grok-build-orchestrator
Use when delegating on Grok Build via spawn_subagent: pick the child by task type and complexity from the live schema and brief it as the mission. Not peer sessions or other CLIs.
38,472 Skills
Search uses this published catalog; rankings and counts are snapshots.
Use when delegating on Grok Build via spawn_subagent: pick the child by task type and complexity from the live schema and brief it as the mission. Not peer sessions or other CLIs.
Use when delegating on Kimi Code CLI: pick the child from its native agent files by task type and complexity, brief it as the mission. Not another runtime's orchestrator, a peer session or another CLI.
Use when changing code with no trusted tests (characterize, cut the smallest seam, red then green). Trusted tests -> refactoring-catalog. New code -> tdd. Unknown cause -> diagnosing-bugs.
Use when an engineering trade-off needs a choice: simplest thing, reversibility, tracer bullet or prototype, DRY, broken windows, estimate uncertainty, \"is this over-engineered?\". Slicing a story -> xp-agile-delivery.
Use when code has real duplication, confusing intent or excess coupling and trusted behavioral tests exist. Gives small safe moves (extract, rename, move), green throughout. No trusted tests -> legacy-code-change.
Use when adding/changing a test or auditing/pruning low-value, implementation-coupled or duplicate tests. Not red-green -> tdd. Not layer choice -> layered-testing-executor. Untested code to change -> legacy-code-change.
Use when writing, fixing or de-flaking a Playwright/e2e browser test: fixtures, locators, waits, user-visible assertions. Not the pre-delivery UI pass.
Apply input minimisation, output discipline, and a human-in-the-loop gate to every surface that sends data to an LLM. Triggers when building or editing any send-to-LLM path: an Edge Function calling a model, a draft-commentary or summary generator, an auto-resolver, a cash-alloca
The unit of change is the action or the fact, never the named list of places someone handed you. Before shipping a gate, constraint, rename, drop, or a correction to any duplicated, mirrored, or denormalised value, grep the whole repo — app, tests, seeds, scripts, open branches,
Keep a live, committed checkpoint log during any work unit expected to span multiple commits or sessions. Each commit ships with a short note in the log, what the commit did, the key decision and why, any deviation from plan; closing the unit requires an explicit walk of the chec
Run a three-lens committee review of a whole project or major subsystem: positive, adversarial, and neutral-chair reviewers over one shared evidence base, with attribution-stripped consolidation and item-by-item voting. Use when the user asks for a committee review, a multi-persp
Always ask explicitly before pushing to a remote or fast-forwarding a protected branch. Per-action authorisation, not standing approval. Triggers on any git push, merge, or branch fast-forward operation, regardless of whether previous pushes in the same session were approved.
Adversarially review a specific change, design, or finding by having Claude debate one or more INDEPENDENT AI agents (e.g. Gemini or GPT in Antigravity, several models at once) over a shared file relay, with mandatory file:line citations, live read-only evidence, and a converge-o
In a UTC server or serverless runtime, new Date("YYYY-MM-DD") is UTC midnight and renders as the previous day in western timezones. Parse date-only strings into explicit local components (new Date(y, m-1, d)) anywhere a date becomes a display string or a day-of-week. Triggers whe
Every database migration plan ships with a post-apply verification query that reads catalog state directly, separate from any runtime tests. Triggers on any work involving a database migration, schema change, RLS policy change, trigger change, or constraint change.
Three gates for AI-rewritten claims, owner-only facts, and machine-parsed output in any generated document. Claims: diff an AI rewrite claim by claim against the source — the original wins unless the owner confirms. Gaps: facts the generator does not hold render as loud allowlist
Catalog captured:2026-11-21