jasonkuhrt

Use when a tool, library, or framework doesn't support what you need and official docs don't cover it — finding solutions off the happy path. Triggers on "how do I make X do Y", "X doesn't support Y", undocumented behavior, bleeding-edge tool limitations, workarounds for missing features, or when the mainstream answer is "you can't do that"

Iteratively review, refactor, verify, and commit toward less code by sharing primitives and improving functional composition. Use when the user asks for a strict refactor review loop, "get a review strictly for refactoring to less code", "repeat review/fix/commit until empty", or similar wording.

Use when the user says "sync" or wants to commit, rebase, push, and converge this dotfiles repo. Uses just up as the public converge command.

Poll, diagnose, and report on a GitHub PR's CI. Use this skill whenever you're about to watch a PR's CI to a terminal state — after pushing commits to a PR, after /git_sync, when the user says "is CI green", "wait for CI", "check the PR's checks", "monitor CI", "did CI pass", "watch the workflow", "fix CI failures", or any phrasing that asks whether a PR is ready to merge based on its checks. ALSO use proactively whenever you push a commit to a branch that has an open PR — never spin up an ad-hoc `gh pr checks --watch` or count-based poll. This skill is the only authority for PR CI status; ignore any older guidance suggesting otherwise.

Complete GitHub PR review-comment closeout. Use whenever the user asks to address, fix, handle, clear, close, resolve, respond to, or follow up on PR review comments, review threads, requested changes, bot findings, CodeRabbit, Greptile, or Devin review feedback. Addressing a review thread includes a written thread reply and resolving the thread after the fix or justification is pushed.

Orchestrate land-pr, gh-ci, and land-merged into one end-to-end landing pipeline. Use when the user asks to land complete, land and merge, merge on green, finish a PR end to end, or land without another confirmation loop.

Use after a GitHub pull request has already been merged to refresh the local develop worktree, remove the local git worktree that backed the merged PR, and delete the merged local branch. Trigger on requests like "land merged", "cleanup merged PR worktree", "sync develop and delete the PR worktree", or "PR is merged, clean up".

Prepare a branch or GitHub PR to an open, ready PR by composing land-worktree first, then creating a PR when missing, moving it out of draft, scanning existing Greptile review feedback, addressing actionable Greptile feedback when present, watching PR checks, and triggering E2E Local Sign Off after other checks are green when required. Use when the user says to land to PR, prepare a PR, create or ready the PR, undraft and handle existing Greptile feedback, finish review-comment closeout, handle local sign off, or get the PR green without merging.

Add a namespace/module to a @kitz package — including extending the @kitz/effect namespaces. Covers the _.ts/__.ts barrel pattern, the package exports map, and import conventions.

Audits the project for consistency issues that may arise from manual editing. Checks package scripts, tsconfig paths, README tables, and other conventions.

Authors and manages global package scripts using the _: prefix convention. Scripts defined in root package.json are propagated to all packages with the prefix stripped.

Creates commits following project conventions. Handles Conventional Commits with project-specific scopes, PR title requirements, and CI validation rules.

Create a new @kitz/<concept> package via the Vite+ generator. Scaffolds package.json (live-types exports + effect peer), the layered tsconfigs, and the namespace barrel, then wires it into the workspace.

Use when adding project conventions, coding rules, or guidelines. Determines correct location and scoping based on which packages the rule applies to.

Use when filing a GitHub issue for this repo — a bug found during QA/stress-testing, or a feature/enhancement request. Enforces the two permitted cold-startable formats (bug = Expected/Actual, feature = Current/Desired), point-form-only bodies, and the gh filing procedure. Trigger on "file an issue", "open a bug", "log this finding", "make a gh issue", or after stress-testing surfaces a defect.

Refactor imperative TypeScript to Effect-first pipeline composition using curried data-first/data-last APIs, Effect collections, and schema-based IO boundaries.

Session dashboard showing thread timeline, agent roster, and commit counts. Use when the user says "/session:dashboard", "show dashboard", "session overview", "session summary", "what's happening in this session", or "agent activity".

Write a reflective debrief for a session thread. Use when closing a thread, after "/session:debrief", "/debrief", "write a debrief", "debrief this thread", or when session:thread:land invokes it after the done verdict passes.

Read all session debriefs, synthesize patterns, and produce a retrospective. Use when the user says "/session:retro", "retrospective", "session retro", "what patterns do we see", "synthesize debriefs", or "review all debriefs".

Manage sessions, threads, and session wiring. Use when the user mentions sessions, threads, plans, reviews, claims, debriefs, or session sync/doctor. Also triggered by natural language like "create a thread", "what threads are open", "close this thread", "show me the session", "sync the session", "check session health", "claim the frontend thread", "lock the plan", "add a task", or "what's the session status".

Structured context brief and claim transfer for thread handoff between agents. Use when the user says "/session:thread:handoff", "/thread:handoff", "hand off this thread", "transfer thread to", "pass this to another agent", "handoff", or "take over thread".

Perform a real closeout audit for the thread-scoped task and, when requested, land it through commit, push, and CI. Use when the user says "/session:thread:land", "are you done", "can we close this", "is anything still open", "wrap this session up", or wants to end the thread without losing unfinished work, buried follow-ups, or useful loose ends.

Dump a Claude Code session transcript as navigable Markdown, inspect CC task lists, or manage skill outfit and library (on/off/move/doctor). Use when user wants to review/analyze/export a session transcript, dump/open task files, or manage skills.

Turn skills on/off, move between scopes/commitments, undo/redo changes. Interprets user intent to determine the right shan CLI command. Use when user says "add", "equip", "enable", "remove", "disable", "undo", "clear all skills", "turn off everything", "move skill to project", "make skill core".

Run automated health checks on skill outfit. Use when user says "check skills", "diagnose skills", "skill problems", "doctor", "fix skills".

Show current skill outfit (core + pluggable status), character costs, and operation history. Use when user asks "what skills are on", "show my skills", "skill cost", "skill history".

Manage skill library. Routes natural language to skills:change (for on/off/reset/undo) or skills:list (for viewing outfit and history). Use when user says "equip", "add skill", "remove skill", "what skills do I have", "show available skills", "undo", etc.

TODO: Describe when this skill should be triggered. Include specific phrases, commands, or contexts that should activate it.

Learn, inspect, and manage Hookify-based hook setups across Claude and Codex. Use when the user mentions Hookify, wants to understand cross-agent hook behavior, wants to inspect current user-level or project-level hook config, or wants help adopting Hookify in a repo or home directory.

Create or update Hookify hook files and rules. Use when the user wants a new Hookify hook, wants to block or warn on a pattern, wants a rule at user or project scope, or wants to express a policy like blocking cmux in `.all`, `.claude`, or `.codex` files.

Diagnose Hookify configuration and behavior. Use when the user wants to know why a Hookify rule is not firing, why a hook is loading from the wrong scope, whether Claude and Codex are seeing the same policy, or what gap remains in the current platform surface.

Migrate existing Claude or Codex hook setups toward Hookify conventions. Use when the user wants to consolidate old hook files, translate existing policies into `.all`, `.claude`, or `.codex` hook files, or reduce duplicated cross-agent hook logic.

Use when creating beads during feature work on an epic. Triggers on "add a bead", "create a task for", "track this as a bead", or /flo:add.

Use when continuing work on a multi-session epic, starting a new agent session on an existing epic, or when told to work on the next bead.

Autopilot execution through an epic — runs all waves hands-off, parallelizing within each wave. Use when the user wants to swarm, fan out, or run the epic on autopilot. Replaces beads:fanout.

Use when asked to review, audit, or QA an epic's implementation. Triggers on "review the issue", "run QA", "audit quality", or /flo:review.