y-a-v-a

@y-a-v-a source repo

13 skills
0 followers
13 hours ago last updated

▌
Grill Me · y-a-v-a bundle
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".

0
installs
▌
Session Export · y-a-v-a bundle
Export the current (or a specified) Claude Code or OpenAI Codex session to a single self-contained HTML file, including any subagent transcripts. Use when the user asks to "export this session", "save the chat as HTML", "share this conversation", or wants an offline-readable record of a coding-agent session.

0
installs
▌
Render Loop · y-a-v-a bundle
Project-local dev feedback loop for the session-export renderer. Use when asked to check, fix, or improve how a Claude Code / Codex session renders in the exported HTML — e.g. "check the rendering of tool call X around Y, see session <uuid>". Exports the session to HTML, screenshots the relevant card with headless Chrome so the result can be viewed, then guides editing skills/session-export and re-validating.

0
installs
▌
Codex Discuss · y-a-v-a bundle
Reach agreement with OpenAI Codex on a design, plan, or approach through a turn-based discussion in a shared markdown file. Use during ideation or planning when you want a second model to challenge and sharpen an approach before any code is written.

0
installs
▌
Codex Validate · y-a-v-a bundle
Validate the codex, codex-review, and codex-discuss skills end-to-end in a session where the Codex CLI is available — preflight, hook unit tests, and per-skill smoke tests that prove context actually reaches Codex — then self-improve by recording each run and tightening checks when something breaks. Use when codex is installed and you want to confirm the skills still work.

0
installs
▌
HTML · y-a-v-a bundle
Use this skill when the user wants to export the current "situation" — the state of the conversation, work done, findings, data, or context — to a standalone HTML file they can open in a browser. The agent decides what is most valuable to capture and visualize. Invoked as /html, optionally with hints about what to focus on.

0
installs
▌
Strunk · y-a-v-a bundle
Strunk's Elements of Style — Rewriter

0
installs
▌
Attribution · y-a-v-a bundle
Use this skill when the user wants to add author attribution to a project, for example to a README.md or as a footer on a website. Handles bare invocation (falls back to git config), explicit name/email/website arguments, and free-form placement instructions.

0
installs
▌
Social Preview · y-a-v-a bundle
Generate a GitHub social preview image (1280×640 PNG) for the current repo. Builds a throwaway social-preview.html styled after the project's own look (webapp theme colors, fonts, layout) with a minimal tagline from the README, screenshots it with headless Chrome, and iterates with the user until approved. Use when the user asks for a social preview, OG image, open-graph image, or repo card image.

0
installs
▌
Google Search · y-a-v-a bundle
Search the web using Google Programmable Search Engine. Use when you need to search for information online with custom search engine configuration.

0
installs
▌
Stern Code Review · y-a-v-a bundle
Use this skill when the user asks for a rigorous, blunt, senior-level code review focused on correctness, maintainability, production risk, unnecessary abstraction, weak tests, security issues, and operational failure modes. Do not use it for brainstorming, greenfield implementation, or purely stylistic feedback.

0
installs
▌
Codex · y-a-v-a bundle
Delegate a coding task to OpenAI Codex CLI for implementation. Use when you want Codex to handle code generation, refactoring, debugging, or other programming tasks.

0
installs
▌
Codex Review · y-a-v-a
Run a code review using OpenAI Codex CLI. Analyzes uncommitted changes or diffs against a base branch.

0
installs

13 published skills