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
8,868 results · page 229 of 296
- View details
controlling-variance-analyzerSkillAI & models
Variance analysis of actual vs. budget with root cause, executive narrative, and RAG status.
Ready to connect★ 50
- View details
emergency-modeSkillAI & models
Use when the Anthropic API is down and you need to keep operating with LocalAI.
Ready to connect★ 50
- View details
evaluations-frameworkSkillAI & models
Use when designing or running quality evaluations of agents and prompts.
Ready to connect★ 50
- View details
harness:certifySkillAI & models
Use when the user wants to verify that the evolved agent's score is stable and reliable. Runs evaluation multiple times and reports mean ± std.
Ready to connect★ 50
- View details
harness:evolveSkillAI & models
Use when the user wants to run the optimization loop, improve agent performance, evolve the agent, or iterate on quality. Requires .evolver.json to exist (run harness:setup first).
Ready to connect★ 50
- View details
harness:setupSkillAI & models
Use when the user wants to set up the evolver in their project, optimize an LLM agent, improve agent performance, or mentions evolver for the first time in a project without .evolver.json.
Ready to connect★ 50
- View details
legal-contract-reviewerSkillAI & models
Contract review with a RAG risk matrix, red flags, and an executive summary. Spanish jurisdiction.
Ready to connect★ 50
- View details
model-upgrade-auditSkillAI & models
Use when a new model is available and you want to detect prompt debt in the workspace.
Ready to connect★ 50
- View details
pi-cli-runtimeSkillAI & models
Internal helper contract for calling the pi-companion runtime from Claude Code
Ready to connect
- View details
pr-agent-judgeSkillAI & models
Use when adding pr-agent as an external judge in the Code Review Court.
Ready to connect★ 50
- View details
savia-dualSkillAI & models
Use when cloud inference fails, is slow, or is rate-limited and local failover is needed.
Ready to connect★ 50
- View details
social-linkedinSkillAI & models
LinkedIn provider skill for the social-networks agent (SE-385 MVP1). Manual import of the official export, neutral SocialArtifact model, local digests (themes/savia-history/writing-style) and capabilities status. Never publishes without external-publish-gate + approval hash. Data in ~/.savia/social/
Ready to connect★ 50
- View details
speq-code-guardrailsSkillAI & models
TDD cycle and code quality guardrails — failing-test-first, evidence, dependency, error-handling, and test-quality rules. Triggered by implementer-agent, implementer-expert-agent, and code-reviewer before any implementation or review work.
Ready to connect★ 50
- View details
speq-code-toolsSkillAI & models
Semantic code navigation and editing via Serena MCP — symbol-level tools required over grep/find/manual edits. Triggered by planner-agent, implementer-agent, implementer-expert-agent, code-reviewer, and recorder-agent.
Ready to connect★ 50
- View details
speq-spec-mergeSkillAI & models
Delta-merge procedure — DELTA marker semantics, library-organization thresholds, and ADR-promotion field mapping. Triggered by recorder-agent.
Ready to connect★ 50
- View details
speq-writing-guardrailsSkillAI & models
Dense prose rules: sentence caps, BLUF, consistent vocabulary, evidence, and no em dashes. Triggered by /speq-mission, /speq-audit, /speq-implement, /speq-plan-pr, /speq-implement-pr, planner-agent, plan-reviewer, and recorder-agent.
Ready to connect★ 50
- View details
surgicalSkillAI & models
Forces Claude to match output scope exactly to what was requested. Triggers on any bounded coding request — "fix X", "add Y", "write a function/script that Z" — at the moment of writing each block, before adding anything the request didn't name: error handling for impossible edge cases, tests, docst
Ready to connect★ 50
- View details
tech-research-agentSkillAI & models
Usar cuando se necesita investigación técnica autónoma sobre un tema específico.
Ready to connect★ 50
- View details
workspace-integritySkillAI & models
Use when auditing workspace integrity (drift, rules, agents, baseline).
Ready to connect★ 50
- View details
cli-dispatchSkillAI & models
Required dispatch procedure for running a build or fix pass on an external coding CLI — the Codex CLI (`codex exec`) or the Cursor CLI (`agent -p`) — when an issue's Execution block stamps that harness as the Build model. Preflight, the two shims, the prompt-as-data rule, the background-and-poll rul
Ready to connect
- View details
cloud-vm-setupSkillAI & models
Set up and run the Donut dev environment on Cursor Cloud VM (no Nix). Use when working on Cloud VM, running tests on Cloud VM, or encountering command errors related to missing nix. Triggers on: cloud VM, cloud agent, no nix available, /workspace path.
Ready to connect
- View details
cpphdl-verilator-rtlSkillAI & models
Use when writing or debugging CppHDL tests that mix C++ testbench models with Verilated RTL, especially reset ordering, register inputs, AXI4 responder wiring, eval sequencing, _assign/_strobe discipline, and avoiding C++/SystemVerilog simulation mismatches.
Ready to connect
- View details
execution-plan-reviewSkillAI & models
Use when the user wants to review or revise the ordering/model/effort/fableplan/plan-effort assignments on a milestone's GitHub issues — "review the execution plan", "/execution-plan-review", "show me the model assignments", or piecemeal revisions like "11 should be medium" or "plan 17 at xhigh". Re
Ready to connect
- View details
fable-dispatchSkillAI & models
Required dispatch procedure for running a subagent on Fable 5.1: positive harness detection, the Claude Code CLI shim for other harnesses, the fallback ladder, the result-parsing contract, the attribution rule, and the caller dispatch-hygiene rules (read-only prompt, snapshot/diff, retry). Load BEFO
Ready to connect
- View details
milestone-workflowSkillAI & models
Use when the user wants a milestone of Execution-block-stamped GitHub issues implemented via a multi-agent dynamic workflow — "create the workflow for v0", "run v0 continuously", "/milestone-workflow v0". Builds dependency tracks, presents the run plan for approval, then runs the milestone-pipeline
Ready to connect
- View details
milestoneplanSkillAI & models
Use when the user wants a milestone's execution plan shown as a table — "milestoneplan v1", "/milestoneplan", "show the plan for v1". Read-only - reads every issue in the milestone and renders one table of issue number, description, complexity, dependencies, validate/build model and effort, fablepla
Ready to connect
- View details
new-app-pipelineSkillAI & models
Use when the user wants to take a new app from raw idea to running multi-agent implementation — "/new-app-pipeline", "let's build a new app", "run the app pipeline on this idea". Orchestrates the full sequence - idea → PRD → question refinement → GitHub issues with Execution blocks → execution-plan
Ready to connect
- View details
better-promptSkillAI & models
Use when the user explicitly asks to "optimize a prompt", "improve a prompt", "polish an instruction", "convert a rough prompt into a best-practices version", or asks to "rewrite a prompt as pseudocode" or "translate it into a program structure / programmable natural language". Supports two output m
Ready to connect
- View details
bootstrap-agents-mdSkillAI & models
Bootstrap or refresh root AGENTS.md and CLAUDE.md.
Ready to connect
- View details
boss-hr-autoSkillAI & models
Full-workflow orchestration for HR resume screening on BOSS Zhipin. Use when the user asks to "screen resumes", "run the 5-step workflow", or "go from job posting to report".
Ready to connect
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.