Comentaris
Comentaris i anotacions del codi
ensembl-database
jaechang-hits
"Query Ensembl REST API for gene/transcript/variant annotations across 300+ species. Retrieve gene info by symbol/ID, sequence, cross-references (HGNC, RefSeq, UniProt), variants, regulatory features, comparative genomics. For bulk local access use pyensembl; for pathway lookups use kegg-database or reactome-database."
bedtools-genomic-intervals
jaechang-hits
"Toolkit for genomic interval operations on BED, BAM, GFF, VCF files. Find overlapping regions, merge adjacent intervals, calculate coverage depth, extract FASTA sequences, find nearest features, and manipulate interval coordinates. Essential for ChIP-seq peak annotation, target region filtering, and genome arithmetic. Use tabix instead for indexed single-region queries; use deeptools for normalized bigWig coverage."
self-media-compliance-review
JuneYaooo
"Use when auditing self-media videos, scripts, covers, subtitles, voiceover, product links, account copy, comments, articles, or publishing packages for platform violation risk; especially before final delivery or publishing after video production or clipping. Supports WeChat Channels, WeChat Official Accounts, Douyin, Kuaishou, Bilibili, Xiaohongshu, TikTok, and other platforms."
architectural-analysis
pedronauck
Deep architectural audit focused on finding dead code, duplicated functionality, architectural anti-patterns, type confusion, and code smells. Use when user asks for architectural analysis, find dead code, identify duplication, or assess codebase health.
clinpgx-database
jaechang-hits
"Query PharmGKB (Clinical Pharmacogenomics) database via REST API for drug-gene interactions, clinical annotations, dosing guidelines (CPIC, DPWG), variant-drug associations, and pharmacogenomic pathways. Search by gene, drug, rsID, or pathway. No authentication required. For somatic cancer pharmacogenomics use cosmic-database or opentargets-database; for drug structures use chembl-database-bioactivity."
bioservices-multi-database
jaechang-hits
Unified Python interface to 40+ bioinformatics web services via bioservices library. Query UniProt proteins, KEGG pathways, ChEMBL/ChEBI/PubChem compounds, run BLAST searches, map identifiers across databases, retrieve GO annotations, and find protein-protein interactions. For single-database deep queries use dedicated tools (gget for Ensembl, pubchempy for PubChem); bioservices excels at cross-database integration workflows.
celltypist-cell-annotation
jaechang-hits
"Automated cell type annotation for scRNA-seq data using pre-trained logistic regression models. CellTypist ships 45+ models covering immune cells, gut, lung, brain, fetal tissues, and cancer microenvironments. Inputs a normalized AnnData; outputs per-cell predicted labels, majority-vote cluster labels, and confidence scores. Use when you want fast, reproducible, reference-model-backed annotation without manual marker inspection."
documenting-python-libraries
wdm0006
Creates comprehensive Python library documentation including Google-style docstrings, Sphinx setup, API references, tutorials, and ReadTheDocs configuration. Use when writing docstrings, setting up Sphinx documentation, or creating user guides for Python libraries.
sync-findings
Agenta-AI
Sync the findings record against local review artifacts and optionally a GitHub PR. Accept optional path and GitHub PR url; when url is provided, sync against both remote PR state and local state, otherwise default to local-only sync. Default to path=infer. Confirm effective variables before starting.
write-docs
Agenta-AI
Use when writing or editing documentation pages (concept pages, how-to guides, API reference prose, tutorials) under docs/. Provides the writing style, voice, and structural rules for Agenta docs. Apply this skill before drafting any new docs page, and include it in the brief for any subagent tasked with writing docs.
review-paper
pedrohcgs
Comprehensive manuscript review with three modes: single-pass (default), --adversarial critic-fixer loop, and --peer [journal] simulated peer-review pipeline (editor + 2 dispositioned referees + editorial decision, calibrated to a target journal). R&R continuation via --peer --r2/--r3; hostile-editor stress test via --peer --stress; reviewer-disposition variance reporting via --peer --variance N. Auto-invokes /review-r + /audit-reproducibility on referenced scripts unless --no-cross-artifact.
respond-to-eval
pedrohcgs
Turn student course evaluations (free-text + numeric) into an actionable teaching-improvement plan — the teaching analogue of /respond-to-referees. Clusters comments into themes, separates signal from noise, classifies each theme Keep / Change / Investigate / Out-of-scope, and drafts concrete changes mapped to the syllabus and slide decks. Use when user says "respond to my evals", "what do these course evaluations tell me", "turn my teaching feedback into a plan", or after a semester's evals arrive.
respond-to-referees
pedrohcgs
Generate a structured response-to-referees document from a referee report and the revised manuscript. Maps each referee comment to the specific revision, classifies coverage (addressed / partially / deferred / disagreement), and drafts polite but firm responses. Use during the R&R (revise-and-resubmit) stage of paper revision.
r-package-check
pedrohcgs
Run the full R package release gate — regenerate docs, run the test suite, run R CMD check --as-cran, and triage every ERROR / WARNING / NOTE against CRAN policy before a release or submission. Use when the user says "check my R package", "R CMD check", "is this package CRAN-ready", "run devtools::check", "prepare for CRAN submission", or points at a directory containing a DESCRIPTION file. Produces a check report + CRAN-submission checklist in quality_reports/.
github-pr-reviewer
OpenHands
Create an automation that reviews GitHub pull requests when a configurable trigger label is applied. Polls GitHub deterministically, starts one OpenHands review conversation per label event, inspects full repository and PR context, and posts the final review comment back to GitHub.
Character / CHARAL Audit
matiaszanolli
"Deep audit of CHARAL — the per-game character ruleset → canonical ActorValues/Level/Perks layer: derived-stat formulas, leveling models, skill/attribute rosters, regen + affliction + reputation systems, population boundary"
ECS Audit
matiaszanolli
"Deep audit of the ECS — storage backends, queries, world, systems, resources"
Incremental / Delta Audit
matiaszanolli
"Delta audit — check only recently changed code for regressions and new bugs"
Audio Subsystem Audit (M44)
matiaszanolli
"Deep audit of the M44 audio subsystem — kira backend, spatial sub-tracks, listener/unit seam, reverb send, underwater filter, streaming music — plus its engine callers (footsteps, water audio, reverb zones, REGN ambient music)"
gene-database
jimmc414
"Query NCBI Gene via E-utilities/Datasets API. Search by symbol/ID, retrieve gene info (RefSeqs, GO, locations, phenotypes), batch lookups, for gene annotation and functional analysis."
audit-comments
mycelium-io
Cheap-model audit of comments and inline docs for temporal/historical narration, overly long prose, over-referencing of GitHub issues / PR numbers / plan-step IDs, and design-justification / conversational residue (comments that defend the approach or echo how the code was steered instead of plainly describing it). Defaults to the current PR diff; pass --all to sweep the whole codebase, --fix to apply the rewrites. Use when the user says "audit comments", "comment cleanup", "tidy comments", "check the comments", or "audit-comments".
Session Close
matiaszanolli
"End-of-session ritual — diff stated facts against ground truth and propose synchronised edits across ROADMAP.md / HISTORY.md / README.md"
Fix Issue Pipeline
matiaszanolli
"Fetch a GitHub issue, investigate, plan, implement, test, and commit the fix"
Tech-Debt Audit
matiaszanolli
"Audit accumulated technical debt — stale markers, dead code, duplication, magic numbers, stub impls, doc rot, oversized files"