← all publishers

lil-lon

@lil-lon source repo

6 published skills

  1. Gh CLI · lil-lon
    Use the GitHub CLI (`gh`) to fetch information from GitHub: issues, PRs, comments, reviews, workflow runs, repos, and search. A curated set of read-only `gh` subcommands and read-only `gh api` endpoints are pre-approved and run without prompts. The sandbox lets `gh *` reach the network unsandboxed. Write operations (anything that changes state on GitHub) are NOT pre-approved and MUST NOT be executed unless the user explicitly asks for that write. Even when explicitly requested, run the natural command and let the harness's approval prompt fire — NEVER reshape the command to evade pattern matching. Use this skill whenever you need information from GitHub. Proactively invoke it (do NOT answer from memory or prior conversation) when the user references a GitHub issue, PR, review, comment, action run, or repo, or asks things like "show me the comments", "what's in PR #N", "what did the reviewer say".
    0
    installs
  2. Ideation · lil-lon bundle
    YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to "brainstorm this", "I have an idea", "help me think through this", "office hours", or "is this worth building". Proactively invoke this skill (do NOT answer directly) when the user describes a new product idea, asks whether something is worth building, wants to think through design decisions for something that doesn't exist yet, or is exploring a concept before any code is written.
    0
    installs
  3. Codex Review · lil-lon bundle
    Review staged changes with Codex by piping `git diff --cached` to `codex exec` and asking for P1-P4 labeled findings. Use when the user asks for a Codex-specific review on staged work ("codex review", "review with codex"). Do NOT auto-invoke for generic "review this" requests — those belong to the built-in `/review` skill.
    0
    installs
  4. Podcast Prep · lil-lon
    Active-recall prep for the Tech Table Log podcast. Given a blog post or paper, drives a Socratic Q&A session that surfaces gaps in the host's understanding before recording, then produces a scannable on-screen script (concept + 3-5 supporting points) to glance at during the live show. Use when the user wants to prep a podcast episode, draft a podcast script, or shares a blog/paper saying they want to discuss it on the podcast.
    0
    installs
  5. Agent Worktree · lil-lon bundle
    Spawn an isolated Claude Code sub-task in a fresh git worktree, split into a new tmux pane next to the caller, then clean up when done. Use this whenever the user wants to delegate a small, self-contained side task without disturbing the current session — e.g. they say "do this in a worktree", "spawn a sub-agent", "start a side task", "run this in the background", or ask for parallel work like "fix this typo while you keep refactoring". Always use this skill for those requests instead of editing files directly when the user's intent is to fork off a parallel job.
    0
    installs
  6. Complete Implementation · lil-lon
    Complete an implementation end-to-end: stage targeted changes, run `codex-review`, fix any P1/P2 findings (loop up to 3×), commit using Conventional Commits, then push. Use when the user asks to finalize, ship, wrap up, or "complete" the current implementation.
    0
    installs