liorhai5

@liorhai5 source repo

10 skills
0 followers
12 hours ago last updated

▌
Agency · liorhai5 bundle
Expert consultation system — get perspectives from specialized AI personas. Use /agency list to browse, /agency find to get recommendations, /agency consult @name for advice, /agency deliberate @name @name for structured debate.

0
installs
▌
Mem · liorhai5 bundle
Search and browse AI conversation history. Requires ai-memory MCP server.

0
installs
▌
Mtg · liorhai5 bundle
Design-first AI development methodology — structured workflows for design, planning, implementation, review, and commit. Governs non-trivial changes through design logs with approval gates.

0
installs
▌
Tsk · liorhai5 bundle
Track tasks, progress, and dependencies across repos and sessions. Requires ai-tasks MCP server.

0
installs
▌
Md2html · liorhai5 bundle
Convert a local markdown file to a self-contained HTML file and open it in the browser, so it can be copy-pasted into Google Docs with formatting and images intact. Use when the user asks to "turn this markdown into a Google Doc", "paste this md into Docs", or "convert md to html for pasting".

0
installs
▌
Search Skill · liorhai5 bundle
Use when the user asks to find, evaluate, rate, refactor, or synthesize Agent Skills (the SKILL.md folder format) across GitHub and skill marketplaces. Covers searching for a skill for a task, deep-diving a candidate, rating an existing SKILL.md, refactoring a skill, fetching a remote skill for inspection, or creating a new local skill from researched patterns. Do NOT activate for general package search (npm, PyPI, cargo), web search, or code research not involving SKILL.md files.

0
installs
▌
Optimize Skill · liorhai5
Use when the user asks to "optimize this prompt", "improve this SKILL.md", "make this prompt more reliable", "fix my agent instructions", "review this AGENTS.md", "strengthen this prompt", "my agent keeps skipping steps", "add enforcement to instructions", or needs to transform weak prompts into reliable, enforceable agent protocols. Uses a 6-step gated flow (with Fast/Full modes), command strengthening, gate injection, and failure mode analysis.

0
installs
▌
Design Critique · liorhai5 bundle
Use when reviewing a UX spec, mockups, screens, a design doc, or a live UI for usability and UX quality, case & state coverage, and completeness. Evaluates against Nielsen's heuristics, Laws of UX, interaction patterns, information architecture, and content quality, then writes a verdict-first critique report. Invoke for "review this design/spec/mockup", "is this UX any good", "heuristic evaluation", "what states/cases are missing", "critique this flow". Read-only — produces a report, changes nothing.

0
installs
▌
Research Codebase · liorhai5
Investigate a codebase with system awareness — read boundaries, ownership, control flows, data flows, contracts, and blast radius BEFORE recommending action. Produces a structured understanding artifact with every claim cited file:line. Use when the user asks to "understand this codebase", "deep-dive this feature", "trace this flow", "why is this slow/flaky/coupled", "is this PR safe", "what breaks if I change Y", "prepare to refactor Z", "investigate this bug at the system level". For research from external sources (URLs, docs, Slack), use a research command in mtg or similar. For greenfield architecture design, this is not the right tool.

0
installs
▌
Create Web Manifest · liorhai5 bundle
Give a web app a complete install identity — favicon set, PWA and home-screen icons, web app manifest, and the <head> meta that iOS, Android and link-preview crawlers read. Use when shipping or deploying a web app, or when the user mentions favicon, app icon, apple-touch-icon, web manifest, PWA, "add to home screen", install prompt, theme color, a stock scaffold title, or icons that look wrong, blurry, black, or cropped on a phone.

0
installs

10 published skills