「sel」の検索結果

Orchestrator for agent harness work — the setup that makes AI agents follow project rules and improve when they fail. FIRES PROACTIVELY when agents misbehave, repeat mistakes, ignore instructions, skip skills, or when AGENTS.md exists but docs/harness/manifest.json is missing. Also triggers on: harness engineering, agent scaffold, agent keeps failing, agent not following instructions, make agents reliable, agents going off rails, agent forgot context, improve agent setup, self-improving agents, agents keep making mistakes, why is my agent bad, agent quality, agent setup broken, agents ignore skills, same mistake again, fix agent behavior, tune agent instructions, set up agent infrastructure, after project setup agents still bad. Routes bootstrap vs evolution. Not multi-agent topology — agent-builder.

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。

Improve agent reliability over time — diagnose why agents fail and fix the setup. Triggers on: agent keeps failing, same mistake again, agent not improving, make agent smarter, agent quality plateau, agents ignore skills, agent skips tests, fix agent behavior, agent unreliable, improve agent setup, self-improving harness, agents worse over time, tune agent instructions, agent going in circles, agent ignores AGENTS.md, repeated agent errors. Requires harness v0 and eval harness. AUTO-ROUTED from harness-engineering on symptoms. Not first setup — harness-generation 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 user-facing or internal release notes and changelogs. Load when the user prepares a release, tags a version, or wants to summarize recent progress. Also triggers on "write a changelog", "prepare release notes", "what's new in this version", "summarize my commits", or "create a release summary". Auto-triggered by library-skill after major repo changes (new skills added, skills renamed, structure changes). Applicable to any project, including this skill library itself.

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。

Score LLM and agent outputs using LLM-as-judge techniques — direct scoring against rubrics or pairwise comparison between two outputs. Includes built-in bias mitigation for position bias, length bias, and self-enhancement bias. Load when the user asks to score an output, judge a response, evaluate against a rubric, compare two outputs, do direct scoring, run pairwise comparison, or says "rate this", "which response is better", "score this against the rubric", "judge this output", "LLM as judge this". Sub-skill of eval-output 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。

Build and deploy applications when the user selects or invokes the Prisma plugin, including requests like "Build a simple Todo app and deploy it" that do not name a stack. Use Prisma Composer for new apps and Prisma Compute for deployment. Also use for explicit Composer/Compute requests, deployment diagnostics, and recovering Composer deployments. Does not cover unrelated ORM or database administration.

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。

Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.

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 wants to visualize data. It intelligently selects the most suitable chart type from 26 available options, extracts parameters based on detailed specifications, and generates a chart image using a JavaScript script.

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 a browser automation expert who has debugged thousands of flaky tests and built scrapers that run for years without breaking. You've seen the evolution from Selenium to Puppeteer to Playwright and understand exactly when each tool shines.

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 a one-line objective into a step-by-step construction plan any coding agent can execute cold. Each step has a self-contained context brief — a fresh agent in a new session can pick up any step without reading prior steps.

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。

Validates animation durations, enforces typography scale, checks component accessibility, and prevents layout anti-patterns in Tailwind CSS projects. Use when building UI components, reviewing CSS utilities, styling React views, or enforcing design consistency.

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。

Extract product data, prices, reviews, and seller information from any e-commerce platform using Apify's E-commerce Scraping Tool.

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。

API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination.

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。

AI-driven data extraction from 55+ Actors across all major platforms. This skill automatically selects the best Actor for your 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。

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.

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。

A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.

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。

Loads, converts, and manipulates Hi-C contact matrices in cooler format (.cool/.mcool/.scool) and Juicer .hic, using cooler (Python + CLI), hic2cool, and hictk. Covers the single-resolution mcool URI (file.mcool::/resolutions/<bp>), the load-bearing divisive-vs-multiplicative weight-naming rule (KR/VC/VC_SQRT auto-divisive vs cooler's multiplicative weight), what survives .hic<->.cool conversion (FRAG matrices and norm vectors do not), raw-vs-balanced coarsening, the .pairs upper-triangle/chromsize-order contract, and chrom-naming/bin-table provenance. Use when loading a cooler, converting .hic to .mcool, selecting a resolution, building a cooler from pairs or a matrix, coarsening/zoomifying, importing Juicer norm vectors, or debugging all-NaN balanced matrices and chr1-vs-1 empty fetches.

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。

Predicts protein-coding gene structures (exons, introns, UTRs) in eukaryotic genomes with BRAKER3 (RNA-seq + protein evidence), BRAKER1/BRAKER2, GALBA (protein-only), Funannotate (fungi), GeMoMa (homology projection), or Helixer/Tiberius (deep-learning ab initio). Covers the evidence-first tool decision, mandatory soft-masking, the training-set-quality-dominates principle, OrthoDB clade-partition selection, the one-isoform-per-locus and missing-UTR traps, merge/split errors, and reference bias against orphan genes. Use when annotating a newly assembled eukaryotic genome, choosing a gene-prediction pipeline based on available evidence, or diagnosing a poor annotation.

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。

Predict B-cell and T-cell epitopes for vaccine antigen design and epitope mapping with BepiPred-3.0, DiscoTope-3.0, the IEDB tools, and EL-mode MHC presentation. Encodes the load-bearing asymmetry that T-cell epitope prediction is mature (it reduces to MHC presentation, AUC>0.9) while B-cell prediction is unreliable (linear predictors ~AUC 0.6 because ~90% of real epitopes are conformational) — so structure-based DiscoTope-3.0 on AlphaFold models is the only defensible B-cell path, propensity scales are obsolete, and NetChop is largely redundant on EL-trained models. Use when mapping epitopes or selecting vaccine antigens. MHC binding lives in mhc-binding-prediction.

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。

Generates, normalizes, and converts bedGraph signal tracks (4-column chrom/start/end/value, 0-based half-open) with bedtools genomecov, deepTools bamCoverage/bamCompare/bigwigCompare, bedtools unionbedg, and UCSC bedGraphToBigWig. Covers why a raw coverage bedGraph is not comparable across samples until normalized, the CPM/RPKM/BPM/RPGC normalization menu and the conserved-total assumption that makes them wrong under a global perturbation, the strict sorted-non-overlapping-chrom.sizes bedGraphToBigWig contract that silently corrupts a bigWig, effective-genome-size selection, and bin-size aliasing. Use when building or normalizing a coverage/signal track from a BAM, comparing tracks across samples or conditions, converting bedGraph to a browser-ready bigWig, or diagnosing a track that looks plausible but reports wrong heights.

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 pegRNAs and nicking guides for prime editing (PE) -- choosing the nick/strand, tuning the primer-binding site (PBS) and reverse-transcription template (RTT) as a per-locus panel, selecting the PE system (PE2/PE3/PE3b/PE4/PE5/PEmax/PE7), adding MMR-evading and PAM-disrupting silent edits, appending epegRNA 3' motifs (tevopreQ1/mpknot), and ranking with PRIDICT/DeepPrime. Covers twinPE/PASTE for large insertions and the prime-vs-base-editing decision. Use when designing a scarless point mutation, small insertion/deletion, or any of the 12 base conversions without a double-strand break, when efficiency is low and MMR inhibition or pegRNA stabilization is needed, or when routing a large insertion to an integrase method. Generic guide scoring and base editing are separate skills.

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 cytosine (CBE, C-to-T) and adenine (ABE, A-to-G) base-editor guides by positioning the target base at the activity-peak of the editing window (protospacer positions ~5-7, PAM-distal numbering), minimizing bystander edits for product purity, reading dinucleotide context (APOBEC1 TC favored / GC disfavored), and selecting the editor variant (BE4max, ABEmax, ABE8e, YE1/SECURE, TadCBE, CGBE, SpG/SpRY-BE). Covers knockout by premature stop (CRISPR-STOP/iSTOP) and splice-site disruption, the three off-target classes (Cas-dependent, Cas-independent DNA, RNA), outcome prediction (BE-Hive/DeepBE), and the base-vs-prime-vs-HDR decision. Use when installing a transition mutation without a double-strand break, knocking out a gene without indels, or choosing CBE vs ABE. Generic guide scoring, prime editing, and HDR donors are separate skills.

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 ranks guide RNAs (sgRNAs) for CRISPR-Cas9/Cas12a gene knockout by scanning a target for PAM sites (NGG SpCas9, NNGRRT SaCas9, TTTV Cas12a, NG SpCas9-NG, near-PAMless SpRY), enumerating candidate spacers, applying hard filters (Pol-III TTTT terminator, 5' G, GC), ranking on-target activity with the context-appropriate model (Rule Set 2/Azimuth for U6/lentiviral, CRISPRscan for T7/embryo, DeepHF for high-fidelity variants, DeepCpf1 for Cas12a), and predicting the indel/frameshift outcome (Bae out-of-frame score, inDelphi, FORECasT, Lindel). Use when selecting sgRNAs to knock out a gene, choosing a nuclease/PAM for a constrained locus, picking which exon to target, or shortlisting guides before an off-target check. Off-target specificity, base/prime editing, and HDR donors are separate skills.

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。