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
9,105 results · page 178 of 304
- View details
cre-underwritingSkillAI & models
CRE Underwriting analysis suite — 3 specialist skills for building pro formas, running sensitivity scenarios, and writing investment committee memos for multifamily acquisitions.
Ready to connect★ 92
- View details
knowledge-base-updateSkillAI & models
Use this skill whenever you learn something important during a conversation: a key architectural decision, a project-specific convention, a bug root-cause, a 3rd-party API quirk, or any fact that would help a future agent avoid re-doing the same research. Writes structured entries to the project's k
Ready to connect★ 92
- View details
magpie-dependency-license-auditSkillAI & models
Read-only license audit of a project's direct and transitive dependency tree. Detects the dependency manager(s), resolves each dependency's declared license from ecosystem metadata, classifies each against a configured policy (ASF three-category A/B/X model or a custom allowlist), and surfaces incom
Ready to connect★ 91
- View details
magpie-setupSkillAI & models
Adopt and maintain the apache-magpie framework in a project. Installs from the agent's marketplace by default; the pinned snapshot install is the fallback where no marketplace reaches. Sub-actions: `setup` - first-time install, marketplace-first; snapshot fallback is main-checkout only. `adopt` is a
Ready to connect★ 91
- View details
magpie-setup-isolated-setup-installSkillAI & models
Guide an adopter through the first-time install of the framework's secure agent setup (bubblewrap + socat + claude-code, sandbox/permissions/clean-env layers). Walks every step interactively; never auto-runs sudo, shell-rc edits, or settings overwrites.
Ready to connect★ 91
- View details
magpie-setup-isolated-setup-updateSkillAI & models
Surface drift between the user's installed secure agent setup and the framework's latest (framework checkout, pinned tools, user-scope script copies, denial commands, comdev MCP checkouts). Read-only — surfaces candidates and diffs, never auto-applies. The user decides what to update.
Ready to connect★ 91
- View details
magpie-setup-upstream-fixSkillAI & models
Turn a framework bug or quirk the agent hit while running a Magpie skill or tool into a fix PR against `apache/magpie` — one PR per issue. First confirms the problem is a framework defect (not a local misconfiguration or a stale snapshot), then searches `apache/magpie` for an existing issue or PR th
Ready to connect★ 91
- View details
magpie-write-skillSkillAI & models
Author a new skill for the Apache Magpie framework, or update an existing one. Walks the user through the framework's skill shape (frontmatter, resources, placeholder convention, prompt-injection defences, Privacy-LLM gate-check) and validates via the framework's existing [`tools/skill-and-tool-vali
Ready to connect★ 91
- View details
pr-precheckSkillAI & models
Use when the user invokes `/pr-precheck <repo> <topic>` or — implicitly, before any other skill opens a pull request — to check the target repo's merged and closed PR history for prior attempts at the same fix, so the agent doesn't open the Nth duplicate of an already-rejected approach. Wraps the `v
Ready to connect★ 92
- View details
test-driven-executionSkillAI & models
Before writing any implementation code, define the acceptance criteria and test cases that the code must satisfy. Agents then write code to pass these tests — not to match a vague description. Eliminates "it works on my machine" and "I think this is what you wanted" outcomes.
Ready to connect★ 92
- View details
agent-rig-systemSkillAI & models
AI agents and Nix: parametrable skills/instructions and tools, packaged together in a reproducible and modular fashion
Ready to connect★ 91
- View details
bailoutSkillAI & models
Forcing function — the user invokes `/bailout` when they catch the main agent bailing out: stopping mid-work, asking "waiting for your direction", presenting bailout-laden option lists, deleting code without a next plan, deferring to "next session", citing "weeks of work" without measurement, going
Ready to connect★ 91
- View details
calcSkillAI & models
Lets your agent create spreadsheets, convert between formats like CSV and XLSX, and work with formulas using LibreOffice Calc.
Ready to connect★ 91
- View details
cerfSkillAI & models
The user types `/cerf` to see the index of the project skills. The skill lists each skill in `.claude/skills/`, with one line for each. Then it offers the environment doctor (`setup.ps1 -Check`) and stops. The doctor runs only when the user agrees. The doctor makes sure that the git hooks are active
Ready to connect★ 91
- View details
connection-auth-rulesSkillAI & models
Build a Connection Auth Rules for a Monte Carlo connection type. Fetches live connector schemas and transform steps from the apollo-agent repo.
Ready to connect★ 91
- View details
evo-dicke-model-simulationSkillAI & models
Builds the open Dicke model Hamiltonian and Lindblad collapse operators in the full 2^N tensor product Hilbert space, solves for the steady-state density matrix, and extracts the reduced cavity state via partial trace.
Ready to connect★ 91
- View details
evo-glm-simulationSkillAI & models
Run the General Lake Model (GLM v3) for Lake Mendota — edit glm3.nml, execute the GLM binary, parse NetCDF output (depth = z_surface - z_layer), match to field observations, compute RMSE, and iteratively calibrate Kw, sw_factor, wind_factor, coef_mix_hyp to achieve RMSE < 2°C.
Ready to connect★ 91
- View details
evo-grid-dispatch-operatorSkillAI & models
End-to-end DC Optimal Power Flow with spinning reserve co-optimization. Parses MATPOWER JSON network data, builds DC power flow model with bus voltage angles, formulates and solves the DCOPF+reserve QP/LP via cvxpy (CLARABEL solver), computes line loading and operating margins, and produces a struct
Ready to connect★ 91
- View details
evo-macro-demand-shock-scenariosSkillAI & models
Builds demand-side investment shock model on NA sheet with bell-shaped spending, currency conversion, deflation, import adjustment, multiplier. Creates 3 scenarios.
Ready to connect★ 91
- View details
evo-r2r-linearizationSkillAI & models
Derives linearized state-space model (A, B matrices) for 6-section R2R system, computes steady-state operating points, discretizes, and computes LQR gain.
Ready to connect★ 91
- View details
evo-seismic-phase-pickingSkillAI & models
Runs SeisBench deep learning models (PhaseNet/EQTransformer) on grouped station waveforms to produce P and S phase picks with timestamps and probabilities.
Ready to connect★ 91
- View details
meshy-3d-printingSkillAI & models
3D print models generated with Meshy AI, plus Creative Lab consumer products. Handles slicer detection, white model printing, multi-color printing via API, the Creative Lab pipeline (figure / lamp / keychain / fridge-magnet), and print-optimized download workflows. Use when the user mentions 3D prin
Ready to connect★ 90
- View details
monte-carlo-asset-healthSkillAI & models
Check the health of a data table/asset using Monte Carlo. Activates on "how is table X", "check health of X", "is X healthy", "status of X", "check on X table", or any health/status question about a data asset.
Ready to connect★ 91
- View details
monte-carlo-reinforce-agentSkillAI & models
Reinforces an AI agent by turning Monte Carlo's reinforcement loop diagnosis into code fixes. Reads the daily reinforcement loop report for an agent's workflows, ranks the diagnosed issues, proposes what to fix, and — with the user's approval at each step — opens a pull request. Activates on "fix my
Ready to connect★ 91
- View details
niceSkillAI & models
Positive reinforcement signal - the user invokes `/nice` when the main agent has been working well in the recent stretch: following CLAUDE.md rules, citing references before writing code, hooking before theorizing, pasting evidence not commentary, surfacing concrete useful findings (decompile result
Ready to connect★ 91
- View details
nix-module-systemSkillAI & models
AI agents and Nix: parametrable skills/instructions and tools, packaged together in a reproducible and modular fashion
Ready to connect★ 91
- View details
riglet-creatorSkillAI & models
AI agents and Nix: parametrable skills/instructions and tools, packaged together in a reproducible and modular fashion
Ready to connect★ 91
- View details
session-feedbackSkillAI & models
Invoke at the end of a session, or when the user asks "anything to add to CLAUDE.md?", "session feedback", "learnings", or types `/session-feedback`. Decides whether a failure hit this session will hit the next agent too, then proposes a durable entry that prevents it - in `agent_docs/` or CLAUDE.md
Ready to connect★ 91
- View details
show-contextSkillAI & models
Bash script to invoke the current agent context window. Reports the agent's remaining context window / token budget by running the repo's context reporter. Invoke when the user types `/show-context`, or when the agent needs to know how much context window is left - including any time it is about to
Ready to connect★ 91
- View details
supported-devicesSkillAI & models
The user invokes `/supported-devices` after board work landed - either a whole new board bring-up or a single feature on an existing board. It syncs `launcher/supported_devices.py` with reality (append the board entry / flip `supported` / flip the feature keys the agent actually worked on), then run
Ready to connect★ 91
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.
55,111 of the 55,543 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.