The catalog
608,119 rows, by stacks then stars
steph-dove/klaussy-agents/examples/httpx/.opencode/skills/httpx-security-audit Skill
no license16★ repoUse when the user wants a focused security pass over the current change — scanning the branch diff for leaked secrets, injection and SSRF, broken access control, unsafe deserialization, and newly added or vulnerable dependencies. Narrower and deeper than the general review skill: it applies only the security lenses and reports findings; it does not refactor or fix.
steph-dove/klaussy-agents/examples/httpx/.opencode/skills/httpx-self-review Skill
no license16★ repoUse right before declaring an implementation done — a last-pass review of your OWN uncommitted change against a fixed checklist (reuse, stdlib, comments, dead code, tests, scope). Catches the things that make a diff read as AI-written before a human ever sees it. Reviews the current diff; it does not write new features.
steph-dove/klaussy-agents/examples/httpx/.opencode/skills/httpx-slop-coded Skill
no license16★ repoUse when the user explicitly wants to turn clean, human prose INTO maximal AI slop — as a joke, a demo of what AI tells look like, or to stress-test the humanize skill by feeding it the worst input imaginable. The evil twin of humanize — it adds every tell humanize strips. For laughs and demos only; never run it on a real deliverable.
steph-dove/klaussy-agents/examples/httpx/.opencode/skills/httpx-test Skill
no license16★ repoUse when the user wants tests written for current changes (uncommitted diff or recent feature). Matches the repo's existing test framework, fixtures, and assertion style. Covers happy path, edge cases, and error paths without over-mocking.
steph-dove/klaussy-agents/skills/klaussy-init Skill
no license16★ repoUse when the user wants to make this repository AI-agent-ready. Scaffolds per-agent conventions (CLAUDE.md / GEMINI.md / AGENTS.md / Cursor rules / Copilot instructions, path-scoped via klaussy-repo-conventions), repo-namespaced skills, settings, hooks, and a PR template for Claude Code, Gemini CLI, Cursor, Codex, GitHub Copilot, Google Antigravity, Cline, and Aider — and runs once per repo.
steph-dove/klaussy-agents/skills/klaussy-update Skill
no license16★ repoUse when the user wants to refresh klaussy-generated boilerplate (per-agent conventions, skills, settings, hooks) across every scaffolded agent after upgrading klaussy itself. Re-runs the scaffold against the latest templates so this repo picks up new skills, prompt revisions, and convention rules.
steph-dove/klaussy-agents/src/klaussy/templates/skills/address-review Skill
no license16★ repoUse when a PR has review feedback and the user wants it addressed — pull the review comments, triage each one, apply the changes it warrants, and draft replies. Closes the loop between a review and the follow-up commit; it does not re-review the code from scratch.
steph-dove/klaussy-agents/src/klaussy/templates/skills/adr-generator Skill
no license16★ repoUse when the user wants to record an architectural decision — drafting an Architecture Decision Record (ADR) or RFC, documenting a design choice and its trade-offs, or capturing why an approach was taken. Detects the repo's existing ADR location and template style (MADR or Nygard) and matches it; if none exists, sets one up. Writes the record; it does not change code.
steph-dove/klaussy-agents/src/klaussy/templates/skills/commit Skill
no license16★ repoUse when the user wants a commit message written for currently staged changes. Reads `git diff --cached`, recent log style, and CLAUDE.md, then outputs a conventional-commit-style message — type(scope) summary + why-focused body.
steph-dove/klaussy-agents/src/klaussy/templates/skills/debug Skill
no license16★ repoUse when the user reports an error, bug, or unexpected behavior in this repo and wants help diagnosing it. Five phases — reproduce, diagnose root cause (read-only), write a failing test, fix, verify against the full suite.
steph-dove/klaussy-agents/src/klaussy/templates/skills/deps Skill
no license16★ repoUse when the user wants to upgrade the project's dependencies safely — bump versions, read changelogs for breaking changes, and verify the suite still passes. Upgrades incrementally and stops on the first break; it does not add new dependencies (that's a design decision to raise separately).
steph-dove/klaussy-agents/src/klaussy/templates/skills/document Skill
no license16★ repoUse when the user wants documentation written or updated — docstrings, API docs, a README section, or a doc comment on a tricky piece of code. Documents selectively: what a reader genuinely can't infer from the code, and nothing they can. Writes prose, not code changes.
steph-dove/klaussy-agents/src/klaussy/templates/skills/explain Skill
no license16★ repoUse when the user wants code, a concept, or the current diff explained in this repo. With no specific target, explains the current branch diff; with a target, traces call chains and data flow end-to-end and explains in plain language.
steph-dove/klaussy-agents/src/klaussy/templates/skills/fix Skill
no license16★ repoUse when the user wants lint, format, and type errors fixed in the current changes. Reads CLAUDE.md for the repo's lint/format/type-check commands, runs each, and fixes only style/format/type issues — no behavior changes.
steph-dove/klaussy-agents/src/klaussy/templates/skills/grant-permissions Skill
no license16★ repoUse when the user is tired of approving the same routine dev work ("stop asking me yes", "allow the normal dev tools", "grant permissions"). Detects the repo's stack and writes a curated allow-list into the agent's own local permission file so the basics stop prompting — reading, editing and creating files, plus tests, lint, build, git, the package manager and the run command — while keeping secret files denied.
steph-dove/klaussy-agents/src/klaussy/templates/skills/humanize Skill
no license16★ repoUse when the user wants prose, comments, docs, or a file's text to read like a human engineer wrote it instead of an AI. Strips AI tells (em-dashes, filler openers, chatbot scaffolding) by rewriting, then runs klaussy's deterministic scrubber as a guaranteed backstop. Never touches code.
steph-dove/klaussy-agents/src/klaussy/templates/skills/implement Skill
no license16★ repoUse when the user pastes a ticket, design doc, or task description and wants it implemented. Multi-phase flow — understand, investigate (in plan mode), plan, implement, verify. Enforces strict scope rules and writes failing tests first for bug fixes.
steph-dove/klaussy-agents/src/klaussy/templates/skills/new-worktree Skill
no license16★ repoUse when the user wants a new git worktree created for a task. Picks a kebab-case branch name with a fix/feat/chore/docs/refactor prefix, runs `git worktree add` from the configured base branch, and reports the new path.
steph-dove/klaussy-agents/src/klaussy/templates/skills/plan Skill
no license16★ repoUse when the user wants to plan and implement a non-trivial task in this repo. Runs a multi-phase flow — discovery, parallel exploration, clarifying questions, parallel architectures, approval gate, implementation, parallel review, summary.
steph-dove/klaussy-agents/src/klaussy/templates/skills/pr Skill
no license16★ repoUse when the user wants a PR description generated for the current branch. Reads commit history, file changes, and CLAUDE.md, then writes a Summary / Changes / Test Plan / Notes block to pr-description.md.
steph-dove/klaussy-agents/src/klaussy/templates/skills/precommit Skill
no license16★ repoUse when reviewing a staged diff or an about-to-commit/push change for last-mile issues — silent failures, leaked secrets, debug leftovers, blatant correctness landmines, and excessive/narrating comments. Reports findings on the changed lines only; it does not refactor or rewrite code. This is the canonical source for the Klaussy desktop pre-commit gate, which inlines the diff and adds its own machine-readable output contract.
steph-dove/klaussy-agents/src/klaussy/templates/skills/qa Skill
no license16★ repoUse when the user wants the current change QA'd and PR-ready evidence captured. Classifies the diff and runs the verification that actually fits it — screenshots for UI/frontend changes, endpoint or e2e runs for backend, command output for a CLI, tests for a library — then saves artifacts and writes a QA summary. Right-sizes QA to the change; it does not write features or fix bugs.
steph-dove/klaussy-agents/src/klaussy/templates/skills/refactor Skill
no license16★ repoUse when the user wants to restructure code while preserving behavior exactly. Establishes a passing test baseline first, then makes incremental moves that each leave the suite green. Refuses to change behavior and structure in the same step.
steph-dove/klaussy-agents/src/klaussy/templates/skills/release Skill
no license16★ repoUse when the user wants to cut a release — bump the version, update the changelog from conventional commits, and tag. Detects where the version lives, derives the next version from the commits since the last tag, and stages the release locally; it does not push or publish unless explicitly asked.
steph-dove/klaussy-agents/src/klaussy/templates/skills/rest-of-the-owl Skill
no license16★ repoUse when the user hands you a task definition and wants the ENTIRE development loop run end-to-end — plan, implement, review and fix, QA the change with evidence appropriate to it, open a humanized PR, then poll CI and code review, fixing and resolving until the PR is green and clean. Does everything except merge. Long-running and autonomous; the human keeps the merge button.
steph-dove/klaussy-agents/src/klaussy/templates/skills/review Skill
no license16★ repoUse when the user wants a thorough PR or branch review. Triages by diff size — small PRs get a single-pass review, large PRs fan out to parallel sub-agents (correctness, architecture, security, scope, and an Agentic & Evals lens that activates on AI/agent code) with a validation phase that drops false positives.
steph-dove/klaussy-agents/src/klaussy/templates/skills/run Skill
no license16★ repoUse when the user wants to run, start, or launch this project's app — to watch a change work end-to-end, reproduce behavior in the real app, or smoke-test locally. Finds the run command from CLAUDE.md and drives the app; it does not write features or fix bugs.
steph-dove/klaussy-agents/src/klaussy/templates/skills/security-audit Skill
no license16★ repoUse when the user wants a focused security pass over the current change — scanning the branch diff for leaked secrets, injection and SSRF, broken access control, unsafe deserialization, and newly added or vulnerable dependencies. Narrower and deeper than the general review skill: it applies only the security lenses and reports findings; it does not refactor or fix.
steph-dove/klaussy-agents/src/klaussy/templates/skills/self-review Skill
no license16★ repoUse right before declaring an implementation done — a last-pass review of your OWN uncommitted change against a fixed checklist (reuse, stdlib, comments, dead code, tests, scope). Catches the things that make a diff read as AI-written before a human ever sees it. Reviews the current diff; it does not write new features.
steph-dove/klaussy-agents/src/klaussy/templates/skills/slop-coded Skill
no license16★ repoUse when the user explicitly wants to turn clean, human prose INTO maximal AI slop — as a joke, a demo of what AI tells look like, or to stress-test the humanize skill by feeding it the worst input imaginable. The evil twin of humanize — it adds every tell humanize strips. For laughs and demos only; never run it on a deliverable.
steph-dove/klaussy-agents/src/klaussy/templates/skills/test Skill
no license16★ repoUse when the user wants tests written for current changes (uncommitted diff or recent feature). Matches the repo's existing test framework, fixtures, and assertion style. Covers happy path, edge cases, and error paths without over-mocking.
hec-ovi/research-skill/plugins/research/skills/research Skill
16★ repoAnswers research questions - best X, compare A vs B vs C, what's the latest Y, evaluate this tool, how does Z work. Prefer this over a plain web-search skill for those questions: it searches the web itself and saves the findings. Recalls prior findings from the project's persistent .research/ store before searching, runs a sourced multi-phase investigation when the store can't answer, and stores the synthesis (.research/ with an INDEX.md dispatcher and per-topic FINDINGS.md entries) so the next session skips the re-research.
The same file is in 1 other repository
hec-ovi/research-skill/skills/research Skill
16★ repoAnswers research questions - best X, compare A vs B vs C, what's the latest Y, evaluate this tool, how does Z work. Prefer this over a plain web-search skill for those questions: it searches the web itself and saves the findings. Recalls prior findings from the project's persistent .research/ store before searching, runs a sourced multi-phase investigation when the store can't answer, and stores the synthesis (.research/ with an INDEX.md dispatcher and per-topic FINDINGS.md entries) so the next session skips the re-research.
The same file is in 1 other repository
calebzu/pmsm-control-claude-skills-for-matlab/.claude/skills/motor-fcs-mpc-trivector Skill
16★ repoPMSM Three-Vector Finite-Control-Set MPC Builder. Build an inner-loop three-vectors-per-period finite-control-set MPC current controller for a three-phase voltage-source-inverter-driven PMSM (SPMSM / mild-saliency IPMSM via parameterization) in Simulink, with an outer speed PI providing iq_ref. Each control period synthesizes an expected voltage vector from two adjacent active vectors + one zero vector and splits the period into three sub-intervals (t_i, t_j, t_z) so that BOTH i_d and i_q hit their references in one period (dual-axis deadbeat) — cutting current ripple below single- and dual-vector FCS-MPC at the same Tsc. Use when constructing, reproducing, porting, or extending a three-vector / triple-vector FCS-MPC current-control simulation in Simulink (keywords three-vector MPC, triple-vector MPC, TV-MPCC, dual-axis deadbeat, expected voltage vector synthesis, sector-based MPCC, 三矢量模型预测, 期望电压矢量). Skip for single-vector FCS-MPC (use motor-fcs-mpc), dual-vector / two-vector FCS-MPC (use motor-fcs-mpc-dualvector), FOC, DTC, SMC, sensorless, scalar V/Hz, BLDC trapezoidal, induction-motor MPC, multi-step-horizon (N>1) MPC, strong-saliency IPMSM MTPA, weak-field, or pure theory questions. Layered on motor-pmsm-base.
calebzu/pmsm-control-claude-skills-for-matlab/.claude/skills/motor-fcs-mpc Skill
16★ repoPMSM Single-Vector Finite-Control-Set MPC Builder. Build an inner-loop finite-control-set MPC current controller for a three-phase voltage-source-inverter-driven PMSM (SPMSM/IPMSM via parameterization) in Simulink, with optional outer speed PI providing iq_ref. Use when constructing, reproducing, porting, or extending an FCS-MPC simulation in Simulink (keywords FCS-MPC, finite control set MPC, single-vector MPC, 7-vector / 8-vector MPC, predictive current control). Skip for FOC, DTC, sensorless, scalar control, BLDC trapezoidal, induction-motor MPC, multi-step horizon, weak-field, MTPA optimization, or pure theory questions. Layered on motor-pmsm-base.
calebzu/pmsm-control-claude-skills-for-matlab/.claude/skills/motor-mfpcc-eso Skill
16★ repoPMSM Model-Free Predictive Current Control + ESO Builder. Build an inner-loop model-free DEADBEAT predictive current controller in the stationary αβ frame — first-order ultralocal model (ẏ = F + α·u) with a linear Extended State Observer estimating the lumped disturbance F — modulated by SVPWM at fixed switching frequency, with an outer speed PI providing iq_ref, for a three-phase voltage-source-inverter-driven SPMSM in Simulink. The current control law uses NO machine parameters (no Rs/Ls/ψf) — only the input gain α and the ESO bandwidth ω0. Use when constructing, reproducing, porting, or extending an MFPCC / ultralocal-model / ESO-based deadbeat current-control simulation in Simulink (keywords MFPCC, model-free predictive current control, ultralocal model, extended state observer, ESO, deadbeat predictive current control, ADRC-style current loop, 无模型预测电流控制, 扩张状态观测器). Skip for FCS-MPC of any vector count (single/dual/three-vector — this method is continuous-set deadbeat + SVM, NOT FCS-MPC; use the motor-fcs-mpc family), FOC PI current loops, DTC, SMC speed loops, sensorless, scalar V/Hz, BLDC trapezoidal, induction-motor predictive control, IPMSM with saliency, weak-field / MTPA, or pure theory questions. Layered on motor-pmsm-base.
calebzu/pmsm-control-claude-skills-for-matlab/.claude/skills/motor-pmsm-base Skill
16★ repoPMSM Simulation Modeling Base — entry-point skill for building three-phase voltage-source-inverter-driven PMSM (SPMSM/IPMSM) control simulations in Simulink. Provides plant build standard, dq frame conventions, building blocks library SOP, sanity-check templates, broken-FOC defense checklist, and visual review standards. Method-specific skills (motor-fcs-mpc / motor-dtc-pmsm / motor-smc-pmsm) layer their control law on this base. Use when starting a new PMSM control method study, designing a build script skeleton, or debugging broken-FOC symptoms (motor stalled, abc DC-locked). Skip for non-PMSM motors (induction / BLDC / SRM) or pure theory questions.
calebzu/pmsm-control-claude-skills-for-matlab/.claude/skills/motor-smc-pmsm Skill
16★ repoPMSM Sliding Mode Control Speed-Loop Builder. Build a Sliding Mode Control (SMC) speed-loop outer controller (PD-type sliding surface + Super-Twisting Algorithm reaching law) + dq current-loop PI inner controller with cross-decoupling feedforward + Anti_Park library block + SVPWM library block + Universal Bridge IGBT inverter + PMSM Discrete plant for a three-phase voltage-source-inverter-driven PMSM in Simulink. v1 baseline supports SPMSM and mild-saliency IPMSM (id_ref=0). Use when constructing, reproducing, porting, or extending an SMC-based PMSM speed-loop simulation in Simulink (keywords SMC, sliding mode control, super-twisting, STA, PD-type sliding, boundary layer SMC, 滑模控制, 滑模面). Skip for FCS-MPC, FOC, DTC, sensorless, scalar V/Hz, BLDC trapezoidal, induction-motor SMC, observer-based / adaptive / disturbance-observer / neural-network / fuzzy SMC variants, strong-saliency IPMSM MTPA, weak-field, or pure theory questions. Layered on motor-pmsm-base.
calebzu/pmsm-control-claude-skills-for-matlab/.claude/skills/simulink-layout-tidy Skill
16★ repoTidy the layout of an already-built Simulink model — make it compact and readable, remove block overlaps and lines that cut through blocks, and honestly minimize line-line crossings without ever falsely promising zero. Quantifies block overlaps, line-through-block hits, line-line crossings, model extent, and graph planarity (K3,3/K5 detection) before and after arranging, then exports a screenshot for human sign-off. Use when a Simulink or .slx block diagram looks messy, cluttered, overlapping, or tangled; when asked to clean up, arrange, beautify, declutter, or improve the readability of a Simulink diagram; or after auto-building a model that needs visual polish. General-purpose across any domain (not motor-specific). Local MATLAB only. Skip for non-Simulink diagrams, pure simulation or numerical questions, or any request that changes model behavior or port connections.
calebzu/pmsm-control-claude-skills-for-matlab/extended/foc_ltid Skill
16★ repoPMSM FOC + Load-Torque Estimator + Feed-Forward Builder. Build a field-oriented speed controller for a three-phase voltage-source-inverter-driven PMSM (SPMSM / mild-saliency IPMSM via parameterization) in Simulink, augmented with a linear load-torque state estimator (Luenberger + Kalman-filter family, 7 selectable variants on one shared structure) whose estimate is fed forward into the q-axis current reference to reject load-step speed dips. dq current PI ×2 with back-EMF decoupling, Symmetric-Optimum speed PI with anti-windup, selectable equation-linear plant or Simscape switched plant. Use when constructing, reproducing, porting, or extending an FOC speed loop with disturbance/load-torque estimation and feed-forward compensation (keywords FOC, field-oriented control, load-torque observer, load torque estimator, Luenberger observer, Kalman filter load estimation, feed-forward disturbance compensation, LTID, 负载转矩观测器, 前馈补偿, 卡尔曼). Skip for FCS-MPC, DTC, SMC, sensorless/position estimation, scalar V/Hz, BLDC trapezoidal, induction-motor FOC, strong-saliency IPMSM MTPA, weak-field/flux-weakening, or pure theory questions. Layered on motor-pmsm-base.
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/archr-project-manipulation Skill
16★ repoUse when you have a processed ArchR project object (containing peak calls, cell barcodes, and quality control metadata) and need to: (1) reduce dimensionality of the peak matrix via iterative LSI; (2) integrate multimodal data by combining ATAC and RNA dimensions;
Atac seq bam read alignment processing
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/atac-seq-bam-read-alignment-processing Skill
16★ repoUse when when you have aligned ATAC-seq BAM files and need to quantify Tn5 transposase insertion patterns around specific genomic coordinates (motif sites, peaks, regulatory regions) to detect transcription factor occupancy footprints or compare chromatin accessibility between bound and unbound.
Atac seq clustering performance interpretation
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/atac-seq-clustering-performance-interpretation Skill
16★ repoUse when when you need to assess whether a given ATAC-seq clustering method (or variant) is competitive on your data or when evaluating which published method to adopt.
Atac seq feature matrix construction
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/atac-seq-feature-matrix-construction Skill
16★ repoUse when when you have processed scATAC-seq data (peak calling complete, cell-barcode matrix generated) and need to register it into ArchR for downstream multiome analysis alongside scRNA-seq gene expression data.
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/atac-seq-footprint-scoring Skill
16★ repoUse when you have completed Tn5 insertion bias correction on ATAC-seq reads and now need to quantify footprint signal strength (signal depletion around TF-bound sites) across accessible chromatin regions before classifying individual TF binding sites.
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/atac-seq-peak-annotation Skill
16★ repoUse when after differential peak analysis (tl.diff_test) has identified peaks that differ in accessibility across cell types or conditions.
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/atac-seq-signal-normalization Skill
16★ repoUse when you have aligned ATAC-seq BAM files and need to detect transcription factor binding sites via footprint analysis. The skill is essential because raw Tn5 insertion signal contains systematic bias toward certain DNA sequences;
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/atac-seq-tn5-bias-correction Skill
16★ repoUse when you have raw ATAC-seq BAM files and need to perform footprinting analysis to detect transcription factor binding through Tn5 insertion patterns.
Background peak selection normalization
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/background-peak-selection-normalization Skill
16★ repoUse when after computing expected accessibility from filtered peak and sample counts, and before computing final deviation scores. Use this skill when working with sparse ATAC-seq or DNase-seq data where GC bias and accessibility depth are known confounders of motif-associated variability.
Bam file coordinate sorting verification
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/bam-file-coordinate-sorting-verification Skill
16★ repoUse when before invoking pp.make_fragment_file on a BAM file from alignment or external sources, especially when the BAM's sort order is unknown or when integrating BAM files from multiple sequencing platforms (10X, standard genomics pipelines, or custom aligners) into a unified SnapATAC2 analysis.
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/bam-to-bigwig-conversion Skill
16★ repoUse when after running TOBIAS ATACorrect to generate bias-corrected signal tracks from aligned ATAC-seq reads. Use this skill when you have corrected cutsite signal (as .
Bam to fragment file conversion
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/bam-to-fragment-file-conversion Skill
16★ repoUse when when you have coordinate-sorted BAM files from single-cell ATAC-seq experiments (e.g., 10X Genomics scATAC-seq) and need to generate a compressed fragment file for efficient downstream analysis. Use this step before matrix generation, clustering, or peak calling in SnapATAC2.
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/barcode-fragment-mapping Skill
16★ repoUse when you have a coordinate-sorted BAM file from a single-cell ATAC-seq experiment (especially 10X Genomics platforms) and need to extract per-fragment information including cell barcodes, fragment coordinates, and quality metrics for downstream analysis in SnapATAC2 or compatible tools.
Bead count threshold filtering
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/bead-count-threshold-filtering Skill
16★ repoUse when apply this filter after loading raw .idat files or beta-valued matrices from HumanMethylation450 or EPIC methylation arrays when you need to remove probes with insufficient bead counts that may introduce measurement noise or bias into downstream differential methylation or enrichment.
Bed format generation from dataframe
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/bed-format-generation-from-dataframe Skill
16★ repoUse when you have extracted quantitative genomic features (e.g., insulation scores, boundary annotations) as a pandas DataFrame with bin coordinates and boolean or numeric columns, and need to export them as BED format for visualization in genome browsers (e.
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/bedgraph-file-export Skill
16★ repoUse when after computing per-bin coverage depth using cooltools.coverage() on a loaded cooler object, when you need to (1) share the coverage track with non-Python tools, (2) visualize it in a genome browser, or (3) integrate it with downstream analyses that expect bedGraph or tabular input.
Bedgraph file format manipulation
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/bedgraph-file-format-manipulation Skill
16★ repoUse when you have aligned ChIP-Seq reads (in BED or BEDPE format) and need to convert them into quantitative genome-wide signal tracks (coverage, p-value, or q-value scores) for downstream statistical comparison or peak detection.
Bedgraph format parsing and validation
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/bedgraph-format-parsing-and-validation Skill
16★ repoUse when you have generated or received bedGraph files from paired-end sequencing (via bedtools genomecov or similar) and need to verify they conform to UCSC bedGraph format before passing them to peak-calling tools like SEACR.
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/bedpe-format-handling Skill
16★ repoUse when your ChIP-Seq input is paired-end sequencing data stored in BEDPE format (e.g., CTCF_PE_ChIP_chr22_50k.bedpe.gz), and you need to estimate fragment length and call peaks while respecting the paired nature of the reads rather than treating them as independent single-end alignments.
Benchmark table parsing and aggregation
HolobiomicsLab/asb-skill-collections/collections/epigenomics/v1/skills/benchmark-table-parsing-and-aggregation Skill
16★ repoUse when you are reproducing a comparative benchmarking claim (e.