ahel is live on Product Hunt today. Upvote

Skills.

Give your AI a better way to work.

A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.

Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.

Category: Dev tools

16,833 results · page 259 of 562

  • chem-sorption-widomSkillDev tools

    Calculates Henry coefficient and heat of adsorption for a gas in a porous framework using Widom insertion with any supported MLIP.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • chem-thermochemistrySkillDev tools

    Compute gas-phase thermodynamic quantities (H, S, G) and reaction thermochemistry (ΔH, ΔS, ΔG) using MLIPs with the ideal-gas/rigid-rotor/harmonic-oscillator approximation.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • chem-ts-optimizationSkillDev tools

    Optimize non-periodic molecular TS guesses and verify first-order saddle point from vibrational modes.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • chem-vibrationSkillDev tools

    Calculate vibrational frequencies, normal modes, zero-point energy, and IR spectra of molecules and clusters using MLIPs.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • drug-admet-predictionSkillDev tools

    Compute RDKit physicochemical descriptors and rule-based drug-likeness heuristics (Ro5, Veber, QED) from SMILES.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • drug-bioactivity-assaySkillDev tools

    Fetch biological assays and target proteins a chemical has been tested against via PubChem.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • drug-complex-system-builderSkillDev tools

    Build a solvated, charge-neutralized protein-ligand complex for OpenMM molecular dynamics simulation. Combines a prepared receptor PDB and ligand SDF, parameterizes the ligand with OpenFF Sage or GAFF (AM1-BCC charges), applies Amber ff14SB to the protein, solvates with explicit water, and adds coun

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • drug-db-chemblSkillDev tools

    Query ChEMBL web services for targets, molecules, and curated bioactivity measurements (IC50, Ki, EC50, etc.).

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • drug-db-pubchemSkillDev tools

    Query PubChem via PUG-REST to retrieve CIDs, computed properties, synonyms, and 2D/3D SDF structures.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • drug-molecular-fingerprintsSkillDev tools

    Compute Morgan/ECFP fingerprints, Tanimoto similarity, and optional Butina clusters/heatmaps for small-molecule comparison.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • drug-pose-validationSkillDev tools

    Validate docked or generated ligand poses for physical plausibility using PoseBusters, filtering out chemically invalid or clashing poses before downstream refinement.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • drug-protein-prepSkillDev tools

    Prepare macromolecular receptor structures (PDB/mmCIF or RCSB PDB ID) for docking or simulation by fixing common structure issues and adding hydrogens.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • drug-redocking-rmsdSkillDev tools

    Compute symmetry-corrected heavy-atom RMSD between docked poses and a reference crystal ligand to validate docking protocols.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • drug-retrosynthesisSkillDev tools

    Predict synthetic accessibility and retrosynthetic pathways for novel molecules using the IBM RXN API.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • drug-trajectory-analysisSkillDev tools

    Analyze a protein-ligand MD trajectory to compute ligand RMSD, pocket RMSF, hydrogen bonds, contact occupancy, and protein-ligand interaction fingerprints over time.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • general-chemical-literatureSkillDev tools

    Retrieve extensive literature (PubMed) and patent associated with a specific chemical compound via PubChem.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • general-chemical-pricingSkillDev tools

    Retrieves averaged elemental prices and provides direct vendor purchase links for elements and precursor compounds.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • general-deep-researchSkillDev tools

    Perform iterative, deep, and comprehensive literature research on a specific materials/chemistry topic.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • general-fair-data-reviewSkillDev tools

    Review a manuscript or code repository for FAIR data compliance (Findable, Accessible, Interoperable, Reusable), producing a structured report with pass/fail per principle and actionable remediation steps.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • general-property-unitsSkillDev tools

    Reference guide for energy, force, and stress units across MLIPs, DFT codes, and ASE, including conversion factors.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • general-workflow-plannerSkillDev tools

    Hierarchically decompose high-level scientific workflows (from literature or user-proposed) into executable sequences of existing SKILLs and MCP tools for the research plan.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • humanizer-ruSkillDev tools

    Russian text editor - removes signs of AI generation, bureaucratic style and filler, preserving facts and adding voice. 38 AI-slop patterns with hard bans (negative parallelisms, em dashes, mathematical signs, tech jargon), a deterministic linter, and detection of copy-paste artifacts from chatbots

    Ready to connect★ 164

    github.com/smixs/humanizer-ru164 stars

    View details
  • mat-amorphizationSkillDev tools

    Generate amorphorized structures from crystalline starting points using a melt-quench MD protocol.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • mat-db-nist-janafSkillDev tools

    Query the NIST Chemistry WebBook (which includes JANAF thermochemical tables) for standard experimental thermochemistry properties.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • mat-defect-energySkillDev tools

    Calculate point-defect formation energies (vacancies, substitutions, interstitials) using MLIPs.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • mat-defect-energy-dftSkillDev tools

    Calculate charged defect formation energies and transition level diagrams using pymatgen-analysis-defects and atomate2 VASP workflows.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • mat-dft-electron-phononSkillDev tools

    Computes electron-phonon coupling to calculate temperature-dependent bandgap renormalization using atomate2.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • mat-dft-electronic-transportSkillDev tools

    Compute electronic transport properties (mobility, conductivity, Seebeck coefficient) using DFT and AMSET via atomate2.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • mat-dft-ferroelectricSkillDev tools

    Calculate the spontaneous ferroelectric polarization across a non-polar to polar structure transition using the Berry Phase method.

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details
  • mat-dft-lobsterSkillDev tools

    Construct computational flows for VASP electronic structure projection via LOBSTER to calculate chemical bonding insights (COHP, atomic charges, DOS).

    Ready to connect★ 164

    github.com/learningmatter-mit/atomisticskills158 stars

    View details

What is a skill?

A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.

53,585 of the 54,017 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.

Install one and every AI you use gets it

Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.

Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.

See how to connect your AI