gotcontext-saddle

Use when continuing work from a previous AI coding-agent session, handoff transcript, chat log, exported conversation, saved artifact set, or session summary.

Use when the user asks for a 'full' or 'end-to-end' release driven by an architecture document — typically a multi-track release landing a substantial product slice (new product line, multi-surface refactor, feature bundle). Triggers: 'design a doc for this system, then plan it, then ship it', 'ultrathink this through to ship', 'do all 10 phases', 'architecture refresh', 'convergence loop the doc, then implement, then push', or any prompt naming 4+ sequential phases ending in push/merge. Meta-skill bundling writing-plans, a peer-review council / codex peer-review, subagent-driven-development, verification-before-completion, gh-release-ship-loop, and blog-post-template.

Use when the user wants to clone or adapt a UI pattern from any website into your app, or asks to "build something like X", "make our nav look like Y", or "clone that component". Requires an aura.build Pro subscription. Aura's clone is now NATIVE — paste a URL or drag a screenshot into aura.build and it generates React/Tailwind directly; the Anima/Chrome-extension flow is only a fallback for login-gated pages Aura can't fetch.

Use when a task is too big for a handful of subagents or needs cross-verification — codebase audits, multi-file migrations, cross-checked research, plan-from-N-angles, multi-source sweeps. Codifies the built-in Workflow tool (dynamic workflows), the authoring API, quality patterns, the framework-decision rule, what to download, and this project's reusable templates + house constraints.

Use when starting or restructuring any software project in ANY language — deciding folder/module layout, dependency direction, public API boundaries, where logic vs entrypoint lives, the testing tiers, smoke tests, or CI gates — when no language-specific architecture skill applies. Language-agnostic parent of typescript-cli-architecture and rust-workspace-architecture. Triggers — "how should I structure this", "where does this file/module go", "feature vs layer", "set up tests and CI", "smoke test", "new package or module?", "structure my Go/Python project", "project layout for <language>".

Use when writing or auditing any blog post on your product's site (new post or existing). Enforces the BlogPostLayout container contract AND a Tier-1/Tier-2 anti-AI-slop checklist derived from 15-source Exa research (2026-05-14). Both checks are mandatory before any blog post merges.

Use when an agent's response/formatting logic is (or will be) reachable from more than one delivery channel (chat, SMS, email, push, web). Triggers — before adding a second channel to a single-channel agent, before writing/editing a shared respond()/format_reply()/persona-selection helper, or when a multi-channel agent's voice output sounds like it was written for text (spelled digits, markdown symbols read aloud).

Use when the user asks "what did we decide about X", "find the session where we discussed Y", "when did we first hit Z bug", "what was the rationale behind W", or any question that needs answers retrieved from prior Claude Code sessions across all projects. Also use proactively when the current session needs context that predates the loaded conversation thread — chat sessions are a queryable backup to long-term memory, and they hold reasoning traces (rejected alternatives, partial understandings, the why) that curated MEMORY.md / project_*.md entries don't capture. Searches the global ~/.claude/projects/*/*.jsonl archive via ripgrep + Python turn-pair extraction. NOT for current state queries (pod status, build status — read those directly), NOT for future plans (read paper §14 work queue or CLAUDE.md), NOT for questions already answered by MEMORY.md (check that first).

Use AFTER a Claude-Design export exists and BEFORE the render-verify step — the discipline for adapting an export into a production page with real data, honest empty states, and existing tokens/components (never shipping mock numbers).

Use when generating, prototyping, or iterating on UI designs (prototypes, wireframes, slide decks, landing/dashboard mockups) with Anthropic's Claude Design tool at claude.ai/design — particularly when you want a design system applied automatically and a clean handoff into Claude Code for implementation.

Use when asked to investigate, deep-dive, audit, review, or assess a codebase/repo/project for bugs, issues, security gaps, infrastructure risks, optimization opportunities, or unwired/dead/partially-implemented code. Triggers on "investigate the X codebase", "audit/review the repo", "find bugs/security issues", "what's broken/risky in X", "dead code", "infra risks", "deep-dive the code". READ-ONLY: produces a structured report, makes NO edits. This is the code/security/infra analog of frontend-audit (which is visual-only).

Use when about to call AskUserQuestion, write "want me to..." / "should I..." / "your call", draft an A/B/C/D option tree, or type a soft hedge ("worth doing...", "...or hold?", "no need to wait", "I'll just fire it" as a preface). Also use when a paid resource is idle/crashed, or when about to end a turn on a question instead of an action.

Use when about to spawn Agent/Workflow subagents, fan out parallel work, or pick a model for delegated work — especially before any multi-agent fan-out, or whenever a task might run on a cheaper model tier than the default.

Use when building any fire-and-forget async delivery or dispatch (send a message, notify, post, trigger a pipeline, enqueue a task) that must survive a process crash or restart — or when a delivery "succeeded" in-session but never arrived.

Use when sending markdown/rich-text formatted messages through a strict wire-format channel API (Telegram, Slack, Discord, SMS/WhatsApp). Triggers — hardening a bot reply path, a message that "sometimes doesn't arrive", or literal *asterisks*/backticks showing in delivered messages. On any parse/entity 4xx, retry with a degraded payload so a malformed render never silently drops a reply on a critical notification channel.

Use when changing LOAD-BEARING code (a transport/driver path, a money-path or safety gate, the eval runner, a reload/merge contract, a release script) with help from subagents — ESPECIALLY when the working tree is concurrently dirty with another agent's in-flight lanes so worktree isolation cannot protect the human-owned mainline. Triggers on "have a subagent fix the transport/driver/money-path", "multi-gap hardening of one file", "an agent edit broke a contract test in another file", "a concurrent-agent git-add swept my change", "apply-then-verify the agent's patch", or any time an agent EDIT would be a hypothesis you must not land blind. NOT for greenfield/throwaway code or large parallel refactors with no shared mainline — those want worktree-isolated editor agents instead.

Use when going from "I want a beautiful page/section/component" to shipped React in <web-app>/src/ — picking a design engine (claude.ai/design vs aura.build vs Figma), wiring the generate → assets → build → audit → ship pipeline, or deciding which generate-path fits ("build a new page", "make our nav look like X", "clone this site", "get my Claude Design mockup into Figma", "this UI looks like AI slop"). Router/meta-skill that bundles the existing UI/UX skills; it selects + sequences them, it does not redefine them.

Use AFTER publishing any CLI, tool, or service package — and BEFORE declaring a release good. Triggers on: 'release shipped', 'published to PyPI/npm', 'v1.X.Y is live', 'the tests all pass', 'CliRunner passes', 'TestClient passes'. Never trust an in-process test runner as proof the REAL shipped binary works: CliRunner (Click/Typer) and FastAPI TestClient invoke the app object DIRECTLY, bypassing the entry-point / front-door bootstrap layer. Install the PUBLISHED artifact in a clean env (Docker or fresh venv) and invoke the REAL binary across every feature flag combination before declaring the release good.

Use when the user asks to audit, review, critique, or "make sure it looks right" on a deployed web page, component, or Figma mockup — or when they mention visual issues, CRO, conversion rate, design consistency, accessibility, "feels off", "looks bad", "make it pop", "looks like AI slop". Triggers on keywords like "audit the page", "review the design", "what's wrong with this UI", "CRO audit", "a11y check", "visual hierarchy", "typography check", "does this look right". Activation also recommended after any significant frontend change on your product's site before calling the work done.

Use whenever shipping a release on any GitHub-backed project with a CI + main-branch-merge pattern (Vercel, Fly, Render, Cloudflare Workers, or just GH Actions deploying somewhere). Encodes the 10-phase loop validated end-to-end on a multi-hop production ship train (several sequential hotfixes on the same feature) — the failure modes captured here cost real session time and CI cycles. Triggers on intent phrases — "ship a release", "push to main", "merge this PR", "deploy this", "release v1.X.Y", "hotfix", "rebase onto main and merge", "ship train", "land this fix in production", "open + merge a PR".

Use when an agent will name a domain entity it does not control — a repo, channel, tool, agent, skill, model alias, team — and act on it; or when an agent reports an action on an entity that may not exist.

Use when you need to prompt AI for UI like Meng To: design-first, spec-driven, skimmable. Covers prompt structure, constraints, variations, typography/spacing rules, and iteration workflow for consistent UI outputs.

Drive a public web surface from baseline to ≥9.5/10 via iterated 3-seat thinktank council rounds. Each round: read verdicts → pick #1 highest-leverage actionable fix → ship → dispatch next round. Validated on 3 pages (news 9.77, benchmarks 8.0 stopped, knowledge-hub 9.73). Default: delegate to a general-purpose subagent.

Use when deciding whether to BUILD or DEFER a researched feature pre-revenue — the demand-signal-over-stated-interest, set-threshold-first, prereq-chain, written-defer-brief discipline (the build-now-vs-defer axis, distinct from an act-vs-ask common-sense-gate axis).

Use when creating, structuring, or adding a crate/module to a Rust Cargo workspace (CLI, agent, or backend) — deciding workspace layout, when to make a new crate vs a module, dependency direction, error types, where tests live, snapshot/property tests, the test runner (nextest), smoke tests, clippy/rustfmt gates, or CI. Triggers — "new crate or module?", "set up the workspace", "where do integration tests go", "insta snapshot", "cargo nextest", "smoke test the binary", "thiserror vs anyhow", "workspace.dependencies".

The 8-phase standard development pipeline locked-in by user 2026-05-24. Use WHEN starting any non-trivial implementation, planning, research, or debug task. Triggers on intent phrases — "let's build X", "implement X", "design X", "plan X", "research X", "fix this bug", "debug Y". The 8 phases (in order): (1) rewrite the task into a well-scoped spec with Opus, (2) Opus plans using superpowers + lists relevant skills, (3) current web research + Gemini + Opus update the plan, (4) a peer-review council flags conflicts → update plan, (5) codex (preferred) or cursor (long/wiring jobs, unlimited tokens until Sept 2026) implements, (6) Opus + Sonnet review codex work via a code-review skill, (7) Gemini for architecture/deep-research review when needed, (8) Debug = Opus + codex pair. Use sub-agents wherever possible to conserve main-session context.

Use BEFORE writing any code that extracts an archive, downloads a binary/wheel/tarball, installs a dependency or tool, self-upgrades a running binary, or bootstraps a toolchain (rustup/uv/mise). Triggers on: 'extract a zip/tar', 'extractall', 'download the release asset', 'self-update/auto-upgrade helper', 'install script', 'pin the dependency', 'cargo/npm/pip install in CI', 'bootstrap the toolchain'. Encodes 6 production-shipped, citation-backed hardening checks: zip-slip guard before extractall; time-bound + byte-capped downloads; checksum-gated FAIL-CLOSED installs (incl. detached self-upgrade helpers, verify before os.replace); --locked + exact version pins for CI tools; fail-closed-with-explicit-opt-in for unverified toolchains; committed-checksum for platform installers whose native bootstrap skips binary verification (uv .ps1/.sh). Apply BEFORE writing the code, not after.

Use when authoring or hardening an agent's system prompt, persona, or tool descriptions — the non-obvious safety-floor, anti-bluff, and tool-description patterns a generic safety section misses.

Use tensor-grep (tg) as the default code-audit path — callers/blast-radius/scan/doctor/map for fast AST-aware impact analysis before touching shared code. Carries the per-version CLI-contract re-verify rule.

Use when building or running an agent eval, CUJ score, benchmark, or automated-improvement loop — and especially when a whole lane fails uniformly, a score looks too good or too bad to be true, you're about to trust a new grader/oracle/judge, or a scored harness invokes pnpm / npm / tsc / any .cmd subprocess on Windows. Symptoms: "the agent can't do X" reads as a capability gap, exit-127 / exit 127, a lane scores 0% or 100%, judge and oracle scores blended into one number, write-only-at-end eval crashed and lost work, ≥2 different failure modes on one harness, hill-climbing against a contaminated signal. Keywords: oracle, grader, LLM-as-judge, position bias, Cohen kappa, sealed holdout, decontamination, SNR, MDE, noise floor, checkpoint, status.jsonl, broken oracle, reward hacking, blind relaunch.

Use when creating, structuring, or adding a feature to a TypeScript/Node/Bun CLI, agent, or backend project — deciding folder layout, where a new tool/command/module goes, naming, module boundaries, the test framework (Vitest), where tests live, smoke tests, or CI gates. Triggers — "where should this file go", "new feature folder", "set up tests", "vitest config", "smoke test the CLI", "structure this TS project", "feature vs layer folders".

Use when fixing, auditing, improving, or building ANY web UI — before reading or editing component code. Fires on contrast/a11y/overflow/responsive/hover-focus/layout complaints, "polish the UI", "audit the page/site", "make it premium", or any visual change (including a local authed dashboard).

Full deep-dive audit loop — bugs, edge cases, backlog, current competitive web research, TDD fix waves, council-reviewed plans, re-audit until clean. Use for ultrathink mandates, /deep-dive, security audits, complete backlog, competitive analysis. Routes orchestrator by provider (Claude Opus vs Fable, Codex gpt-5.5, Cursor Auto vs Opus, agy Gemini 3.5/3.1). Spawns workflows + subagents; a peer-review council audits plans.

Use when driving Chrome for navigation, form-filling, scraping, or front-end debugging via the chrome-devtools CDP MCP — especially when you need DOM/accessibility-tree access instead of screenshots, or when the official Claude-in-Chrome extension is unavailable because the CLI is on a different Claude account.

Use when an agent (Claude Code main session, cursor-agent, codex-cli, or gemini-cli) needs to drive a real Chrome browser via the claude-in-chrome MCP server — for live UI verification, OAuth flows, dashboard captures, paid-ad screenshots, OAuth secret rotation (e.g., Resend / Polar / Clerk dashboards), competitor recon, or any task that needs to interact with an authenticated web product the user is logged into. Inherits the user's Chrome session (cookies, OAuth, MFA-passed) — does NOT prompt for new logins. Sibling of `use-gemini` and other CLI-delegation skills.

Use when delegating bounded coding, audit, or review work to codex-cli (OpenAI Codex) for an independent SECOND-OPINION pass that doesn't share Claude's blind spots, or to conserve Claude tokens on heavy content-writing. Codex picker (2026-07-01): gpt-5.5 (frontier/current default), gpt-5.4, gpt-5.4-mini, gpt-5.3-codex-spark (ultra-fast); gpt-5.3-codex and gpt-5.2 dropped from picker. Spec-driven, diff-first audit pattern — best for peer review of non-trivial diffs (money/auth/webhooks/migrations), bulk audits, multi-file content writes to spec. Skip for small edits or live step-through debugging. Sibling skill of use-cursor.

Use when delegating bounded coding, audit, or review work to GitHub Copilot CLI. Copilot's edge is GitHub-native MCP integration (issues, PRs, code search) on a GitHub Copilot subscription with no separate billing. Sibling skill of use-codex / use-gemini / use-cursor / use-droid.

Use when delegating bounded coding work to cursor-agent (in WSL, auto-mode, unlimited tokens) to conserve Claude tokens for orchestration + audit — multi-file edits over an explicit task spec where the work is bounded, auditable diff-first, and an Agent-tool subagent's tokens would otherwise be wasted on writing-out-content.

Use when delegating bounded coding, audit, multi-agent mission, or review work to Factory's Droid CLI (droid exec, --mission mode with worker+validator subagent orchestration). Droid runs Claude Opus 4.8 by default (also carries Fable 5, Sonnet 5, GLM-5.2, Kimi K2.7, MiniMax M3, nemotron-3-ultra) on one Factory subscription across Anthropic/OpenAI/Google. Sibling skill of use-codex / use-gemini / use-cursor / use-copilot. Invoke from PowerShell (droid.ps1), NOT WSL — WSL's droid lacks auth (FACTORY_API_KEY error). Use -m to switch model, --cwd (Windows path) for target dir, -w/--worktree for isolated edits, -r/--resume or --fork for session memory. NOT for small targeted edits or live mid-flight debugging.

Use when delegating bounded coding, audit, or review work to Antigravity CLI (agy binary, post-2026-06-18 successor to gemini-cli) for a THIRD-OPINION pass alongside Claude + codex (3-way cross-validation), OR when work needs Gemini 3.1 Pro reasoning OR Gemini 3.5 Flash speed. Native Windows + WSL tmux wrapper for headless dispatch. Sibling skill of the other CLI-delegation skills.