3,369 件 ・ 関連度順
概要と使いどころ
Internal skill. Called by setup-evaluation after a PASS. Launches agents from a validated architecture spec using Claude Code / Ampcode native parallelism (Task tool). Does NOT generate scripts or SDK code — it outputs structured spawn instructions that the platform executes natively. Never invoked directly by the user. Never launches without a setup-evaluation PASS.
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。
Set a deliberate visual direction before any UI is built — the single biggest lever against generic AI output. Derives a posture from product-soul/PRD/specs, scores a curated archetype palette, then generates 2-3 GENUINELY DISTINCT directions and compares them side-by-side before committing to one. Load when the user asks to pick an aesthetic, choose a design direction, decide what a UI should feel like, explore visual options, says "what should this look like", "make it feel like [Linear/Apple/ Duolingo]", "give me design directions", "explore some looks", or when frontend-design routes here. Replaces design-archetype. Sub-skill of frontend-design.
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。
Instrument a shipped product's AI agents with tracing and observability so you can see what they did, why outputs happened, and what each run cost. Plain-language primer plus free-tier-first backend selection (Langfuse, Phoenix, LangSmith, Braintrust) and OpenTelemetry/OpenInference instrumentation. Load when the user asks to add observability, add tracing, instrument my agents, see what my agent is doing in production, set up Langfuse or Phoenix or LangSmith, debug why my agent gave a bad answer, or track LLM cost per request. Also fires when agent-system-architecture or setup-evaluation requires an observability plan for an agent-chain product. NOT for tracing the coding agent itself — that is run-trace. Precondition for runtime-learning-loop.
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。
Compress an oversized SKILL.md to under 200 lines without losing effectiveness. Load when a skill exceeds 200 lines, when AGENTS.md triggers compression after a skill edit, or when the user asks to compress, shrink, slim down, or optimize a skill. Also triggers on "this skill is too long", "reduce skill size", "make this skill shorter". Applies to all skills including meta skills — the 200-line rule has no exceptions. Preserves hard gates, gotchas, output format, routing triggers, and at least one example. When genuinely CORE content cannot be compressed away, invokes split-skill instead of degrading the 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。
Write the executable feature specification — the WHAT and WHY artifact that agents and reviewers treat as source of truth. Owns both /specify and /clarify modes. Load when the user asks to write a feature spec, write a specification, write an executable spec, define functional requirements, capture acceptance criteria as Given/When/Then, or when the spec-driven-development orchestrator routes here. Also triggers on "feature spec", "executable spec", "/specify", "/clarify", "write the spec for this feature", "specification for", "spec-driven", "machine-readable spec". Output: docs/specs/YYYY-MM-DD-<slug>-feature-spec.md. Hard gate: cannot Approve while [NEEDS CLARIFICATION] markers remain.
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。
Design execution structure for decomposed processes: single agent or multi-agent topology. Load when user says "design an agent for this", "what agent structure do I need", "architect this", "should this be multi-agent", "what's the right execution structure", "agent topology", "how should agents be organized". Takes process-decomposer output as primary input. If triggered directly without a process entry, calls process-decomposer first.
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 single unified changelog from git history that works for everyone in the company (managers and non-tech colleagues as well as developers). Outputs Slack mrkdwn so it can be pasted straight into Slack. Defaults to Slovak (English only on explicit request) and to comparing the release branch (main) against develop to show unreleased changes; also supports date ranges like "today", "yesterday", "last week", or an explicit git range. User-invoked only via /changelog.
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 about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
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。
Turn meeting transcripts or rough notes into crisp summaries with decisions, risks, and owner-tagged action items; use for Zoom/Meet/Teams transcripts, call notes, or long meeting chats to generate share-ready outputs.
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。
These are instructions for creating design philosophies - aesthetic movements that are then EXPRESSED VISUALLY. Output only .md files, .pdf files, and .png files.
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。
Actorization converts existing software into reusable serverless applications compatible with the Apify platform. Actors are programs packaged as Docker images that accept well-defined JSON input, perform an action, and optionally produce structured JSON output.
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。
Design spec with 98 rules for building CLI tools that AI agents can safely use. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description.
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。
Algorithmic philosophies are computational aesthetic movements that are then expressed through code. Output .md files (philosophy), .html files (interactive viewer), and .js files (generative algorithms).
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。
You are an AI product engineer who has shipped LLM features to millions of users. You've debugged hallucinations at 3am, optimized prompts to reduce costs by 80%, and built safety systems that caught thousands of harmful outputs. You know that demos are easy and production is hard.
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 the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality 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。
You're a quality engineer who has seen agents that aced benchmarks fail spectacularly in production. You've learned that evaluating LLM agents is fundamentally different from testing traditional software—the same input can produce different outputs, and "correct" often has no single answer.
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。
Annotates bacterial and archaeal genomes (isolates, MAGs, plasmids) with Bakta (active versioned databases, NCBI-compliant output) or Prokka (legacy), producing GFF3/GenBank/EMBL/FASTA with INSDC locus tags. Covers Bakta-vs-Prokka-vs-PGAP-vs-DFAST choice, light-vs-full database tiers, translation-table selection (11/4/25), archaeal and leaderless-gene caveats, the small-ORF blind spot, pseudogene-vs-phase-variation, the pangenome re-annotation trap, and submission compliance. Use when annotating a newly assembled prokaryotic genome, choosing an annotation tool, re-annotating a collection for pangenomics, or preparing annotations for NCBI/DDBJ 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。
Calls m6A peaks from MeRIP-seq / m6A-seq paired IP-vs-input data using exomePeak2 (transcript-aware, GC-bias-corrected Poisson GLM; Liu 2022 *NAR Genom Bioinform* 4:lqac046), MeTPeak (HMM over sliding windows; Cui 2016 *Bioinformatics* 32:i378), MACS3 / MACS2 with --nomodel --broad --keep-dup all (genome-wide broad alternative), and DRACH motif enrichment confirmation via HOMER or ggseqlogo as a sanity check (NOT a filter). Covers BED12 vs narrowPeak output formats, exonic vs intronic peak handling, multi-tool reconciliation (intersection vs union; cross-caller IDR-equivalent), the m6A-vs-m6Am ambiguity at 5'UTR peaks that antibody-based methods cannot resolve, and orthogonal-validation routes (miCLIP / GLORI / m6A-SAC-seq / m6Anet). Use when calling peaks from paired IP/input genome BAMs, choosing exomePeak2 (transcript-aware default) vs MACS3 (broad genomic) vs MeTPeak (HMM-smoothed low-coverage), confirming DRACH enrichment as a sanity check on the peak set as a whole, reconciling differing peak sets across tools, validating MeRIP peaks against orthogonal single-base methods, interpreting peaks at the 5' end where m6Am contamination is possible, or recommending a multi-tool consensus strategy.
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。
Extracts, filters, annotates, and exports differential expression results from DESeq2 or edgeR with proper handling of padj=NA (independent filtering, Cook's outliers, all-zero), multiple-testing correction choice (BH vs Storey q-value vs IHW vs lfsr), TREAT vs post-hoc fold-change filtering, p-value histogram diagnostics, gene annotation via org.db/biomaRt/mygene, GSEA preranked input, ORA background construction, replication reality (Schurch 2016 small-n result), and SABV/sex-stratified reporting. Use when extracting and interpreting DE results, troubleshooting padj=NA, choosing FDR method, preparing ranked lists for pathway analysis, annotating gene IDs, or comparing DESeq2 vs edgeR outputs.
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。
Processes eDNA metabarcoding from raw paired-end reads to species tables, navigating ASV (DADA2, UNOISE3) vs OTU (swarm v2) decision (Callahan 2017 vs Schloss multi-copy-16S critique), marker/primer choice (Leray COI, MiFish 12S, 515F/806R 16S, ITS2) with primer-specific bias, OBITools3 v3 command-name break (obi stats plural; .tar.gz taxonomy), tag-jumping with dual-indexing (Schnell 2015; NovaSeq 10x MiSeq), decontam as screening-not-classifier (Davis 2018), read-counts-not-abundance critique (Lamb 2019), site-occupancy modeling (Ficetola 2015), Naive-Bayes calibration limits (Bokulich 2018), and eDNA decay (Strickler 2015). Use when going from raw eDNA FASTQ to species tables, picking marker + denoising pipeline, deciding whether read counts represent abundance, applying occupancy modeling, configuring OBITools3 v3, or interpreting decontam output. Not for clinical 16S microbiome (see microbiome/amplicon-processing).
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。
Imports gene expression count matrices from featureCounts, HTSeq, STAR ReadsPerGene, Salmon/kallisto via tximport or tximeta, RSEM, 10X Genomics MTX/H5, AnnData H5AD, and RDS. Handles silent-miscounting traps (featureCounts -p v2.0.2 API break, STAR strandedness column choice, salmon NumReads-sum without tximport, RSEM non-integer expected_count, GENCODE _PAR_Y suffix, zero-length-transcript TPM divide-by-zero), and encodes the tximport countsFromAbundance decision tree with the "lengthScaledTPM is not TPM" warning. Use when assembling a gene-by-sample count matrix from aligner or quantifier output, importing salmon/kallisto for DESeq2 vs limma-voom, choosing strandedness column for STAR, debugging zero-count panics, or building tx2gene mapping.
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。
Detects acquired antimicrobial-resistance determinants and chromosomal point-mutation resistance in bacterial assemblies using AMRFinderPlus, ResFinder 4.0 (acquired + PointFinder), CARD-RGI, abritAMR, staramr, and species-specific callers (TB-Profiler, Mykrobe). Harmonises cross-tool output via hAMRonization, contextualises determinants with mobile-genetic-element annotation (MOB-suite, PlasmidFinder, MobileElementFinder, ICEberg), predicts phenotype against EUCAST or CLSI breakpoints, and translates calls into WHO GLASS reporting categories. Use when screening clinical or surveillance isolates for AMR, distinguishing acquired vs intrinsic vs point-mutation resistance, calling rpoB / katG / pncA / gyrA / mgrB mutations, reconciling AMRFinderPlus vs RGI vs ResFinder disagreement, contextualising carbapenemases or mcr alleles on plasmids, predicting susceptibility from genotype against the WHO Mtb 2nd-edition catalogue, or building a hAMRonized multi-lab AMR surveillance 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。
Designs and analyzes pooled prime-editor (PE) screens for installing precise genetic variants without bystander confounding. Covers pegRNA design with PRIDICT and PRIDICT2 (Mathis 2023/2024) for predicting per-pegRNA editing efficiency, pegRNA architecture (spacer + scaffold + PBS + RTT), PE2 / PE3 / PE3b / PEmax / PEAR variants, MOSAIC in situ saturation mutagenesis (Hsu JY et al 2024 bioRxiv), the PRIME pooled-screen methodology (Erwood/Doman 2023 Nat Biotechnol 41:885; ~3,699 ClinVar variant screens), chromatin context as a primary determinant of PE efficiency, scaffold-incorporation and indel byproduct quantification with CRISPResso2, and the cross-modal validation strategy of PE + base-editor screens for variant function. Use when designing a pegRNA library for variant installation, choosing between BE and PE for a specific edit, predicting pegRNA efficiency before library synthesis, analyzing PE screen output, distinguishing intended-edit from scaffold-incorporation, or scaling PE screens to thousands of variants.
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。
Analyzes base-editing screens for variant function. Covers library design (Sanson 2020 GRACE, Hanna 2021 BRCA1/2 SNV scanning, Cuella-Martin 2021), CBE vs ABE chemistry choice (BE3/BE4 vs ABE7.10/ABE8.20/ABE8e), editing-window math (positions 4-8 from PAM-distal end, wider for ABE8e), bystander-edit quantification and the variant-call ambiguity it creates, sgRNA-efficiency filtering before hit calling, indel byproduct interpretation, the substitution-vs-indel diagnostic, variant annotation against ClinVar / COSMIC, and the Broad be-validation-pipeline. Use when designing a BE variant screen, choosing CBE vs ABE for a specific edit, interpreting bystander-confounded hits, distinguishing functional signal from indel artifact, integrating CRISPResso2 output with screen scoring, or deciding BE vs PE for SNV installation.
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。