データ・AIのスキル

This skill should be used when analyzing weekly price charts for stocks, stock indices, cryptocurrencies, or forex pairs. Use this skill when the user provides chart images and requests technical analysis, trend identification, support/resistance levels, scenario planning, or probability assessments based purely on chart data without consideration of news or fundamental factors.

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。

Evaluates market bubble risk through quantitative data-driven analysis using the revised Minsky/Kindleberger framework v2.1. Prioritizes objective metrics (Put/Call, VIX, margin debt, breadth, IPO data) over subjective impressions. Features strict qualitative adjustment criteria with confirmation bias prevention. Supports practical investment decisions with mandatory data collection and mechanical scoring. Use when user asks about bubble risk, valuation concerns, or profit-taking timing.

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。

This skill should be used when analyzing sector and industry performance charts to assess market positioning and rotation patterns. Use this skill when the user provides performance chart images (1-week or 1-month timeframes) for sectors or industries and requests market cycle assessment, sector rotation analysis, or strategic positioning recommendations based on performance data. All analysis and output are conducted in English.

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 datasets and extract insights. Use when user needs to understand data patterns, statistics, or trends.

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 writing eBPF programs with libbpf, bpftrace, or Rust with aya-ebpf and aya-log, attaching kprobes, tracepoints, or XDP hooks, declaring maps, sharing data with a Tokio loader, triaging verifier or Aya load errors, or porting with CO-RE. Not for full kernel bypass: use dpdk.

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 profiling with Intel VTune or AMD uProf for hotspots, top-down pipeline stalls, memory-bound analysis, or roofline data. Not for raw perf stat counters: use linux-perf.

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 writing a GNU ld script for a bare-metal target, placing code in a flash or RAM region, wiring .data and .bss startup, or fixing a region overflowed error. Not for LTO: use linkers-lto.

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 turning perf, DTrace, pprof, or async-profiler stacks into an SVG flamegraph with the FlameGraph scripts, reading one, or diffing two profiles. Not for collecting data: use linux-perf.

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 explaining pipeline stages, data or control hazards, forwarding, stalls, or superscalar basics behind a counter reading. Not for mispredict cost: use branch-prediction-and-speculation.

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 writing reset-to-main startup code, vector tables, VTOR, .data/.bss init, stack setup, startup.s, or crt0 for Cortex-M/RISC-V. Not for the bootloader jump: use bootloaders-embedded.

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 a human-curated dbt model index must guide BigQuery SQL for a warehouse question. Not for discovering undocumented models or executing warehouse changes.

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 work reaches a session boundary or the user asks to hand off, delegate, or get a clipboard-ready prompt. Mode brief packages continuity; mode prompt builds the delegation prompt.

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 asks "where to help", "contribution opportunities", or "find a good first issue". Returns data-backed first steps. Not for PR review queues: use gh-review-requests.

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 bloated code needs clean re-derivation, or the user says "this module is bloated" or "break it and rebuild". Not for untracked data or changes without VCS rollback.

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 asked to remove old code, migrate consumers, or decide whether to maintain or sunset a system. Not for untracked data or changes without VCS rollback.

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。

Optimize a pydantic-ai agent's instructions, tool descriptions, output type, and signature inputs using the gepa CLI. Trigger when the user asks to "optimize this agent", "improve tool descriptions", iterate on prompts driven by eval failures, or otherwise improve a pydantic-ai agent against a dataset. Operates in the user's repo with full filesystem access — YOU are the reflection model; the gepa CLI handles minibatches, evaluation, and Pareto bookkeeping.

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。

Recover from stale RFDB nodes that survive `commit_batch` cleanup despite having their `file` field listed in `changed_files`. Use when: (1) re-running an enricher/orchestrator step but old data with the same file field stays in the graph, (2) `commit_batch(changed_files=[X], ...)` reports success but a query later still returns nodes with `file = X`, (3) you re-pointed structural nodes (e.g., DIRECTORY/FILE) from a synthetic file path to real file paths and the old synthetic-path nodes won't go away, (4) graph-stream / find_by_type returns a mix of "stale" and "new" nodes for the same logical entity. Root cause: `handle_commit_batch` calls `engine.find_by_attr({file: X})` to enumerate nodes-to-delete, but that query path returns only a PARTIAL set after compaction (L1 segments and the file→nodes index can desync). Workaround: enumerate stale nodes via the TS rfdb client `queryNodes({file: X})` (different code path that finds all of them) and call `deleteNode(id)` per node, then re-commit the intended state. Related: rfdb-manifest-l1-carryforward (same L1 family).

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。

Pattern for adding derived edge types in the Grafema Rust orchestrator (main.rs). Use when: (1) need to create new graph edges derived from existing edges (e.g., MODULE-level DEPENDS_ON from IMPORTS_FROM), (2) Datalog joins on large edge sets time out, (3) adding enrichment steps that combine data from multiple resolver outputs, (4) need to understand how resolver outputs flow through the orchestrator pipeline.

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。

Verify which process actually owns a TCP port before assuming your fresh restart succeeded. Use when: (1) you killed an old server and started a new one but behaviour matches the OLD code/data, (2) `pkill -f pattern` returned 0 but old behaviour persists, (3) you embedded a new asset/binary but the served version is stale, (4) any "I just restarted X but I'm getting old results" situation. `pkill -f` matches against the process command line — if the live old process was started with `--port 0` (auto-assigned) and got the port you now want, the pattern won't match it. Always verify with `lsof -i :PORT` before debugging deeper.

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。

Diagnose and fix RFDB data disappearing after compaction, where rfdb-server reports a tiny node count (e.g. "15 nodes") on startup despite manifest_index.json showing hundreds of thousands of nodes and segment files existing on disk. Use when: (1) rfdb-server logs "Default database: N nodes" with N orders of magnitude smaller than recent analysis output, (2) /api/stats returns only the most recent commit's nodes, (3) the issue appears AFTER a compaction event (manifest with l1_node_segments populated and node_segments: []), (4) subsequent commits dropped L1 references. Root cause: ManifestStore::create_manifest() initializes l1_node_segments/l1_edge_segments to Vec::new() instead of cloning from current manifest, so any commit AFTER compaction silently orphans all L1 data even though segment .seg files still exist on disk. Compaction injects L1 fields explicitly after create_manifest, but regular commits do not.

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。

Decide what to PERSIST in your data structures (graph nodes, DB tables, cache layouts) based on the QUERIES you must answer, not the DEFINITIONS that justify the data. Definitions tell you logical identity; storage strategy is independent. Materializing every definitional component leads to O(N×M) blow-ups that masquerade as memory leaks. Use when: (1) designing a new graph-node type, edge type, DB table, or cache layout; (2) about to name a `subgraph` / `comprises` / `members` / `contains` collection on a parent entity; (3) memory growth proportional to (entities × per-entity-elements); (4) "memory leak" debugging that survives multiple targeted patches — the leak may be storage shape, not retention; (5) pre-implementation sketch includes "for each X, store all reached nodes"; (6) research/spec doc says "X = ⟨A, B, C⟩" and you're tempted to make it three storage edges per X.

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 queried data for trends, week-over-week comparisons, distributions, funnels, cohorts, top-N lists, anomalies, sanity checks, and report-ready findings. Use after or alongside ClickHouse queries when the user wants insight rather than raw rows.

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 these skills when you need to explore the database structure, discover schema objects like tables and graphs, and execute custom SQL queries to interact with your data.

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 for Desktop Commander MCP capabilities — persistent shells and REPLs, long-running processes, filesystem beyond the workspace, structured files (.xlsx, .docx, .pdf, images) and large local data files such as CSVs, ripgrep search at scale, SSH, or cross-turn state.

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。