ワンクリックで
ask-ben
Router for Ben's frontend-skills harness and every local skill.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Router for Ben's frontend-skills harness and every local skill.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Evidence-backed Go review for bounds, APIs, concurrency, errors, security, tests, rollout, and controllers. Use when reviewing a Go diff, PR, or branch, or as the golang hat /review adds when the diff touches *.go, go.mod, or backend protos.
Evidence-backed Go conventions for workload bounds, error boundaries, proto/API implementation, Temporal, testing, rollout, and controllers. Use when writing or changing Go services, handlers, workflows, controllers, or Go tests.
Evidence-backed Go review for bounds, APIs, concurrency, errors, security, tests, rollout, and controllers. Use when reviewing a Go diff, PR, or branch, or as the golang hat /review adds when the diff touches *.go, go.mod, or backend protos.
Evidence-backed Go conventions for workload bounds, error boundaries, proto/API implementation, Temporal, testing, rollout, and controllers. Use when writing or changing Go services, handlers, workflows, controllers, or Go tests.
Reviews a diff with a 7-hat parallel panel -- product/spec, standards, complexity, adversarial, resilience, visual/design, test/perf -- plus a mandatory cross-family GPT hat. Use when reviewing a branch, PR, WIP, or a release audit (deep mode).
Bootstrap the frontend stack -- toolchain, lint, quality gates, React/router/data enforcement, CI -- from lazy per-tool profiles.
| name | ask-ben |
| description | Router for Ben's frontend-skills harness and every local skill. |
| disable-model-invocation | true |
Use this when you forget which local skill fits Ben's work. Default: ship frontend/React/TypeScript/Go changes and skills repo releases with enforced TDD, review, resilience, visual proof, PR, CI, and installable plugin surfaces.
Routes: product -> /development-lifecycle//work -> /go; bugs -> /diagnosing-bugs + /tdd; planning -> /grilling; huge, foggy work -> /wayfinder -> /to-spec; specs -> /to-spec -> /to-tickets; review -> /review (add --deep for release audits); UI/resilience -> /visual-review//resilience-review; parallel -> /swarm.
Builder.io skills are both direct commands and under-the-hood helpers: /visual-plan, /visual-recap, /agent-watchdog, /efficient-frontier, /plan-arbiter, /plow-ahead, /read-the-damn-docs.
| Skill | Use for |
|---|---|
/accessibility | React accessibility patterns -- ARIA labels, keyboard handlers, widget attributes, nested-pressable fixes,... |
/agent-watchdog | Use when asked to watch, audit, compare, or fix another agent's work from a Codex/Claude session, transcrip... |
/aip | Designs Google AIP-style protobuf resource APIs. |
/ask-ben | Router for Ben's frontend-skills harness and every local skill. |
/codebase-design | Shared vocabulary for designing deep modules. |
/codex-compat | Generate Codex hooks.json and AGENTS.md parity surfaces from the Claude hook manifest. |
/codex | Delegate work to GPT-5.6 via the codex CLI -- clear-spec implementation, independent review, computer use,... |
/commit-push-pr | Analyze changes, create categorized conventional commits, push, and open a PR. |
/connect-query | ConnectRPC + connect-query + Protobuf v2 patterns -- schema-first create(), typed transports, invalidation... |
/deslop | Write the least code that works and remove unjustified surface area. |
/development-lifecycle | Use when frontend/React/TypeScript/UI work. |
/diagnosing-bugs | Diagnosis loop for hard bugs and performance regressions. |
/domain-modeling | Build and sharpen a project's domain model. |
/e2e-testing | Playwright + Testcontainers + axe-core E2E patterns for forms, tables, and workflows. |
/efficient-frontier | Use when a frontier model (Fable, Opus, GPT-5.6) should delegate bounded research, coding, testing, or log... |
/extend-harness | Extend the frontend-skills hook harness: add rules, tune severity tiers, view analytics, debug non-firing h... |
/frontend-starter-kit | Bootstrap the frontend stack -- toolchain, lint, quality gates, React/router/data enforcement, CI -- from l... |
/go | Ship what built. |
/golang-review | Evidence-backed Go review for bounds, APIs, concurrency, errors, security, tests, rollout, and controllers. |
/golang | Evidence-backed Go conventions for workload bounds, error boundaries, proto/API implementation, Temporal, t... |
/grilling | Explore options, then interview the user relentlessly about a plan, decision, or idea, with a 3-hat plan ga... |
/handoff | Compact the current session into a handoff document for another agent or fresh session. |
/hook-audit | Analyze hook effectiveness + session retro from collected metrics. |
/improve | Surveys a codebase as a senior advisor and writes implementation plans. |
/make-pr-easy-to-review | Clean noisy PR history and add reviewer guidance without changing code behavior. |
/plan-arbiter | Use when comparing, cross-reviewing, merging, judging, choosing, or arbitrating competing plans from agents... |
/plow-ahead | Use when the user says plow ahead, do not stop, use your best judgment, keep going until done, or similar. |
/prime | Builds repo startup brief. |
/prototype | Build a throwaway prototype to answer a design question. |
/read-the-damn-docs | Use for third-party APIs, libraries, frameworks, CLIs, cloud services, SDKs, fast-moving behavior, current/... |
/redpanda-ai-gateway | Run AI CLIs (claude, codex) through the Redpanda AI Gateway via rpk ai -- auth, environments, providers, ga... |
/registry-workflow | Component registry maintenance -- taxonomy, consumer drift analysis, sync discipline. |
/research | Investigate a question against high-trust primary sources and capture the findings as a Markdown file in th... |
/resilience-review | Murphy-law hat panel for unhappy paths -- input, timing, system, state, UX-recovery hats probe a change in... |
/resolve-pr-feedback | Resolve PR review feedback by fetching unresolved threads, triaging, fixing in parallel, and replying. |
/resolving-merge-conflicts | Use when you need to resolve an in-progress git merge/rebase conflict. |
/revamp | Run a large rewrite, port, or migration using the Bun-in-Rust playbook -- baselines, mechanical-first trans... |
/review | Reviews a diff with a 7-hat parallel panel -- product/spec, standards, complexity, adversarial, resilience,... |
/setup-atlassian-workflow | Opt-in Atlassian/Jira integration via acli -- create work items, transition status, comment, link PRs. |
/setup-routines | Configure Claude Code routines -- automated PR review, codebase health, issue triage, docs drift -- on Anth... |
/snyk-ux-security | Snyk dependency sweeps across frontend, Go, and Bazel paths with npm false-positive triage and release-age... |
/stay-within-limits | Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage... |
/steelman | Argue the strongest evidence-backed case against a premise. |
/swarm | Parallel executor for independent bulk work across worktree lanes. |
/tanstack-router | TanStack Router patterns -- Router-loader vs Query-cache ownership, typed search params, route tree generat... |
/tdd | Test-driven development with red-green-refactor loop. |
/teach | Teach the user a new skill or concept within this workspace. |
/thermo-nuclear-code-quality-review | Alias for /review --deep -- release-blocking cold PR audit. |
/to-spec | Turn the current conversation into a spec and publish it to the project issue tracker -- no interview, just... |
/to-tickets | Break a plan, spec, or the current conversation into tracer-bullet tickets with blocking edges, published a... |
/triage | Move issues through triage roles and prepare agent-ready work. |
/upgrade-dependency | Upgrade a dependency AND adapt the code to it in one pass -- bump, codemods, call-site migration, new-API a... |
/ux-copy | UX text style for UI strings and prose -- sentence case, action labels, banned phrases, inclusive language,... |
/visual-plan | Turn text plans into interactive Agent-Native visual plans with diagrams, file maps, annotated code, questi... |
/visual-recap | Turn a PR, branch, commit, or diff into an interactive Agent-Native visual recap with diagrams, file maps,... |
/visual-review | Reviews customer-facing surfaces with product, design, engineering, and QA hats from visual evidence. |
/wayfinder | Plan huge work that cannot fit in one agent session as a shared issue-tracker map, then resolve decision ti... |
/what-did-i-get-done | Summarize authored git commits over a time period into a concise status update. |
/wizard | Generate an interactive bash wizard that walks a human through a manual procedure -- third-party setup, a o... |
/work-automation-kit | Install planning/PM workflows: specs, ticket breakdown, tracker docs, triage. |
/work | Alias for /development-lifecycle. |
/writing-beats | Build article beat by beat from raw material with user-chosen pivots. |
/writing-fragments | Mine user conversation into raw writing fragments in one markdown file. |
/writing-great-skills | Reference for writing and editing predictable skills. |
/writing-shape | Shape raw markdown material into an article through conversational drafting. |