Skills your agents can run

Invoke the installed `atlas` command-line tool from any working directory to access Atlas capabilities built on PocketBase. Use this skill when a user requests bookkeeping actions such as record an entry, add income, add expense, query accounts, query transactions, view expenses, view income/expense, summarize income and expenses, analyze category breakdowns, or delete/modify bookkeeping records. Also use this skill when Codex needs to log into PocketBase, list which Atlas modules are available, invoke a module command, or call Atlas from another skill/agent in a stable `--output json` form. Treat `txns` as a currently implemented module, but do not assume it will always be the only module.

Interpret logs from baseline/test/lint commands and produce a structured triage report.

Manage CelerData BYOC cluster disk (volume) configuration — modify volume size, count, IOPS, and throughput for FE, BE, and Warehouse modules. Requires celerdata-shared skill.

Consultation of Argentine legislation: National Constitution (CN), Penal Code (CP) and Civil and Commercial Code (CCyC). Activates when the user asks about specific articles, constitutional rights, crimes, penalties, contracts, obligations, family, successions, real rights, prescription (statute of limitations), civil liability, or any substantive topic of Argentine law. Also when they say "what does the article say", "penal code", "civil code", "constitution", "is it constitutional", "prescription", "damages", "lease agreement", "consumer rights", "amparo", "habeas corpus", "habeas data", "divorce", "succession", "inheritance", "condominium ownership", "alimony/support", "civil liability", "property crimes", "fraud", "homicide", "Argentine law", "Argentine legislation", "Argentine law".

Convert requirements and architecture into a concrete test plan that includes unit, integration, and end-to-end (E2E) test cases.

Convert Gaussian gjf input files to XYZ format. Use when an agent needs to convert molecular structure files from Gaussian input format (.gjf) to XYZ format for visualization or use with other computational chemistry software.

Turn structured requirements into a phased, dependency-aware implementation plan with clear Definition of Done.

UV-Vis spectrum from SMILES via UV-adVISor (https://spectra.collaborationspharma.com/). Input SMILES, auto-fetch, plot PNG.

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

Convert IUPAC chemical names to SMILES strings. Uses the OPSIN API exclusively and supports intelligent parsing of polymers.

Compute and visualize IR spectra from an input SMILES string or XYZ file using MLatom.

j-cli (work-copilot) command-line tool for daily workflow automation. TRIGGER when the user wants to: (1) manage daily/weekly reports (daily/weekly reports), (2) manage todo items (todos), (3) open apps or URLs via aliases, (4) register/manage app aliases (aliases), (5) create or run preset scripts (scripts/concat), (6) install or check j-cli availability. DO NOT TRIGGER for general shell commands unrelated to j-cli.

Notion API for creating and managing pages, databases, and blocks.

Predict small-molecule pKa values, supporting a custom heuristic backend and a Uni‑pKa single-file weights backend (Bohrium notebook workflow).

name: curaden-communications description: This skill should be used when the user wants to "run the weekly sync", "sync RevolveNote to GitHub", "push revolvenote", "sync Jira to Notion", "update BO..."

ADME property prediction tool. Predicts molecular absorption, distribution, metabolism, and excretion properties, including Caco-2 permeability, PAMPA, HIA, Pgp inhibition, bioavailability, lipophilicity, and more. Uses Morgan fingerprints + Random Forest/XGBoost. Triggered when a user mentions ADME prediction, drug properties, permeability, absorption, metabolism, etc.

XRD spectrum from a CIF structure file using pymatgen (Cu Kα).

Provides reference surface tension predictions for surfactant-related tasks based on SMILES, supporting a baseline heuristic backend and a public_joblib public-model backend.

Predict multiple physicochemical properties of small molecules (boiling point, refractive index, density, viscosity, surface tension, etc.). Currently integrated with the bamboo_mixer single-molecule property model backend.

Plausible Analytics is a lightweight, open-source, privacy-friendly alternative to Google Analytics. It requires no cookies, is fully GDPR/CCPA/PECR compliant, and provides a clean single-page dashboard with all essential website metrics and traffic insights.