lkshrk
- 20 skills
- 0 followers
- 6 hours ago last updated
- ▌ AI Context Generator · lkshrk bundleGenerates .ai-context knowledge base for coding agents. Activate when: (1) setting up a new project for AI-assisted development, (2) user asks to "create project knowledge" or "setup ai-context", (3) existing .ai-context needs regeneration. Creates tiered documentation structure optimized for agent comprehension and token efficiency.
- ▌ Litho Document Skill · lkshrk bundleThis skill should be used when the user asks to "generate project documentation", "analyze codebase architecture", "create C4 architecture diagrams", "document a repository", "generate technical docs", "使用 Litho 生成文档", "分析代码库架构", "生成架构文档", "为项目生成技术文档", "生成 C4 模型文档", "为这个项目写文档", "自动生成文档", "帮我分析这个代码库", or any request involving automated documentation generation for a software project. This skill enables the AI agent to autonomously analyze any codebase and produce high-quality C4 architecture documentation (Overview, Architecture, Workflow, Deep-Exploration modules, Boundary Interfaces, Database Overview) — equivalent to what deepwiki-rs produces — purely through agent reasoning and tool usage, without depending on any external binary.
- ▌ Upgrade Deps · lkshrk bundleUpgrade a repository's dependencies safely, one at a time, in any ecosystem — npm/pnpm/yarn/bun, cargo, go modules, pip/poetry/uv, gradle/maven, Docker images, and Flux/GitOps Helm/OCI charts. Detects the stack, prioritizes security and patch bumps, reads each changelog before bumping, asks before major/breaking upgrades, and gates every change on validate + verify (build/test, or Flux health) before moving to the next. Use when the user wants to upgrade/update/bump dependencies, refresh lockfiles, process Renovate/Dependabot PRs, or update charts/images in any repo.
- ▌ Loc Change Table · lkshrk bundleCount line changes in one folder and all subdirectories since a given date, grouped by git repository and file category. Use when the user asks for LOC changes, line changes, churn, diff stats, changed lines, or repo-by-category tables since a date.
- ▌ Mac Disk Reclaim · lkshrk bundleDiscover and reclaim wasted SSD space on macOS, then delete it interactively with the consequences spelled out. Finds bloat by what it is, wherever it lives — build/dep dirs (node_modules, target, .venv, DerivedData) scattered across every project, package/tool caches, Electron app caches buried under Application Support, AI agent history (Claude/Codex logs), bloated .git objects, merged git worktrees, .DS_Store swarms, per-volume trash, Time Machine local snapshots. Walks findings largest-first and, only after the user confirms each one, deletes it directly (NOT to Trash) — telling the user up front what regenerates vs what is gone forever. Remembers each delete/skip choice so reruns only ask about newly-found items. Use when the user is low on disk/SSD space, wants to free space, clean a Mac, purge caches, or remove build/dependency bloat.
- ▌ Yabai Skhd Doctor · lkshrk bundleHealth-check the macOS yabai (tiling window manager) and skhd (hotkey daemon) services — verify they are installed, their launchd services are running, they hold Accessibility permission, configs exist, and yabai's scripting-addition prereqs (SIP, sudoers) are met. When anything is wrong it prints a concrete fix path. Use when yabai or skhd stopped working, hotkeys/window management aren't responding, after a macOS update, or when the user asks to check/verify/diagnose/fix their yabai or skhd setup.
- ▌ Project Tool Allowlist · lkshrk bundleScan a repo's stack and tooling plus installed helper tools (package managers, build/test/lint commands, make, git, rtk) and generate a project-local permission allowlist for the current agent/client so those commands run without prompting. Use when the user wants fewer permission prompts, to pre-approve a project's dev tools, or to set up an agent config for a repo's stack.
- ▌ Linear Close · lkshrk bundleFinalize a Linear issue after review: verify merged PR evidence, issue-ID commit evidence, moved cross-team issue IDs, or squash/import release file evidence, update dashboard/status evidence, move the issue to Done, and clear LLM workflow labels.
- ▌ Linear Doctor · lkshrk bundleCheck whether a Linear workspace is ready for Linear AI workflows. Use before first run, when labels/projects are missing, when setup is uncertain, or when agents cannot decide target team, project, component, type, LLM, or Superpowers labels.
- ▌ Linear Refine · lkshrk bundleRefine a Linear issue into a ready implementation plan through targeted questions, local review, and marked plan comments. Use when an issue needs clarification, planning, accepted unknowns, acceptance criteria, or a `llm-ready` handoff.
- ▌ Linear Review · lkshrk bundleRun parallel reviewer subagents across a target repo or diff to surface findings across correctness, security, maintainability, performance, tests, dead code, and dependency health, dedup them against a persistent ledger and Linear, then triage survivors into Linear tickets. Use when the user wants a code review, repo health audit, or to turn review findings into tickets.
- ▌ Linear Status · lkshrk bundleInspect a Linear issue and report the current workflow phase, missing evidence, state inconsistencies, and recommended next skill. Use when the user asks what is next, where the issue stands, whether work can resume, or why labels/comments disagree.
- ▌ Linear Implement · lkshrk bundleExecute a ready Linear implementation plan: make code changes, verify them, ask for the final code destination, and post marked implementation status comments. Use when a Linear issue already has a ready plan and needs implementation.
- ▌ Linear Batch Close · lkshrk bundleBatch-orchestrate Linear closeout: find llm-review issues, confirm the queue and bounded parallelism, and dispatch linear-close subagents while closeout mutations stay with linear-close.
- ▌ Linear Batch Refine · lkshrk bundleBatch-orchestrate Linear refinement: find llm-refine and llm-blocked issues, show the queue, process one issue at a time with linear-refine subagents, and aggregate questions and feedback.
- ▌ Linear Create Issue · lkshrk bundleCreate or update clean Linear issues from rough bug reports, feature ideas, or copied Linear issue drafts. Use when the user asks to ingest, triage, classify, tag, or prepare a Linear issue before implementation planning.
- ▌ Linear Nontech Intake · lkshrk bundleInterview non-technical people directly and create Linear issues from plain-language reports, requests, confusion, screenshots, screen recordings, error messages, links, examples, or desired outcomes. Use when a non-technical user needs help filing a Linear issue that should enter `llm-refine` with a `nontechnical-intake` marker because technical triage is still required.
- ▌ Linear Repo Reconcile · lkshrk bundleReconcile messy Linear-linked repository state after multiple agents, branches, worktrees, commits, PRs, or old session data: discover issue-tagged work, compare it with main, PRs, Linear issue content, comments, revisions, timeline evidence, and locally available agent session evidence; produce a reconciliation plan; safely delete only proven-merged local work; integrate finished work; rebase active work; diagnose common pipeline failures; and update Linear statuses, labels, descriptions, and marked comments to match verified repository reality.
- ▌ Linear Batch Implement · lkshrk bundleBatch-orchestrate ready Linear implementation work: find llm-ready issues with newest valid ready plans, confirm the queue and parallelism, and dispatch isolated linear-implement subagents.
- ▌ Linear Deliver Feature · lkshrk bundleRun the full Linear AI workflow for one feature or bug: create issue, refine plan, implement work, verify, prepare review handoff, and close after merge. Use when the user wants one feature delivered through all Linear AI steps end to end.