation, art/graphics, sound design, theming, and any craft-driven work where richness and detail are the point — and whenever output quality has been called cheap, flat, simple, or generic.

1 4d ago A 60 tokens original MIT

atomic-commits

03

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Commit discipline for every repository — small atomic commits, Conventional Commits messages, only commit working states. Use whenever creating git commits, splitting work into commits, or writing commit messages, in any project.

1 4d ago A 45 tokens original MIT

audio-verification

04

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Verify and debug synthesized audio (Web Audio API) by rendering it offline and measuring the samples, instead of guessing from code or claiming it works untested. Use whenever building, changing, or reviewing UI sound effects, tones, synths, or any AudioContext graph — and especially when sound is reported as…

1 4d ago A 117 tokens original MIT

build-and-look

05

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Prefer building and looking at variations over prolonged reasoning. Use when work is visual, aesthetic, or hard to predict from first principles — UI, art, animation, sound, layout, colour — and whenever you notice yourself planning at length without producing anything to look at.

1 4d ago A 57 tokens original MIT

build-without-fear

06

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Implement exhaustive, production-grade solutions without minimizing code size. Use when the user explicitly asks for a large, ambitious, comprehensive, defensive, possibility-covering implementation; requests thousands of lines or says not to fear complexity; or when a repeatedly failing UI, animation, audio…

1 4d ago A 78 tokens original MIT

comfyui-assets

07

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Generate game/app art assets locally with ComfyUI and SDXL — seamless tileable textures, transparent-background cutouts, ornament stamps, wallpaper patterns. Use when producing material textures or sprite elements for a rendering pipeline, or when asked to create art assets with a local image model.

1 4d ago B 61 tokens original MIT

diagnosing-bugs

08

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

1 4d ago A 40 tokens copy · 100% MIT

finish-the-list

09

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Keep working until the list is actually empty. Use whenever there is a backlog, a TODO file, a multi-item request ("fix all of these", "complete everything"), or a set of known bugs — and especially when you notice yourself about to summarise progress instead of doing the next item.

1 4d ago A 63 tokens original MIT

frontend-design

10

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

1 4d ago A 40 tokens copy · 100% MIT

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Proactively split work into subagent lanes whenever a request has two or more independently verifiable outcomes, or combines implementation with research, documentation, platform work, audit, or visual/testing verification. Re-run this routing check when the user adds an independent item mid-turn. Keep only simple…

1 4d ago A 69 tokens original MIT

playwright-qa

12

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Drive the running app with Playwright to verify UI work — act, screenshot, read the screenshot, decide. Use whenever a change is visible or interactive, whenever a UI bug is reported, and instead of reasoning about what the UI probably does.

1 4d ago A 54 tokens original MIT

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Require explicit user approval immediately before directly contacting or replying to another person through GitHub comments or reviews, Slack, email, chat, issue trackers, reactions, mentions, assignments, or reviewer requests. Use whenever Codex may send a human-facing message. Do not block otherwise-authorized…

1 4d ago A 87 tokens original MIT

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Broadly research current best practice across dozens of credible online sources before building, then implement the most capable evidence-backed approach rather than the simplest one that works. Use at the start of craft, art, generation, rendering, animation, audio, or ML work, and whenever a default technique may be…

1 4d ago A 67 tokens original MIT

try-it-first

15

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Prefer running the thing to predicting it. Use when a question could be settled by a quick experiment — UI behaviour, rendering, timing, an API's real shape, whether a bug reproduces — and especially when you notice yourself reasoning at length without having tried anything.

1 4d ago A 57 tokens original MIT

visual-verification

16

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Verify UI work by actually looking at rendered screenshots before claiming it works. Use whenever building, changing, reviewing, or debugging anything visual — layout, styling, animation, theming, canvas/WebGL art, icons, or any "does this look right" question. Also use when a UI change is reported broken, or when…

1 4d ago A 73 tokens original MIT

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

1 4d ago A 44 tokens copy · 100% MIT

writing-for-agents

18

AkshitIreddy/agent-skills

Skill Claude CodeCodex

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

1 4d ago A 28 tokens copy · 100% MIT