AdirD
UserReusable skills, commands, and rules for coding agents (Cursor, Claude Code, Codex).
Categories
Indexed Skills (24)
melech-consult
Get an independent verdict on an AI-proposed plan, fix, architecture, or claim by verifying its premises against the real artifact, then dispatching a panel of fresh models from different providers that answer independently. Use for "double check", "proof this", "are you sure", "second opinion", "am I right or is he right", "this still isn't working", or "not sure this is the right approach".
melech-idea-to-canvas
Turn rough ideas or docs into a standalone Cursor Canvas for team understanding.
melech-think-with-me
Think out loud with a sharp, well-read engineer peer who expands half-formed ideas with real prior art, patterns, and mechanisms — not interrogation, not a council, not a spec.
melech-debug-mode
Debug or verify a local UI end to end in the user's existing Chrome tab, with temporary runtime probes and a manual browser fallback.
melech-live-browser
Operate the user's already-open, logged-in Chrome tabs through Chrome DevTools MCP. Use whenever the user asks the agent to jump into their current browser, continue work in an existing tab, fill or submit a form, write or post a comment or reply, update a page, inspect what is open, or interact with signed-in web apps such as Confluence. Also use as the browser-driving companion to melech-debug-mode; do not start a debugging collector for ordinary browser work.
melech-market-validation
Test whether a product or market opportunity has real demand and willingness to pay.
melech-smart-comments
Preserve code intent with selective comments and protect meaningful existing comments.
melech-sync-skills
Sync this skill library globally across supported coding agents.
melech-cr-clone-trainer
Build or resync a private reviewer that learns your GitHub code-review style.
melech-diff-minimizer
Minimize an existing PR or diff while preserving its required behavior and containing semantic blast radius.
melech-handoff
List and continue coding-agent transcripts across Cursor, Claude Code, Codex, Gemini, and other local agents. Use when finding a recent transcript, resuming prior work, or invoking `/melech-handoff`.
melech-make-it-click
Recover when the agent's explanation did not land by finding the smallest thing blocking understanding and replacing the failed mental model with a concrete one.
melech-pr-gardener
Tend one explicit GitHub author's open PRs and keep them green — one stateless pass per scheduled run.
melech-prompt-shake
Tree-shaking for prompts — strip bloat from system prompts, skill files, and instruction docs so they cover 100% of needed cases in the fewest lines.
melech-8020
Find the smallest useful path to a product or engineering outcome.
melech-babysit
Keep a PR moving through review, conflicts, and CI until merge-ready.
melech-buy-vs-build
Decide whether to adopt an existing tool or build a capability yourself, grounded in verified research.
melech-challenge
Pressure-test an existing direction before implementation.
melech-distill-need
Uncover the real need behind a requested solution before building it.
melech-pre-plan
Align on a buildable design concept before planning or coding.
melech-prune
Audit and remove dead code, AI residue, and unnecessary complexity after iteration.
melech-visualize
Turn an idea, flow, or structure into a compact ASCII diagram.
melech-code-review-clone
Build or resync a private reviewer that learns your GitHub code-review style.
melech-verify
Give the caller a genuine second opinion on a claim, conclusion, or approach already discussed. Use for "verify", "re-verify", "prove it", "second opinion", or "is that actually true".
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.