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: AI & models

9,019 results · page 104 of 301

  • principle-minimize-reader-loadSkillAI & models

    Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.

    Ready to connect★ 341

    github.com/michael-denyer/pstack-claude370 stars

    View details
  • principle-never-block-on-the-humanSkillAI & models

    Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.

    Ready to connect★ 341

    github.com/michael-denyer/pstack-claude370 stars

    View details
  • principle-outcome-oriented-executionSkillAI & models

    Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.

    Ready to connect★ 341

    github.com/michael-denyer/pstack-claude370 stars

    View details
  • principle-sequence-verifiable-unitsSkillAI & models

    Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.

    Ready to connect★ 341

    github.com/michael-denyer/pstack-claude370 stars

    View details
  • principle-subtract-before-you-addSkillAI & models

    Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.

    Ready to connect★ 341

    github.com/michael-denyer/pstack-claude370 stars

    View details
  • principle-test-behavior-not-implementationSkillAI & models

    Apply when you write, change, or keep a test. Call the code the way its users do and assert the result they observe against a literal expected value. If the test would still pass when every imported function returns undefined, rewrite the assertion or delete the test.

    Ready to connect★ 341

    github.com/michael-denyer/pstack-claude370 stars

    View details
  • principle-type-system-disciplineSkillAI & models

    Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.

    Ready to connect★ 341

    github.com/michael-denyer/pstack-claude370 stars

    View details
  • swarmSkillAI & models

    Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.

    Ready to connect★ 341

    github.com/michael-denyer/pstack-claude370 stars

    View details
  • teachSkillAI & models

    Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.

    Ready to connect★ 341

    github.com/michael-denyer/pstack-claude370 stars

    View details
  • unslopSkillAI & models

    Cut AI tells from any writing. Must always apply.

    Ready to connect★ 341

    github.com/michael-denyer/pstack-claude370 stars

    View details
  • clear-allSkillAI & models

    Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.

    Ready to connect★ 369

    github.com/reflexioai/reflexio354 stars

    View details
  • integrate-reflexioSkillAI & models

    Integrate Reflexio Enterprise into an existing AI agent application by retrieving learned context, publishing completed interactions, and optionally routing evaluation setup. Use when a developer asks to add, install, wire, verify, or evaluate Reflexio in an agent codebase; do not use for operating

    Ready to connect★ 369

    github.com/reflexioai/reflexio354 stars

    View details
  • reflexioSkillAI & models

    Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.

    Ready to connect★ 369

    github.com/reflexioai/reflexio354 stars

    View details
  • reflexio-embeddedSkillAI & models

    Captures user facts and procedural corrections into .reflexio/ so the agent learns across sessions. Use when: (1) user states a preference, fact, config, or constraint; (2) user corrects the agent and confirms the fix with an explicit 'good'/'perfect' or by moving on without re-correcting for 1-2 tu

    Ready to connect★ 369

    github.com/reflexioai/reflexio354 stars

    View details
  • restartSkillAI & models

    Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.

    Ready to connect★ 369

    github.com/reflexioai/reflexio354 stars

    View details
  • showSkillAI & models

    Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.

    Ready to connect★ 369

    github.com/reflexioai/reflexio354 stars

    View details
  • claude-codex-fallbackSkillAI & models

    Implements a fallback for CLI automation that uses the default model and automatically re-runs with a different CLI when the usage limit is hit.

    Ready to connect★ 364

    github.com/bam-bam-2/solo-skills365 stars

    View details
  • style-skill-creatorSkillAI & models

    Creative writing skill for creating style skills that teach Claude to write in specific styles. Use when you want to create style guides that Claude can follow when writing long-form content. Creates AI-directive style guides based on analyzing existing writing samples. 트리거: "내 글체로 스킬 만들어줘", "문체 스킬

    Ready to connect★ 364

    github.com/bam-bam-2/solo-skills365 stars

    View details
  • voice-dna-creatorSkillAI & models

    Analyze writing samples to create a comprehensive voice DNA profile. Use when the user wants to capture their unique writing voice, needs to create a voice profile for AI content, or is setting up a new writing system. 트리거: "내 글체 분석해줘", "보이스 DNA", "내 스타일로 써줘", "/voice-dna-creator". 산출물이 Claude용 글쓰기

    Ready to connect★ 364

    github.com/bam-bam-2/solo-skills365 stars

    View details
  • adaptyv-bioSkillAI & models

    API + Python SDK for ordering cell-free protein expression and binding assays. Submit sequences for expression (10–100 µg), measure binding affinity (KD) against targets, track status, and retrieve results programmatically — no wet-lab setup. Built for ML-guided directed evolution and antibody/nanob

    Ready to connect★ 363

    github.com/jaechang-hits/sciagent-skills363 stars

    View details
  • aeonSkillAI & models

    scikit-learn compatible Python toolkit for time series ML: classify, cluster, regress, segment, transform with 30+ algorithms (ROCKET, InceptionTime, KNN-DTW, HIVE-COTE, WEASEL). Handles panel, multivariate, and unequal-length series. Maintained successor to sktime. Alternatives: sktime (larger ecos

    Ready to connect★ 363

    github.com/jaechang-hits/sciagent-skills363 stars

    View details
  • arboreto-grn-inferenceSkillAI & models

    GRN inference from expression via GRNBoost2 (gradient boosting) or GENIE3 (Random Forest). Load matrix, filter by TFs, infer TF-target-importance links, save network. Dask-parallelized to single-cell scale. Core SCENIC component.

    Ready to connect★ 363

    github.com/jaechang-hits/sciagent-skills363 stars

    View details
  • benchling-integrationSkillAI & models

    Benchling R&D Python SDK: CRUD on registry entities (DNA, RNA, proteins, custom), inventory, ELN, workflow automation. Needs Benchling account and API key. Use biopython for local sequence analysis; pubchem for chemical DBs.

    Ready to connect★ 363

    github.com/jaechang-hits/sciagent-skills363 stars

    View details
  • biopython-molecular-biologySkillAI & models

    Molecular biology toolkit: sequence manipulation, FASTA/GenBank/PDB I/O, NCBI Entrez, BLAST automation, pairwise/MSA alignment, Bio.PDB, phylogenetic trees. Use for batch processing, custom pipelines, format conversion, PubMed/GenBank queries. For quick gene lookups use gget; for multi-service REST

    Ready to connect★ 363

    github.com/jaechang-hits/sciagent-skills363 stars

    View details
  • biopython-sequence-analysisSkillAI & models

    Biopython sequence analysis: parse FASTA/FASTQ/GenBank/GFF (SeqIO), NCBI Entrez (esearch/efetch/elink), remote/local BLAST, pairwise/MSA alignment (PairwiseAligner, MUSCLE/ClustalW), phylogenetic trees (Phylo). Use for gene family studies, phylogenomics, comparative genomics, NCBI pipelines. For PCR

    Ready to connect★ 363

    github.com/jaechang-hits/sciagent-skills363 stars

    View details
  • cancer-research-figure-guideSkillAI & models

    Cancer Research (AACR) figures: resolution (300-1200 DPI), formats (EPS/TIFF/AI), hierarchical panel labels (Ai, Aii, Bi), figure/table limits, legend requirements with replicate counts.

    Ready to connect★ 363

    github.com/jaechang-hits/sciagent-skills363 stars

    View details
  • cellchat-cell-communicationSkillAI & models

    Infer and visualize intercellular communication from scRNA-seq with CellChat (R). Build CellChat from Seurat/counts → subset CellChatDB ligand-receptor pairs → over-expressed genes per group → communication probabilities → pathway signaling → network centrality (senders/receivers/influencers) → chor

    Ready to connect★ 363

    github.com/jaechang-hits/sciagent-skills363 stars

    View details
  • cicd-supply-chainSkillAI & models

    Use when attacking or auditing a CI/CD pipeline or software supply chain — pwn requests, poisoned pipeline execution, compromised/mutable-tag actions, dependency confusion, registry worms, runner backdoors, OIDC trust abuse, SLSA/provenance

    Ready to connect★ 363

    github.com/hypnguyen1209/offensive-claude362 stars

    View details
  • datamol-cheminformaticsSkillAI & models

    Pythonic RDKit wrapper with sensible defaults for drug discovery. SMILES parsing, standardization, descriptors, fingerprints, similarity, clustering, diversity selection, scaffold analysis, BRICS/RECAP fragmentation, 3D conformers, and visualization. Returns native rdkit.Chem.Mol. Prefer datamol for

    Ready to connect★ 363

    github.com/jaechang-hits/sciagent-skills363 stars

    View details
  • general-figure-guideSkillAI & models

    Universal QA checklist for generated scientific plots: overlapping labels, clipped text, missing axes/legends, overcrowded data, and cross-journal resolution/format guidance.

    Ready to connect★ 363

    github.com/jaechang-hits/sciagent-skills363 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.

54,764 of the 55,196 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