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
8,700 results · page 47 of 290
- View details
klauselinhalt-und-verbote-pruefenSkillAI & models
Prüft eine AGB-Klausel anhand von Kontrollfähigkeit, gesetzlichen Klauselverboten und Interessenabwägung. Für B2C und B2B; liefert ein Klauselvotum mit Leitbild, Gegenposition und konkreter Rechtsfolge.
Ready to connect★ 2k
- View details
klauselinventar-und-scopeSkillAI & models
Für Klauselinventar und Scope: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Ready to connect★ 2k
- View details
review-assessmentSkillAI & models
For ratings and reviews: assigns standard, burden of proof, and counterargument; result: assessed product with risk and next step.
Ready to connect★ 2k
- View details
warranty-exclusionSkillAI & models
For warranty exclusions: organizes the standard, burden of proof, and counterarguments; result: review product with risk and next step.
Ready to connect★ 2k
- View details
warranty-qualitySkillAI & models
For warranty quality: assigns the standard, burden of proof, and counterargument; result: assessment product with risk and next step.
Ready to connect★ 2k
- View details
lookml_ingestSkillAI & models
Map a LookML view/model/explore into ktx semantic layer sources. Covers the LookML to ktx primitive table, provenance tagging, and three worked examples (overlay, standalone from derived_table, standalone with sql_always_where). Load when the turn contains `.lkml` content.
Ready to connect★ 2k
- View details
adjudicate-reviewSkillAI & models
Turn an incoming set of findings — from an AI reviewer, a referee report, a code review, a linter, or a second model — into verified fixes, without letting a confident misread damage correct work. Every finding is a CANDIDATE until checked against the actual source. Use whenever you receive review c
Ready to connect★ 2k
- View details
audit-reproducibilitySkillAI & models
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.
Ready to connect★ 2k
- View details
capture-environmentSkillAI & models
Snapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lockfiles (renv.lock + sessionInfo.txt, requirements.txt / environment.yml / uv.lock, Stata version + ado package list), records seeds and RNG kind, optionally write
Ready to connect★ 2k
- View details
context-statusSkillAI & models
Show current context status and session health. Use to check how much context has been used, whether auto-compact is approaching, and what state will be preserved.
Ready to connect★ 2k
- View details
deep-auditSkillAI & models
Comprehensive adversarial audit of a theory, proof, math/econ paper, codebase, or set of claims — decompose into components, fan out independent skeptics that must return CONCRETE defects, adjudicate every finding with a separate judge, fix all confirmed defects, then re-verify. Use when correctness
Ready to connect★ 2k
- View details
differential-auditSkillAI & models
Compare two implementations of the same thing — a port (R↔Python↔Stata), a reimplementation, a replication package, a refactor, or a new version against the old — so that agreement means something. Freeze inputs first, inventory every expected output, test the comparator itself, compare every channe
Ready to connect★ 2k
- View details
new-diagramSkillAI & models
Scaffold a new TikZ diagram from the snippet gallery with prevention rules pre-applied (explicit node dimensions, coordinate map, directional edge labels). Compiles standalone, invokes tikz-reviewer with citations from tikz-measurement.md, and loops on revisions until APPROVED.
Ready to connect★ 2k
- View details
new-skillSkillAI & models
Scaffold a new skill that follows this repo's conventions — interviews for purpose, trigger phrases, and tool needs, then writes `.claude/skills/<name>/SKILL.md` from the skill template with frontmatter and body that pass the integrity gates on first try. Use when user says "write a skill", "scaffol
Ready to connect★ 2k
- View details
oracle-reviewSkillAI & models
Run an external frontier-model referee (Claude Code -> GPT-5.6 Sol Pro via the Oracle CLI) on a paper, proof, estimator, or replication package -- and adjudicate what comes back. Use when the user says "send this to oracle", "get an external review", "run a referee round", "deep-check this proof", o
Ready to connect★ 2k
- View details
pedagogy-reviewSkillAI & models
Holistic pedagogical review of a lecture deck (`.qmd` or `.tex`). Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use when user says "pedagogy review", "does this teach well?", "is the flow right?", "will students follow?", "review the narrat
Ready to connect★ 2k
- View details
respond-to-evalSkillAI & models
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 change
Ready to connect★ 2k
- View details
review-paperSkillAI & models
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-edito
Ready to connect★ 2k
- View details
review-rSkillAI & models
Read-only R code review protocol for `.R` scripts. Checks code quality, reproducibility, domain correctness, tidyverse idioms, and professional standards; produces a report without editing. Use when user says "review this R script", "check the R code", "audit the analysis code", "code review on the
Ready to connect★ 2k
- View details
scaffold-exercisesSkillAI & models
Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types. Use when user says "make a problem set on X", "scaffold exercises for this lecture", "create practice problems", "generate homework with a
Ready to connect★ 2k
- View details
seven-pass-reviewSkillAI & models
Mechanize Pattern 15 — the seven-pass adversarial review protocol for academic manuscripts. Spawns 7 forked subagents in parallel (abstract, intro, methods, results, robustness, prose, citations), then synthesizes a prioritized revision checklist. Use for submission-ready or R&R-stage papers where s
Ready to connect★ 2k
- View details
simulation-studySkillAI & models
Scaffold and run a reproducible Monte Carlo simulation study in R — a declared assumption regime, a parameterized DGP, an estimator grid, a seeded replication loop, and a summary of bias, RMSE, empirical SE, coverage, size/power with Monte Carlo standard errors. Use when the user says "run a Monte C
Ready to connect★ 2k
- View details
submission-disclosuresSkillAI & models
Generate the submission-time disclosure block for a manuscript — the AI-use disclosure statement matched to the target journal's policy, CRediT author-contribution roles, conflict-of-interest statement, and data-availability statement. Use when the user says "AI disclosure", "disclosure statement",
Ready to connect★ 2k
- View details
vaccinateSkillAI & models
Qualify a check before it is allowed to clear anything — prove it can detect the failure it is meant to catch. Seeds known defects into a copy of a real artifact plus a clean control, runs the checker, and reports recall and false-positive rate into a qualification ledger. Use when the user says "do
Ready to connect★ 2k
- View details
verify-claimsSkillAI & models
Run Chain-of-Verification (CoVe) on a draft or a block of text with factual claims. Spawns the `claim-verifier` agent in a forked (fresh) context so it never sees the draft — then reports which claims are supported, contradicted, or unverifiable. Use when user says "verify these citations", "check t
Ready to connect★ 2k
- View details
huashu-agent-swarmSkillAI & models
Multi-agent swarm parallel collaboration with pure git self-organization, suited for large project development. Use when the user mentions "蜂群模式", "多agent", "并行开发", or "agent swarm".
Ready to connect★ 2k
- View details
huashu-prompt-saveSkillAI & models
Automatically identifies the Prompt type and saves it by category (technical/content/teaching/product/general). Use when the user mentions "保存prompt", "记录prompt", or "整理prompt".
Ready to connect★ 2k
- View details
golem-add-agent-moonbitSkillAI & models
Adding a new MoonBit agent to a Golem component. Use when the user asks to create, add, or define a new agent type in a MoonBit Golem project.
Ready to connect★ 2k
- View details
golem-add-agent-rustSkillAI & models
Adding a new Rust agent to a Golem component. Use when the user asks to create, add, or define a new agent type, implement an agent trait, or add agent methods in a Rust Golem project.
Ready to connect★ 2k
- View details
golem-add-agent-scalaSkillAI & models
Adding a new Scala agent to a Golem component. Use when the user asks to create, add, or define a new agent type, implement an agent trait, or add agent methods in a Scala Golem project.
Ready to connect★ 2k
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.
52,524 of the 52,958 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.