Plan & spec
10,746 rows, by stacks then stars
2,010 of these skill files have been read, by 1,360 distinct authors, and what they tell an agent counted. What Plan & spec authors agree on, and what they forbid
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/lipid-structure-specification Skill
16★ repoUse when you have identified lipid species unique to your sample type (e.
Mass spec tolerance parameter application
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/mass-spec-tolerance-parameter-application Skill
16★ repoUse when when you have a feature table from Orbitrap LC-MS containing m/z, retention time, and intensity columns, and you need to group individual mass features into putative metabolites that represent the same chemical entity across different ionization states and isotopic compositions.
Metabolic model constraint specification
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/metabolic-model-constraint-specification Skill
16★ repoUse when you have a generic constraint-based metabolic model (SBML format) and cross-sectional omics data (RNA-seq, intracellular metabolomics, YSI or bioanalyzer extracellular flux measurements) for multiple biological samples and need to create sample-specific models that discriminate whether.
Metabolite set decomposition plage
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/metabolite-set-decomposition-plage Skill
16★ repoUse when you have peak intensity data from metabolomics experiments with annotated metabolites assigned to known groupings (KEGG pathways, Reactome, GNPS Molecular Families, or MS2LDA Mass2Motifs) and need to identify which metabolite sets change significantly across experimental comparisons while.
Missing data mechanism specification
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/missing-data-mechanism-specification Skill
16★ repoUse when when you have a metabolomics abundance table with missing values and need to decide which imputation method to apply, or when designing a simulation to evaluate imputation performance.
Missing value imputation strategy selection
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/missing-value-imputation-strategy-selection Skill
16★ repoUse when after mark_nas() has replaced non-NA missing-value codes (e.g., 0, 1) with R's NA in the exprs matrix of a MetaboSet object, and you need to decide whether to apply random forest imputation, simple imputation strategies, or defer imputation.
Ms dial export file specification
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/ms-dial-export-file-specification Skill
16★ repoUse when you have MS-DIAL 4 or MS-DIAL 5 alignment results and need to configure LipoCLEAN for quality filtering of lipid identifications. Use this skill at the start of a LipoCLEAN analysis when you need to specify which MS-DIAL export files to analyze and how to locate them.
Ms dial peak character estimation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/ms-dial-peak-character-estimation Skill
16★ repoUse when you have a filtered MS-DIAL peak list (post-generic filtering, containing m/z, retention time, and peak intensity metrics for each feature) and need to group features into clusters that represent true metabolite signals rather than instrumental or chemical artifacts.
Multiplexed spectrum decomposition
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/multiplexed-spectrum-decomposition Skill
16★ repoUse when you have SWATH-MS data (mzML or vendor binary format) where precursor isolation windows intentionally capture multiple co-eluting compounds, resulting in multiplexed MS/MS spectra that contain mixed fragment ion peaks from unknown metabolites.
Network diffusion prioritization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/network-diffusion-prioritization Skill
16★ repoUse when after clustering and filtering KEGG candidates for LC-MS features, when you have a ranked set of candidate metabolites per feature and access to a metabolite interaction network (e.g., from FELLA).
Open modification spectral search strategy
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/open-modification-spectral-search-strategy Skill
16★ repoUse when when searching an unknown query MS/MS spectrum against a large spectral library (>100k spectra) for both unmodified and modified peptides, and computational speed is critical without sacrificing sensitivity or FDR control.
Pairwise alignment with anchor prioritization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/pairwise-alignment-with-anchor-prioritization Skill
16★ repoUse when when processing LC-MS metabolomics datasets with 10 or fewer samples and requiring reproducible mass track alignment across the cohort.
Pathway activity decomposition via plage
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/pathway-activity-decomposition-via-plage Skill
16★ repoUse when you have a log2-transformed, standardized peak intensity matrix (rows = metabolite features, columns = samples) with compound annotations mapped to curated pathway databases (KEGG, Reactome, or custom metabolite sets), and you need to rank pathways by their activity level while tolerating.
Pathway activity decomposition via svd
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/pathway-activity-decomposition-via-svd Skill
16★ repoUse when when you have a metabolite intensity matrix (samples × metabolites) with compound annotations and need to score pathway activity levels for pathway enrichment analysis.
Pathway ranking and prioritization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/pathway-ranking-and-prioritization Skill
16★ repoUse when after peak annotation when you have: (1) a peak intensity matrix (rows=peaks with KEGG/ChEBI/UniProt IDs, columns=samples) with group labels; (2) a pathway database (KEGG, Reactome, or user-defined metabolite sets); (3) a comparative experimental design (case vs. control groups).
Permutation test p value estimation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/permutation-test-p-value-estimation Skill
16★ repoUse when after computing Multi-Block Variable Importance in Projection (MB-VIP) scores on a fitted MB-PLS discriminant model, when you need to distinguish signal features from noise by establishing empirical significance thresholds rather than relying on parametric assumptions.
Pfas candidate prioritization by scoring
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/pfas-candidate-prioritization-by-scoring Skill
16★ repoUse when you have a feature list (containing m/z, retention time, and molecular formula or neutral mass per feature) extracted from LC- or GC-HRMS data in mzML format with data-dependent acquisition, and you need to rank or flag features as likely PFAS compounds to reduce manual review burden in.
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/pfas-feature-prioritization Skill
16★ repoUse when you have detected features in LC- or GC-HRMS data (via pyOpenMS or custom feature tables) and need to systematically rank them for likelihood of being PFAS compounds.
Ranked annotation prioritization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/ranked-annotation-prioritization Skill
16★ repoUse when you have completed cluster-based filtering of KEGG candidate assignments in untargeted LC-MS metabolomics and need to rank those candidates by biological plausibility using a metabolite interaction network. Specifically, use it after `clusterBased.
Ranked candidate prioritization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/ranked-candidate-prioritization Skill
16★ repoUse when you have a feature quantification table (m/z, retention time, peak areas) and candidate metabolite annotations (chemical identifiers, MS/MS spectra matches, or SIRIUS/GNPS predictions) linked to a sample organism or taxon, and you need to prioritize which candidates are most biochemically.
Retention time regression output specification
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/retention-time-regression-output-specification Skill
16★ repoUse when after initializing and executing a forward pass through a dual-branch RT-Transformer model (combining fingerprint and molecular graph inputs) on a batch of molecular samples, to verify that the output tensor conforms to the expected shape, data type, and numeric range for retention time.
Scalability extrapolation and throughput estimation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/scalability-extrapolation-and-throughput-estimation Skill
16★ repoUse when you have a new or modified LC-MS data processing tool and need to determine whether it can handle production-scale sample cohorts (50–100+ samples) on modest hardware (single-core CPU, ≤16 GB RAM).
Set activity prioritization ranking
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/set-activity-prioritization-ranking Skill
16★ repoUse when after computing activity scores for a collection of metabolite sets (pathways, GNPS Molecular Families, or MS2LDA Mass2Motifs) from intensity and annotation data.
Singular value decomposition metabolomics
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/singular-value-decomposition-metabolomics Skill
16★ repoUse when when you have a log2-normalized, zero-mean, unit-variance intensity matrix (rows=metabolites, columns=samples) and a curated metabolite set database (e.
Skyline import format specification
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/skyline-import-format-specification Skill
16★ repoUse when you have computationally generated precursor m/z values, fragment m/z values, collision energies, and retention time predictions for a set of lipid targets (e.
Statistical significance estimation mass spectrometry
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/statistical-significance-estimation-mass-spectrometry Skill
16★ repoUse when after aligning fragment ions between two tandem mass spectra (query and reference) using maximum weight matching and you need to assign confidence scores to the matched ion pairs.
Uncertainty estimation across models
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/uncertainty-estimation-across-models Skill
16★ repoUse when when you have multiple independently trained models (e.g., ROASMI_1 through ROASMI_5) making predictions on the same set of compounds or samples, and you need to assess confidence in individual predictions.
Variance estimation within and between groups
HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/variance-estimation-within-and-between-groups Skill
16★ repoUse when you have a QC-annotated LC-MS feature intensity table (CSV or data frame) with replicate QC samples and biological samples from multiple batches or run orders, and you need to assess which features maintain consistent signal intensity across technical replicates (within-group) relative to.
Binary format specification implementation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/binary-format-specification-implementation Skill
16★ repoUse when you have a compressed file format (e.g., igzip) with a custom binary header structure that encodes metadata (index-to-offset mappings) in a fixed layout, and you need to parse or generate compliant files.
Cascade search strategy fdr control
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/cascade-search-strategy-fdr-control Skill
16★ repoUse when when searching high-resolution mass spectra against spectral libraries and you need to identify both unmodified and post-translationally modified peptides while maintaining strict control over false positive identifications.
Cascade search strategy implementation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/cascade-search-strategy-implementation Skill
16★ repoUse when when performing open modification spectral library searches on high-resolution mass spectra where computational cost is prohibitive if every query is scored against every library spectrum.
Chromatographic baseline estimation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/chromatographic-baseline-estimation Skill
16★ repoUse when you have extracted ion chromatogram (EIC) candidate data from untargeted LC/HRMS files (mzXML, mzML, or netCDF format) and need to identify genuine peaks within each EIC.
False discovery rate estimation untargeted
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/false-discovery-rate-estimation-untargeted Skill
16★ repoUse when performing untargeted metabolomics annotation (i.e., matching observed spectra to a compound database without a pre-defined target list) and you need to assign statistical significance or confidence to candidate metabolite identifications.
Fdr aware psm retention strategy
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/fdr-aware-psm-retention-strategy Skill
16★ repoUse when rescoring PSMs with machine learning or statistical models where: (1) you want to consider multiple candidate PSMs per spectrum (e.
Ms signal correction strategy selection
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/ms-signal-correction-strategy-selection Skill
16★ repoUse when you have loaded raw MS intensity tables into QuantyFey and observe or suspect intensity drift artifacts across your measurement sequence. Drift is especially likely in long-running targeted MS experiments where calibration curves or internal standards show systematic variation over time.
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/peak-border-center-estimation Skill
16★ repoUse when you have LC-HRMS chromatograms in retention time × m/z matrix format and need to automatically localize chromatographic peak positions and extents prior to matching against a reference peak library or generating CNN training instances.
Reference feature combination strategy
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/reference-feature-combination-strategy Skill
16★ repoUse when when you have isolated, high-confidence reference chromatographic peaks (ground-truth) from reference LC-HRMS chromatograms that have been matched across multiple samples, and you need to train a CNN model to detect peaks in new chromatograms but lack sufficient labelled instances.
Singular value decomposition pathway analysis
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/singular-value-decomposition-pathway-analysis Skill
16★ repoUse when when you have a peak intensity matrix (rows = metabolite features, columns = samples) with corresponding compound annotations (peak ID → KEGG/ChEBI ID mapping), and you need to rank pathways or metabolite set groupings (KEGG pathways, Reactome pathways, GNPS Molecular Families, MS2LDA.
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/tic-peak-boundary-estimation Skill
16★ repoUse when after sliding-window analysis has identified candidate TIC peaks but before parameter extraction from Extracted Ion Chromatograms (EICs).
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-generic/skills/xcms-parameter-estimation Skill
16★ repoUse when you have raw untargeted metabolomics data (at least 3 samples in mzML, mzXML, or CDF format) from qTOF, orbitrap, or Fourier transform ion cyclotron resonance mass analyzers and need to obtain optimized XCMS processing parameters tailored to your specific instrument and dataset rather than.
Hdf5 file structure specification
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-imaging/skills/hdf5-file-structure-specification Skill
16★ repoUse when when exporting quantified MSI data (feature-by-pixel intensity matrices with associated ion m/z, lipid annotations, and pixel spatial coordinates) from LipidQMap and you need to produce a standards-compliant HDF5 container that can be read by Cardinal and other MSI analysis tools.
Metabolite detection frequency estimation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-imaging/skills/metabolite-detection-frequency-estimation Skill
16★ repoUse when after loading spatial metabolomics data (from CSV, imzML, or merged positive/negative ionization modes) into an AnnData object, and before filtering metabolites or performing cross-modal integration.
Noise estimation snr thresholding
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-imaging/skills/noise-estimation-snr-thresholding Skill
16★ repoUse when after normalizing, smoothing, and baseline-reducing mass spectra via normalize(), smooth(), and reduceBaseline(), when you need to distinguish true peaks from noise-induced artifacts.
Vendor file format specification handling
HolobiomicsLab/asb-skill-collections/packs/metabolomics/ms-imaging/skills/vendor-file-format-specification-handling Skill
16★ repoUse when you have a raw MSI data file from an unknown or mixed set of vendors and need to apply format-specific data extraction, spectral parsing, or image reconstruction. The file extension alone must determine which parsing module (MSIGen.raw, MSIGen.D, MSIGen.baf, MSIGen.tdf, MSIGen.
Fusion pooling strategy implementation
HolobiomicsLab/asb-skill-collections/packs/metabolomics/nmr/skills/fusion-pooling-strategy-implementation Skill
16★ repoUse when you have extracted parallel feature streams from a CNN backbone (local spectral patterns) and a Transformer backbone (global dependencies) in 1H NMR spectra, and you need to fuse them into a single embedding for bi-encoder or cross-encoder processing before compound identification scoring.
HolobiomicsLab/asb-skill-collections/packs/metabolomics/nmr/skills/hybrid-model-fusion-strategy Skill
16★ repoUse when you have 1H NMR spectral data from complex mixtures and need to identify component compounds, but a single architecture (CNN or Transformer alone) fails to capture both fine local patterns in peak structures and long-range dependencies across the full spectral range.
Memory mapped file selection strategy
HolobiomicsLab/asb-skill-collections/packs/metabolomics/nmr/skills/memory-mapped-file-selection-strategy Skill
16★ repoUse when initializing a Dataset object in NMRFx and must decide which storage backend to use for in-memory or memory-mapped file access.
Pathway ranking and prioritization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/nmr/skills/pathway-ranking-and-prioritization Skill
16★ repoUse when after peak annotation when you have: (1) a peak intensity matrix (rows=peaks with KEGG/ChEBI/UniProt IDs, columns=samples) with group labels; (2) a pathway database (KEGG, Reactome, or user-defined metabolite sets); (3) a comparative experimental design (case vs. control groups).
Peaklist metabolite assignment prioritization
HolobiomicsLab/asb-skill-collections/packs/metabolomics/nmr/skills/peaklist-metabolite-assignment-prioritization Skill
16★ repoUse when you have extracted m/z and retention time (m/z-RT) information for peaks from untargeted LC/HRMS data (using tools like IDSL.IPA) and need to assign molecular formula identities to those peaks.
Sample prioritization through structural clustering
HolobiomicsLab/asb-skill-collections/packs/metabolomics/nmr/skills/sample-prioritization-through-structural-clustering Skill
16★ repoUse when you have 2D NMR spectral data (HSQC, HMBC, COSY) from multiple samples in a natural products screening campaign and need to rank samples by structural novelty or identify which samples share common molecular scaffolds.
eduwxyz/my-awesome-skills/skills/interview-to-spec Skill
no license15★ repoConduct a focused interview to draft a spec.md for an upcoming task (the input step of SDD — spec-driven development). Walks through goal, behaviors, acceptance criteria, edge cases, and out-of-scope one branch at a time, then writes the spec to disk. If during the interview the scope turns out to be multiple independent features, pauses and asks the user to pick one — the chosen one becomes the spec, the rest stay outside the repo. Trigger when the user wants to draft a spec before implementation, mentions "draft the spec", "let's spec this out", "what should we build", or starts an SDD workflow.
eduwxyz/my-awesome-skills/skills/spec-approach Skill
no license15★ repoAdd a refined `## Approach` section to an existing feature spec.md before TDD executes it. Reads the spec, explores the codebase to ground the approach in real modules and patterns, proposes 2–3 alternatives when they exist, validates with the user, then appends `## Approach` to the same spec file. Trigger after `interview-to-spec` for non-trivial features when the user says "plan the approach", "spec the implementation", "design the approach", "how are we building this", or before invoking `tdd` on a feature whose HOW is unclear.
domengabrovsek/claude/skills/spec Skill
no license15★ repoDefine requirements before planning. Use when starting a new feature, when requirements are ambiguous, or when the user says 'write a spec' or 'define requirements'.
domengabrovsek/claude/skills/to-issues Skill
no license15★ repoBreak a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
ilyautov/small-business-ru/small-business-ru/skills/content-strategy Skill
15★ repoАнализирует данные о продажах из ~~платежи и ~~бухгалтерии (ЮKassa, 1С, МойСклад), находит хиты и зависшие позиции, накладывает сезонность и выдаёт приоритизированный контент-бриф на 30 дней: что продвигать, какие акции запускать, что придержать. На выходе только стратегия — без календарей и макетов. Используй, когда владелец спрашивает «что постить», просит контент-план, спрашивает «что продаётся» или «что продвигать в этом месяце». Триггеры: "контент-план", "что постить", "что продвигать", "что продаётся", "план на месяц".
ilyautov/small-business-ru/small-business-ru/skills/friday-brief Skill
15★ repoВыдаёт пятничный пульс конца недели — выручка против прошлой недели, топ-продавцы, победы и точки наблюдения. Принимает необязательное окно обзора 7 или 14 дней. Триггеры: «итоги недели», «бриф на пятницу», «чем закончилась неделя», «победы и наблюдения».
ilyautov/small-business-ru/small-business-ru/skills/monday-brief Skill
15★ repoСобирает одностраничный бриф на утро понедельника — деньги, продажи, воронка, неделя впереди, три главных дела. Принимает необязательные аргументы: куда отправить и куда сохранить. Триггеры: «утренний бриф», «бриф на понедельник», «с чего начать неделю», «введи в курс на неделю».
ilyautov/small-business-ru/small-business-ru/skills/plan-payroll Skill
15★ repoПрогнозирует деньги, ранжирует просроченные счета, готовит напоминания об оплате и считает фонд зарплаты с налогами РФ 2026 — чтобы собственник уверенно выплатил зарплату сотрудникам. Принимает необязательные аргументы горизонта и даты выплаты. Триггеры: «хватит ли на зарплату», «спланируй зарплату», «посчитай фонд оплаты труда», «когда платить аванс и расчёт», «сколько уйдёт на взносы и НДФЛ».
ilyautov/small-business-ru/small-business-ru/skills/sales-brief Skill
15★ repoВыносит топовых и слабых продавцов, находит сезонные паттерны и собирает двухнедельный контент-бриф, чтобы продвигать лидеров и распродавать залежавшееся. Принимает необязательное окно обзора 30, 60 или 90 дней. Триггеры: «что продаётся», «разбор продаж», «контент-план по товарам», «что продвигать на этой неделе».
viktorbezdek/skillstack/cloud-finops/skills/cloud-finops Skill
15★ repoExpert FinOps guidance covering cloud, AI, SaaS, and adjacent technology spend. Includes AI cost management, GenAI capacity planning, AI-powered FinOps automation, Anthropic billing, AWS (EC2, Bedrock, Savings Plans, CUR, commitment strategy), Azure (reservations, Savings Plans, AHB, OpenAI PTUs, portfolio liquidity), GCP (Vertex AI, Compute Engine, BigQuery), Kubernetes and container FinOps (OpenCost, Kubecost), serverless FinOps (Lambda, Functions, Cloud Run), data platforms (Kafka/MSK, Elasticsearch/OpenSearch, Redis/Valkey), multi-cloud normalization (FOCUS specification), tagging governance, SaaS management (SAM, licence optimisation, SMPs, shadow IT), AI coding tools (Cursor, Claude Code, Copilot, Windsurf, Codex), ITAM, Databricks, Snowflake, OCI, and GreenOps. Use for any query about technology cost, commitment portfolio management, rightsizing, cost allocation, SaaS sprawl, AI dev tool spend, container cost attribution, serverless optimization, multi-cloud strategy, or connecting spend to business value. NOT for general cloud architecture decisions, application performance tuning, or security/compliance reviews — use the relevant architecture, performance, or security skills for those. Built by OptimNow and Viktor Bezdek.