636 件 ・ 関連度順
概要と使いどころ
Check a change for performance regression against this machine's recorded baseline - decide whether the diff needs checking, run the deck benchmark under the hygiene wrapper, and attribute any regression to an element. Use before opening a PR that touches the simulation hot path.
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。
Apply these opinionated TypeScript conventions whenever writing or reviewing TypeScript: branded types for domain modeling, discriminated unions for state, `satisfies` over `as`, const objects instead of enums, type-only imports, and the strict tsconfig baseline beyond `strict: true`. Also use for monorepo project references and incremental build setup.
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。
对 profiling 数据（kernel_details.csv / trace_view.json / step_trace_time.csv）做统一分析： 5 层递进管道（analyze_trace.py）+ baseline/优化后 kernel diff（compare_traces.py），输出 瓶颈诊断、算子执行序、可融合候选与 P0-P2 方向建议。输入统一来自 profiling-collect。 只要用户有 profiling 产出并问"为什么慢/瓶颈在哪/优化前后差多少/往哪个方向"，都用本技能；采集走 profiling-collect，方案选档走 dit-perf-opt，实现/并行/基准走 pattern-dev/dit-parallel-opt/benchmark-dev——本技能只做诊断与方向。 由 model-auto-optimization 的 S1（融合分析）/S3（并行）阶段调用，亦由 dev-workflow 的分析阶段指引加载。 融合机会候选只做**识别**；候选的**边界与收益判定**（能不能融成一个单元、融多大、值不值）交 `fusion-scope-analyze`（本技能的辅助技能）——本技能不判融合边界。
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。
Advanced vulnerability analysis principles. OWASP Top 10 baseline + current threat landscape awareness, Supply Chain Security, attack surface mapping, risk prioritization. Use when performing security audits, threat modeling, or OWASP reviews. NOT for STRIDE/CSO-mode infrastructure audits (see mk:cso).
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。
Investigate reviewed Grafana APM evidence for request rate, error rate, and operational latency. Use when an application is slow, erroring, dropping traffic, regressing against a baseline, or needs a bounded request-rate, error, and p95 latency health assessment.
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 approved Grafana business-intelligence evidence for revenue, conversion, and operational KPIs. Use for bounded KPI scorecards, financial or operational metric checks, baseline comparisons, and business-unit reviews without changing source systems.
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。
Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can edit before publishing or testing. Use when Codex needs to create a new local plugin, add optional plugin structure, or generate or update repo-root `.agents/plugins/marketplace.json` entries for plugin ordering and availability metadata.
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。
Build publication-quality figures in R with ggplot2 using the grammar of graphics (data + aesthetics + geometries + scales + facets + themes) with CVD-safe palettes, cairo_pdf TrueType embedding, programmatic aes via tidy evaluation, and the theme_classic publication baseline. Use when producing static figures in R for papers, presentations, or reports.
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。
Visualize copy number profiles, segments, allele-specific tracks, and cohort patterns from CNVkit, GATK, ASCAT, FACETS, Sequenza, and other callers. Covers genome-wide and per-chromosome log2 scatter plots, B-allele-frequency/minor-allele-fraction tracks, ideograms, cohort heatmaps, circos views, and caller-native plots. Use when creating publication CNV figures, choosing which plot answers a given question, diagnosing a wrong diploid baseline visually, displaying loss of heterozygosity, or deciding what depth-only plots cannot reveal.
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。
Infer integer allele-specific copy number, tumor purity, and ploidy from tumor sequencing by jointly modeling read depth (logR) and B-allele frequency (BAF) with ASCAT, Sequenza, FACETS, PURPLE, and PureCN (tumor-only). Covers the purity-ploidy identifiability problem, the diploid-baseline (dipLogR) anchor, major/minor copy number, loss of heterozygosity, sunrise/contour fit diagnostics, and reconciliation of conflicting fits. Use when tumor analysis needs absolute copy number rather than relative log2, when estimating purity and ploidy, calling LOH or copy-neutral LOH, resolving whole-genome doubling, running tumor-only allele-specific calling, or choosing among ASCAT, Sequenza, FACETS, and PureCN.
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。
Estimates SNP heritability and partitions it across functional annotations, cell types, and loci from GWAS summary statistics or individual-level genotypes. Implements LDSC, stratified LDSC with the baseline-LD model, Finucane 2018 cell-type prioritization, LDAK SumHer, HDL, HESS local heritability, BOLT-REML, GCTA-GREML, graphREML, and Popcorn cross-population genetic correlation. Use when computing total h2_SNP from summary stats, partitioning heritability across functional categories, prioritizing trait-relevant tissues or cell types from ENCODE/Roadmap chromatin marks, reconciling LDSC vs LDAK enrichment estimates, computing local heritability with HESS, estimating genetic correlation between traits, or producing publication-grade enrichment with calibrated sensitivity to model assumptions.
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。
Reads, validates, and prepares CDISC SDTM and ADaM clinical trial data for analysis. Covers SDTM domain joins (DM, AE, EX, VS, LB, DS), ADaM architecture (ADSL, BDS, OCCDS, ADTTE) with traceability, treatment-emergent AE conventions, baseline derivation, SUPPQUAL/NSV handling, Define-XML 2.1, and Pinnacle 21 / CORE validation. Use when working with clinical trial datasets in CDISC SDTM/ADaM format, preparing analysis-ready data, or validating for regulatory submission.
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。
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
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 recommends obtaining a postoperative pituitary MRI within 1–3 months after successful transsphenoidal surgery (TSS) to establish a new baseline for future recurrence assessment. Use when a Cushing’s syndrome patient has achieved biochemical remission post‑TSS and is entering routine follow‑up.
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。
Identifies patients with a positive aldosterone-to-renin ratio screening who may proceed directly to subtype testing without confirmatory testing based on specific clinical criteria. Triggers include spontaneous hypokalemia, baseline plasma aldosterone concentration >100 pg/mL (CLEIA), renin suppression, or a clinician questioning the need for a confirmatory test after a positive screen.
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。
Recommends checking and managing vitamin D according to Endocrine Society guidelines to avoid hypocalcemia in patients receiving bisphosphonates or denosumab for hypercalcemia of malignancy. Use when a clinician notes risk factors for hypocalcemia (e.g., low 25‑OH vitamin D, renal insufficiency) and asks about baseline labs before antiresorptive start.
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。
Standard operating procedure for producing a documentation page end to end — gather source material, classify, draft against the measured corpus profile, then run the reader-level and humanizer passes and both gates. Use for any page on a documentation surface, or when rewriting a page that reads as machine-written. Orchestrates technical-writing, reader-level and humanizer in a fixed order.
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-only release + backlog recap. Reports the last release, commits-since-tag classified by conventional-commit type with the semver bump they trigger and pushed-vs-origin state, the backlog bucketed (open/picked-up/dropped with epic parent→child nesting), the roadmap epics with their per-task tallies, and condensed open questions — then recommends the next pickup. One `cli.mjs recap` call returns all six recap keys. Invoke any time (on demand) to plan a release or choose the next thing to build; a compact form is also surfaced at session start. Not a workflow phase; never writes CHANGELOG; never starts or commits work.
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。
Write technical documentation that matches the measured profile of professionally-written docs. Carries the craft rules derived from 114k words of pre-2022 documentation (SQLite, PostgreSQL, Python, Django, Rust, Go, Pro Git, nginx), the per-Diátaxis-type numeric targets, and the copywriting register for page leads. Use when drafting or rewriting any documentation prose, or when a page is factually right but reads as machine-written.
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。
Workflow Phase 6 — TDD coordinator. Decides the scenario recipe and the implementation contract in main context, writes them to a state file, seeds per-worker tasks (scenario, implement, verify-tick, design-ui-tick) into the TaskList, and yields with harness_state continue so the harness invokes each worker as its own tick. No subagent delegation; no nested Skill calls.
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。
Decompose an approved spec into a dependency-ordered swarm plan — one task per component, each with an explicit write_set. Produces `.claude/state/swarm/<slug>.json` with tasks + waves. The wave scheduler guarantees pairwise-disjoint write_sets within each wave so parallel dispatch is provably conflict-free.
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。
Execute a swarm plan wave by wave with filesystem isolation via git worktrees. For each wave, main context decides the scenario recipe + implementation contract for every task, then spawns one swarm-worker per task in parallel. Each worker executes its recipe and reports JSON status. Worktree merge-audit verifies write-set discipline before changes land on main. Aborts remaining waves on any audit or task failure.
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。
Report the health of the central system spec at `docs/system/` across seven checks — coverage gaps, stale elements, dangling anchors, duplicate anchors, orphan shards, unillustrated elements, and shards missing their kind annotation. Report-first and read-only: it repairs nothing until a human confirms a specific item. Use when the corpus has drifted, after a merge that touched `docs/system/`, or from `/archive` Step 5.5 in report-only mode. Requires `memory.architecture_map.enabled`.
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。
When the user wants to create step-by-step technical tutorials, quickstarts, or code walkthroughs. Trigger phrases include "tutorial," "quickstart," "getting started guide," "walkthrough," "step by step," "how to guide," "hands-on guide," or "code tutorial."
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。