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

16,980 results · page 157 of 566

  • alias-resolutionSkillDev tools

    SOP for detecting and resolving concept aliases — merge duplicate pages,

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • alternative-analysisSkillDev tools

    'Strategy: What-If Analysis, Alternative Futures, and Four Ways of Seeing

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • alternative-futuresSkillDev tools

    Generate 2-4 divergent scenarios from the same evidence base, each representing

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • alternative-scoringSkillDev tools

    Score each candidate alternative against all criteria to produce a score

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • alternatives-generationSkillDev tools

    Generate alternatives for every known approach — ensure no approach goes

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • analogical-transferSkillDev tools

    Systematic structure-mapping from source to target domain (Gentner).

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • analogy-chainSkillDev tools

    Chain analogies to deeper levels (3-5 layers). Each layer reveals new

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • analogy-extractionSkillDev tools

    Extract transferable structural principles from source domains. Orchestrates

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • analogy-quality-assessmentSkillDev tools

    Assess analogy depth (surface/structural/systemic). Determines whether

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • and-or-decomposeSkillDev tools

    KAOS-style recursive goal decomposition. AND decomposition for sub-goals

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • anomaly-characterizationSkillDev tools

    SOP: Describe and classify anomalous phenomena that existing theory cannot explain

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • anomaly-driven-abductionSkillDev tools

    'Tactic: Inductive/abductive path — describe anomalous phenomena, generate

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • anti-benchmarkSkillDev tools

    Challenge industry best practices' hidden assumptions. Deconstruct benchmarks

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • appreciative-reframingSkillDev tools

    Find positive deviants and reframe the problem from deficit-based to

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • appropriateness-boundingSkillDev tools

    Establish acceptability standards through RAND/UCLA Appropriateness Method

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • ara-compileSkillDev tools

    SOP: Turn the feeding plan into the compiler''s $ARGUMENTS and run the external ARA compiler once inline to produce ../ara/

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • ara-rigor-reviewSkillDev tools

    SOP: Run the external ARA rigor-reviewer (Seal Level 2, six-dimension semantic review) over ../ara/ and pass its level2_report.json to the user

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • argument-crystallizationSkillDev tools

    Distill the strongest arguments from each perspective through Argument

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • argument-extractionSkillDev tools

    Extract and steel-man the core arguments supporting a given opinion cluster.

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • argument-mappingSkillDev tools

    Campaign for mapping argument structures — extract claims, link evidence,

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • argument-synthesisSkillDev tools

    Strategy for synthesizing argument positions — aggregate evidence, resolve

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • argument-visualizationSkillDev tools

    SOP for generating argument structure visualization — query graph for

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • artifact-detectionSkillDev tools

    Detect annotation artifacts and shortcuts in benchmarks

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • ask-constraintsSkillDev tools

    Understand hard boundaries on the user's research — target venues, methodology

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • ask-decomposition-validationSkillDev tools

    Present the GoalTree to the user for confirmation. Ask about reasonableness,

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • ask-obstacle-acceptanceSkillDev tools

    Present obstacles with their severity assessments and proposed mitigations

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • assess-obstacle-severitySkillDev tools

    Rate each identified obstacle's difficulty — overcomability, time cost,

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • assignee-normalizationSkillDev tools

    Standardize assignee names and identify corporate group affiliations

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • assumption-cascadeSkillDev tools

    'Tactic: Surface assumptions, sort by dependency, attack root assumptions

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 stars

    View details
  • assumption-cascade-tracerSkillDev tools

    Build assumption dependency graphs and trace cascade failures when root

    Ready to connect★ 469

    github.com/yogsoth-ai/de-anthropocentric-research-engine417 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.

53,462 of the 53,895 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