Menu
SkillsMP has collected 36 skills from juspay/kolu. Open a skill to review its source and details.
Showing 36 of 36 collected skills.
How a downstream app consumes the shared @kolu/surface stack (@kolu/surface · surface-app · surface-remote · surface-mcp) — declaring a typed reactive surface, serving it, consuming it (SolidJS hooks or a CLI), and mirroring a remote surface over ssh.…
Run this repo's tests scoped to the current changes — the unit lane (`just test-unit` / a `--filter`ed vitest run) and the e2e lane (`.feature` files selected from `git diff`, run via `just test-quick`), plus which lane a diff needs and where it is safe to…
odu MCP server launcher — drive CI from a coding agent. `bin/serve` resolves odu via Nix and runs `odu mcp` in the cwd. See the repo README for the tools/resources and override knobs.
Reference for the `odu` runner — how to invoke a full pipeline, a single recipe, or a platform-pinned node, and how to attach to a live run, from a project whose CI odu runs. Trigger when the user asks to "run CI", "run the pipeline", "re-run a check", to run…
Evaluate an architecture against foundational principles of state, change, and time — five grounded principles PLUS a fixed set of named, executable review checks (C1–C7) run as a Workflow fan-out over a diff: ecosystem duplicates, consumer ergonomics,…
Modern, interactive alternative to `/do` — clarify intent up front, then take a task end-to-end with a serial AI review gauntlet (lens review (lowy ∥ hickey) → agent debate → simplify → code-police, each editing the branch in turn) → CI → evidence. ONLY…
Drive one AI agent from another through kolu's terminals: spawn a Claude Code / Codex / opencode session in a PTY, prompt it, watch the screen, read the reply, prompt again. PRIMARY PATH: the kolu MCP tools (`lifecycle_create`/`lifecycle_sendInput`,…
Kolu's project-wide default for filesystem monitoring is `@parcel/watcher`. Reach for this skill when adding or modifying any code that watches files or directories — recursive subtree watching, single-file observation, fs.watch alternatives, chokidar…
Run an automated debate with a live Claude, Codex, or Grok peer until consensus — no round cap, no deadlock exit. Two explicit subcommands: `review` has the selected peer critique the current diff while the invoking agent fixes or disputes findings,…
Running memory of the bridge — the coordination rules for a supervising agent driving implementing agents on kolu terminals — authorization boundaries, the dispatch protocol (MCP-first via the kolu skill, with its TUI fallback), verification discipline, and…
Run an automated debate with a live Claude, Codex, or Grok peer until consensus — no round cap, no deadlock exit. Two explicit subcommands: `review` has the selected peer critique the current diff while the invoking agent fixes or disputes findings,…
Run this repo's CI end-to-end — the kolu-specific procedure on top of the odu runner: the odu MCP front door, banned opt-out flags, mandatory two-platform coverage, venue-pool leasing, fail-fast surfacing, e2e timing evidence, and the green-gate. Triggers on…
Run /be's review gauntlet SERIALLY — architecture-first-principles FIRST (framework/structure diffs), then /lens-debate (lowy ∥ hickey), then /agent-debate with an explicitly selected Claude/Codex/Grok peer, then /simplify, then code-police, each editing and…
Create, update, or finalize a note in the kolu Atlas (docs/atlas) — frontmatter, the MDX component kit, build + check-sync, and the preview/share links. Use whenever authoring or editing an Atlas note (e.g. a /be plan-of-record).
Review code for quality, simplicity, and common mistakes before declaring work complete.
Do a task end-to-end — implement, PR, CI loop, ship. ONLY invoke when the user explicitly types `/do` or `$do`; never auto-select from a natural-language request, even one that sounds like an end-to-end task.
Produce visual PR evidence — a screenshot or video — whenever a change has on-screen impact. Tests are never a substitute; a change can be backend by cause and visible by effect. Capture via the project's e2e harness on a pu box, or by driving a live kolu…
Evaluate code (especially LLM-generated) for structural simplicity using Rich Hickey's "Simple Made Easy" framework. Use when reviewing a PR, diff, or snippet for accidental complexity, or when the user asks about complecting, simplicity vs. easiness,…
Evaluate architecture and module boundaries for volatility-based decomposition using Juval Lowy's framework (from "Righting Software", building on Parnas 1972). Use when reviewing module splits, service boundaries, new abstractions, or any decomposition…
Enter talk mode — conversation and research, no repo changes. ONLY invoke when the user explicitly types `/talk` or `$talk`; never auto-select from a natural-language question or design discussion.
Audit an implementation against its plan with a hostile peer agent, debate findings to consensus, and drive fix waves until the auditor runs dry. Use when a done-claim needs verification the implementer cannot game ("hostile review", "adversarial audit", "is…
Run an autonomous overnight campaign to find, prove, fix, and document CI flakes. Use when the user asks to stabilize CI through repeated full-pipeline runs and leave an evidence-backed draft PR.
Cut a kolu release — tag master, promote the Unreleased changelog entry, publish a GitHub release. ONLY invoke when the user explicitly types `/release` or `$release`; never auto-select from a natural-language request.
Test kolu's remote-host features (multi-host / padi-remote) in a real browser against a real remote box — the ONLY full end-to-end harness for this surface (real ssh provision, no mock). Covers the isolated nix-run invocation (or just dev, which bakes the…
Supervise an implementing agent driving a /be run in a kolu terminal: brief it, wire the backchannel, set the goal. Use when one agent session dispatches a task to another agent ("coordinate this", "have Grok/Codex implement X via /be", "supervise the run") —…
Review the current diff through two structural lenses — lowy (volatility-based decomposition) and hickey (structural simplicity) — run as two independent parallel subagents, then merged by ONE reconcile-and-apply pass that commits the uncontested fixes.…
Write engaging PR titles and descriptions for any forge (GitHub today; Bitbucket planned). Use when creating or updating PRs. Leads with narrative paragraphs and reaches for lists, tables, and diagrams when content is genuinely structured.
Launch the kolu dev server on two RANDOM free ports so it never collides with the running production `kolu.service`, remember the ports for the rest of the session, and tear down only the dev instance. Load before running the app locally — for evidence…
Classify, write, and audit documentation per Diátaxis (diataxis.fr) — the four-quadrant method (tutorials · how-to guides · reference · explanation). Encodes the compass as a decision procedure, each quadrant's contract as hard rules, and an executable…
Adversarial "perfection" review — hold a change to an *ideal* bar, not just a correct one, assuming eternal time, unlimited energy, and no ship pressure. Use when the user asks to review "for perfection", to make a defect "impossible to express", or to hunt…
Write a kolu blog post grounded in the real build history — mine the Claude Code session logs behind a feature for the actual story (for large efforts, fan out over the transcripts with an ultracode workflow), draft it in the author's voice, and wire it into…
Write essays, articles, and blog posts in Paul Graham's voice — plain, spoken prose that reasons out loud and lands surprising true claims, not AI filler. Use when asked to write or rewrite something "like Paul Graham", "in PG's style", or to make a piece…
chrome-devtools-mcp launcher — a single bash script that resolves Playwright's bundled Chrome-for-Testing and Node.js directly through Nix. See repo README for usage, override mechanisms, and version compatibility.
Use Pierre Computer Company's `@pierre/trees` (path-first file tree) and `@pierre/diffs` (shiki-based code/diff renderer) in Kolu. Pierre ships Preact/vanilla cores with optional React wrappers — Kolu consumes the vanilla classes and wraps them in thin…
pnpm + Nix build conventions. Covers fetchPnpmDeps hash management and dependency workflow.
Diagnose Kolu client-side performance issues (memory leaks, high GPU, slow interactions) using chrome-devtools MCP + the Debug → Diagnostic info dialog + heap-snapshot analyzers. Triggers on "memory leak", "GPU memory", "tab bloat", "why is kolu slow", "debug…