jl-cmd

Build, install, run, and test the claude-dev-env installer. Use when asked to run claude-dev-env, install the Claude Code config into ~/.claude, drive the installer, smoke-test it against a sandbox, or run its test suite.

Max-recall code review at a selectable effort level (low, medium, xhigh), with optional auto-fix and an auto-execute loop for any level. Triggers: /e-code-review, /e-code-review low, /e-code-review medium, /e-code-review xhigh, /e-code-review <level> --fix, /e-code-review <level> loop.

Build a polished self-contained HTML product launch and release-notes page from work completed in the current session, using available repository state, source-of-truth files, tests, approvals, artifacts, commits, pull requests, previews, and release evidence. Use when the user asks to build release notes, create a launch page, document completed work, produce feature-release HTML, or turn the session into product-facing release notes.

File, update, and close GitHub work as one epic with native sub-issues. Dedup open and closed issues first. Edit status only inside marker sections. Refresh the epic checklist so it matches its children. Triggers: issue tracker, file an issue, track this issue, open an epic, update the epic, close the issue, refresh the epic checklist, attach a sub-issue.

Harvests session obstacles into GitHub issues backed by quoted evidence: validates each draft with the user, then delegates filing to the issue-tracker agent (skill fallback), which dedupes against open and closed issues and files each under an epic as a native sub-issue. Prints a cloud handoff prompt. Triggers: /closeout, close out this session, close out the session, file the session obstacles, session closeout, harvest session obstacles, end-of-session issue filing. Not session-log (vault journal) — closeout files issues and writes no journal.

Cleanup-only pass on the current diff — reuse, simplification, efficiency, altitude — that fixes what it finds directly; no correctness-bug hunting. Triggers: /e-simplify.

Coordinates source-grounded implementation through a validated plan packet, planned task tickets, fixed model routing, verified commits, independent Luna review, and publication gates. Triggers: "Plan-to-PR", "plan to PR", "implement this with one task per commit", "run the Plan-to-PR workflow", "validate Plan-to-PR", "publish the PR".

Gather open session tasks and register them with the best available task or plan tool. Triggers: '/task-build', 'build my task list', 'capture these tasks', 'add open tasks to the task list', 'track these', task list, update plan.

Caveman-trimmed variant of pmax. Builds prompts decision by decision. Asks structured multiple-choice questions in small rounds, posts each approved answer as a tagged line in chat, then assembles the final prompt only from those tagged lines so nothing unapproved is added. Use when the user wants a prompt built piece by piece without re-reading drafts. Triggers: '/pmax-cm', 'pmax-cm', 'caveman pmax', 'trimmed pmax'.

Builds prompts decision by decision. Asks structured multiple-choice questions in small rounds, posts each approved answer as a tagged line in chat, then assembles the final prompt only from those tagged lines so nothing unapproved is added. Use when the user wants a prompt built piece by piece without re-reading drafts. Triggers: '/pmax', 'build a prompt with me', 'pmax', 'incremental prompt builder'.

Single-pass XML formatter — takes a raw input block, emits one clean xml fence with context-adapted tags and an Outcome digest. Zero tool calls, zero plan mode, zero validation loop.

Mid-tier XML formatter — takes a raw input block, drafts context-adapted XML, runs the 15-row compliance audit and file-based validation loop, then emits the validated fence and Outcome digest. Zero plan mode, zero AskUserQuestion, zero Outcome preview gate.

Authors repository-grounded XML prompt artifacts for Claude: system and developer instructions, agent harnesses, tool-use patterns, evaluation rubrics, NotebookLM audio customization, and MCP or browser automation steering. Enters plan mode for deep codebase exploration, runs AskUserQuestion rounds during planning, gets user approval via ExitPlanMode, converts plan headers to XML tags at all depths, runs a mandatory Outcome preview gate, then delivers one fenced XML block and a skimmable Outcome digest after the fence. Trigger when the user asks to write, refine, or improve steering text for Claude. Execution of the described work belongs in /agent-prompt only after the user explicitly confirms they want it run.

Runs the prompt-generator workflow through its paste-ready XML handoff, then spawns a background subagent whose task is that user-approved XML. Triggers: '/agent-prompt', 'launch an agent', 'spawn agent to do X', 'delegate this', 'run in background', 'execute the prompt with an agent'. Does not apply when the user only needs the fenced prompt and digest with no subagent (/prompt-generator).

Validate Obsidian backend connectivity and vault health. Run diagnostics on MCP server, headless CLI, vault path, sync status, and vault structure. Use when the user says /obsidian-check, check obsidian, obsidian status, vault health, or any variation of "is my vault working".

Log a session report to the Obsidian vault, track vault context usage, extract unrecorded decisions, tidy the project's session folder, and output a /rename command. Use when the user says /session-log, journal this session, log this work, session report, or any variation of "summarize/log/record this session". Also triggers on "save session", "capture session", or "document what we did".

Audit, clean, and consolidate session logs in the Obsidian vault. Fixes format drift, resolves orphaned next-steps, updates stale statuses, and generates project rollup summaries. Use when session logs feel cluttered or before starting a new project milestone. Triggers on '/session-tidy', 'tidy sessions', 'clean up session logs', 'session audit'.

Deep Research mode — iterative multi-source research producing comprehensive Obsidian reports with citations. Official-docs-first methodology. Triggers: '/deep-research [topic]'

Enforces anti-hallucination constraints by requiring citations, source grounding, and explicit 'I don't know' responses when evidence is lacking. Activates for research tasks where factual accuracy is critical. Triggers: 'research mode', 'toggle research', '/research-mode'.

Consolidate, prune, and reorganize auto memory files. Simulates Auto Dream -- fixes format drift, deduplicates facts, enforces index structure. Use when memory feels stale or cluttered. Triggers on '/dream', 'consolidate memory', 'clean up memory', 'dream'.

A 3-step demo workflow that enforces completion via the verify-completion Stop hook. Use to test workflow enforcement or as a template for your own skills.