Results for “drift-checks”

Detects drift between declared reality (docs, manifests, inventories, ADRs) and actual reality (filesystem, git state, dependencies, hooks) on session start, reporting findings with severity and evidence.

Validates that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after deploying a disagg or multi-node recipe to confirm KV transport is correct, or use troubleshoot for already-failed pods.

Detect unauthorized modifications to running containers by monitoring for binary execution drift, file system changes, and configuration deviations from the original container image.

スキル定義（SKILL.md）を静的点検・ドライランで検証するスキル。 `--all` で全スキル一括健全性監査モード（ランキング＋修正案ドラフト生成）。 「スキルを点検して」「スキルをテストして」「スキルのバグ確認」「スキル検証」 「全部のスキルを点検して」「一括点検」または /skill-test を呼び出した時にトリガー。

Automates repeated rounds of Copilot code review on GitHub pull requests: triggers review, triages threads, dispatches parallel fix agents, commits, replies, and loops until convergence.

Verify work before committing, pushing, or requesting review

Checks desktop, tablet, and mobile UI for overflow, clipping, navigation, grid, canvas, and breakpoint regressions.

开发前 Git 前置检查 — 防多 AI 并行开发冲突。每次改代码前先 fetch + diff 检查远端是否有新提交。

Reviews and repairs risky or unclear code with minimal validated changes, running a fixed-point loop until the diff is clean across two consecutive review cycles.

Re-derive your knowledge system from first principles when structural drift accumulates. Analyzes dimension incoherence, vocabulary mismatch, boundary dissolution, and template divergence. Preserves all content while restructuring architecture.

Verifica que una implementación cumpla los specs del ciclo SDD ejecutando tests reales, revisando cobertura y emitiendo un veredicto de aprobación o rechazo.

Check post-launch traction for a shipped VARD app and recommend iterate, graduate, or archive

Use when a commit's changes are finished and about to be presented for review. Runs the checks that catch the objections the user would otherwise raise, before they spend time reviewing.

Close the PDCA loop on this session's diff. Headed playwright-cli, fix as you go. Use when "test my changes", "PDCA this". Pixel diffs → test-visual-regression. Story CRUD → test-qa. Monkey / guest vs logged-in → test-exploratory.

PR Fleet

Check pinned external tool versions against npm and GitHub releases. Use for the weekly heartbeat tool-pin drift scan.

Diagnose and validate cron expressions before they ship, catching impossible dates, OR-semantics, midnight spikes, uneven step drift, and leap-year February 29.

Runs project tests, stages and commits changes with a conventional message, then rebases and pushes to the current branch, stopping on any failure.

Clade coverage-driven project review — walks every VERIFY.md checkpoint, fixes failures in-session, converges when all checkpoints pass. NOT the Claude Code built-in /review (which reviews a single pull request diff) — if the user wants a PR review, route to /review-pr (Clade's PR reviewer) or the CC built-in.

Pre-landing PR review. (gstack)