1,731 件 ・ 関連度順
概要と使いどころ
Enter talk mode — conversation and research, no repo changes. ONLY invoke when the user explicitly types `/talk` or `$talk`; never auto-select from a natural-language question or design discussion.
日本語の概要は準備中です。原文の説明を表示しています。
Do a task end-to-end — implement, PR, CI loop, ship. ONLY invoke when the user explicitly types `/do` or `$do`; never auto-select from a natural-language request, even one that sounds like an end-to-end task.
日本語の概要は準備中です。原文の説明を表示しています。
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 named lanes or recipes (e.g. "run fmt and nix", "just the e2e lane", bare selectors like `fmt`/`nix`/`e2e`), or names a recipe by `<recipe>@<platform>`. This skill — not a repo's local `just ci` / `just <recipe>` — is how an odu-run request is served.
日本語の概要は準備中です。原文の説明を表示しています。
Modern, interactive alternative to `/do` — clarify intent up front, then take a task end-to-end with a serial AI review gauntlet (lens debate (lowy ⇄ hickey) → codex debate → simplify → code-police, each editing the branch in turn) → CI → evidence. ONLY invoke when the user explicitly types `/be` or `$be`; never auto-select from a natural-language request.
日本語の概要は準備中です。原文の説明を表示しています。
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 where a defect "relocates" across review rounds. Grounds every claim in the diff, fans out adversarial verifiers via Workflow, and reports residual surfaces with a structural fix for each. ONLY invoke when the user explicitly asks for a perfection / ideal-bar review.
日本語の概要は準備中です。原文の説明を表示しています。
Diagnostic-only skill for Slurm scheduler and node-daemon issues on Amazon SageMaker HyperPod Slurm clusters. Scope mirrors the HyperPod troubleshooting guide. Invoke when the user reports a Slurm node stuck in down/drain, "Node unexpectedly rebooted" after auto-repair, slurmd not running, jobs stuck PENDING with REASON=Resources while sinfo shows idle nodes, jobs stuck COMPLETING after node replacement, GRES/GPU counts wrong, scontrol ping failing, slurmctld unresponsive, an Action:Reboot/Replace request that did not trigger HyperPod auto-recovery, or auto-resume not restarting a job. Also triggers on "drain before reboot", "diagnose a Slurm node", "investigate stuck jobs."
日本語の概要は準備中です。原文の説明を表示しています。
Initialize a PM Brain — a markdown-native second brain for a product operator (PM, product lead, founder, or anyone accountable for one product or initiative) doing judgment-heavy work with scattered inputs. Detects greenfield vs. migration mode, runs a focused interview, copies the deterministic scaffold into the working directory, populates placeholders from interview answers, runs a self-test, and commits. Use when invoked via `/pm-brain` or when the user asks to set up a PM Brain.
日本語の概要は準備中です。原文の説明を表示しています。
Automatic final verification pass on completed deliverables. Runs at the end of every fable-mode run — those skills invoke it before delivery. Also triggers when the user says "double check this". Uses a panel of fresh checker agents when spawning is authorized (otherwise a cold self-check) to verify the finished output — not to redo the task. Any FAIL gets fixed and re-checked before delivery.
日本語の概要は準備中です。原文の説明を表示しています。
Run fable-mode execution discipline on Claude Sonnet. When invoked by slash command or by name, spawns a Sonnet subagent that follows the staged loop — stage plan, parallel delegation, a failable verification check at each stage, and a skeptical self-review before delivery; a wording-only request runs the loop inline on the current model. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on Sonnet.
日本語の概要は準備中です。原文の説明を表示しています。
Guide to analyze a current work session and propose improvements to skills. Use (1) automatically after working with a skill to capture learnings, (2) when the user suggests improvements, corrections, or additions during a skill-related session, or (3) when the user manually invokes `self-improve`.
日本語の概要は準備中です。原文の説明を表示しています。
Generate a spreadsheet of test entries — newly designated names from OFAC, OFSI, and EU sanctions lists plus deliberate variations of those names — to validate that a sanctions screening system catches fresh designations and is tuned to the right fuzziness threshold. Use this whenever the user asks for sanctions list update test data, screening regression test data, screening QA, fuzzy match calibration, or wants to verify their screening lists are current. Trigger even if the user doesn't say 'screening' explicitly — phrases like 'test my sanctions list', 'check our SDN coverage', 'is my list up to date', or 'build me a regression set from the latest designations' should also invoke this skill.
日本語の概要は準備中です。原文の説明を表示しています。
Start (or restart) a local Temps control plane built from this checkout, and the web dev server (`bun dev`) in `<checkout>/web`. Invoke when the user says "start temps", "restart temps", "launch the server", "kill and restart temps", or asks to bring the local server up after backend changes. Ports, database and data dir are allocated PER CHECKOUT (a "slot") so several worktrees/branches run side by side without killing each other or corrupting each other's schema — the first checkout you start in claims slot 0 (the familiar `:8080` / `:3000`); every other worktree gets its own slot and its own `temps_s<N>` database. Uses the `fast` cargo profile (release semantics, no debug symbols, parallel codegen) for quick rebuilds. Pass `split` (e.g. "start temps split", "/start-temps split") to launch the two-process proxy/console topology for testing that feature.
日本語の概要は準備中です。原文の説明を表示しています。
Start (or restart) a local multi-node Temps cluster using Docker-in-Docker — one control plane + 3 worker nodes, each a privileged DinD container running its own dockerd + `temps agent`, wired with the real multi-host overlay (VXLAN, compute_cidr allocation) via `tools/dev-cluster/` in whichever checkout/worktree you run it from. Invoke when the user says "start the temps cluster", "spin up a multi-node dev cluster", "test this with multiple workers", "bring up worker nodes locally", "docker in dind cluster", or wants to verify cross-node behavior (node targeting, cluster DNS, overlay networking, node join/mTLS) that a single-node `start-temps` server cannot exercise. Distinct from `start-temps` (single-node, native binary, port-slot based) and `start-temps-ee` (single-node EE binary) — this is the only path that actually has more than one node.
日本語の概要は準備中です。原文の説明を表示しています。
Analyze the current session and propose improvements to skills. **Proactively invoke this skill** when you notice user corrections after skill usage, or at the end of skill-heavy sessions. Also use when user says "reflect", "improve skill", or "learn from this".
日本語の概要は準備中です。原文の説明を表示しています。
Generic PowerPoint authoring skill for A-share investment analysis and pitch decks. Creates professional 路演PPT / 投资分析PPT for any A-share company using live data from iFind MCP (Tier-1) and AkShare MCP (Tier-2 fallback) tools. All company-specific values are parameterized — never hardcoded. Triggers on "A股PPT制作", "投资PPT", "制作PPT", "路演PPT", "pitch deck", "PowerPoint [company/ticker]", or any request to create slides for a Chinese stock. When invoked, use the `generate_a_share_ppt` script with --company and --ticker args.
日本語の概要は準備中です。原文の説明を表示しています。
Codex-only — use when the user asks to run claude-smart commands in Codex, including claude-smart show, learn, restart, dashboard, clear-all, or slash-like requests such as /claude-smart:learn. In Claude Code the native plugin slash commands handle these; do not invoke this skill there.
日本語の概要は準備中です。原文の説明を表示しています。
Read and refresh wp-rocket's pre-built dependency graph at .claude/graph/dependency-graph.json. Use to locate a class file, trace dependencies, find the ServiceProvider that wires a service, or enumerate Subscribers in a module — without re-scanning the codebase from scratch. This skill is primarily a reader: the graph is built (and incrementally refreshed) by `node bin/build-knowledge-graph.js`. Invoke this skill at session start (to refresh if stale) and before grep/glob searches for class relationships.
日本語の概要は準備中です。原文の説明を表示しています。
Lead substantial Codex builds with one configured implementation worker and lead acceptance. Use when the user requests codex-on-crack, names a model to delegate work to, asks to run subagents through Claude, or requests a lead/worker split. Keep host-only work direct; honor explicit external model choices. Workers must not invoke this orchestrator.
日本語の概要は準備中です。原文の説明を表示しています。
Plan and execute substantial multi-file builds, features, migrations, and refactors with Astra as orchestrator and DeepSeek V4.1 Flash as the native Codex implementation worker. Use for phased planning and delegated build execution, including existing Superpowers or GSD plans. Skip trivial edits and explicitly single-agent tasks. Worker children must not invoke this orchestration skill.
日本語の概要は準備中です。原文の説明を表示しています。
One sentence that describes WHEN to invoke this skill. Write it as a trigger phrase, not a summary — include the words a user would say ("fix bug", "add feature", "review diff"). The agent routes on this field.
日本語の概要は準備中です。原文の説明を表示しています。
Review a diff against the goal spec assuming the code is BROKEN. The reviewer that lives in the maker's head always agrees with itself — this pulls review into a hostile, separate pass. Invoke after every code change before marking work done.
日本語の概要は準備中です。原文の説明を表示しています。
Use when the user mentions the Higgsfield CLI (binaries `higgsfield` / `higgs` / `hf`, `higgsfield auth login`, `higgsfield generate create`, `higgsfield workflow`, the `@higgsfield/cli` npm package), the Higgsfield MCP custom connector (`mcp.higgsfield.ai/mcp`) or its bundled workflows (`get_workflow_instructions` — character-sheet, thumbnail-generation, ugc-* videos, faceless-video, narrator, subtitles, product-photoshoot, brand-asset-creation, ad-multiplier, video-editing / Higgsedit, website-builder-flow), Higgsfield's bundled skills repo (`higgsfield-ai/skills` — `higgsfield-generate`, `higgsfield-soul-id`, `higgsfield-product-photoshoot`, `higgsfield-brandkit`, `higgsfield-marketplace-cards`, `higgsfield-websites`, `higgsfield-video-explainer`, `higgsfield-youtube-thumbnail`, invoked as `/higgsfield:generate` etc.), or asks how this skill coexists with those tools (`do I need both`, `how does this work with the CLI/MCP/skills`, `should Higgsfield's workflow do this or you`).
日本語の概要は準備中です。原文の説明を表示しています。
Audit and tend to existing travel reservations. Reads a user-provided reservations file, then systematically checks every booking for price drops, better cabin availability, improved routings, schedule changes, nearby airport alternatives, and award repricing opportunities. Invoke proactively on a regular cadence or when the user says "garden", "check my bookings", "audit reservations", "price drop", "better routing", "did my flight change", "tend reservations", "reservation maintenance", or "check my trips".
日本語の概要は準備中です。原文の説明を表示しています。
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.
日本語の概要は準備中です。原文の説明を表示しています。