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.
Filter by category
55,435 results · page 202 of 1,848
- View details
create-config-fieldSkillAI & models
Lets your agent create a claude skill-like config field: add a new option to the Datadog Agent's datadog.yaml via the config schema.
Ready to connect★ 4k
- View details
create-core-checkSkillMonitoring & ops
Lets your agent create Claude skill files for a Go core check that sends metrics to Datadog.
Ready to connect★ 4k
- View details
create-epic-recapSkillDocs & knowledge
Lets your agent create a Claude skill that recaps progress on a Jira Epic from child issues, PRs and release notes.
Ready to connect★ 4k
- View details
create-go-moduleSkillAI & models
Lets your agent create Claude Skill Go modules, scaffolding a new Go module in the agent repository.
Ready to connect★ 4k
- View details
create-invoke-taskSkillProductivity
Lets your agent create a claude skill as a Python invoke task for the dda CLI.
Ready to connect★ 4k
- View details
create-release-noteSkillDocs & knowledge
Lets your agent create a reno release note for a PR or change, and acts as a create claude skill for documenting updates.
Ready to connect★ 4k
- View details
create-runtime-settingSkillAI & models
Lets your agent create a runtime setting that can be changed later via agent config set/get.
Ready to connect★ 4k
- View details
create-status-providerSkillAI & models
Lets your agent create claude skill sections that appear in the agent status command output.
Ready to connect★ 4k
- View details
create-subcommandSkillAI & models
Lets you create claude skill subcommands that add new CLI commands to an agent binary.
Ready to connect★ 4k
- View details
cws-btfhub-syncSkillMonitoring & ops
Lets your agent regenerate checked-in kernel offset constant files by running a GitHub workflow and merging its PR.
Ready to connect★ 4k
- View details
cws-iouring-coverageSkillSecurity
Lets your agent audit which io_uring operations have functional tests and write tests for uncovered ones.
Ready to connect★ 4k
- View details
distillSkillDocs & knowledge
Lets your agent turn an existing codebase into a written behavioural specification.
Ready to connect★ 4k
- View details
e2e-auditSkillAI & models
Judges whether Agent behavior should be tested as e2e, integration, or unit tests.
Ready to connect★ 4k
- View details
elicitSkillSearch
Lets your agent run a structured interview to turn feature descriptions into a clear written specification.
Ready to connect★ 4k
- View details
explain-lading-configSkillFiles & storage
Explains what a lading.yaml regression test config does, grounding field meanings and defaults in the lading source code.
Ready to connect★ 4k
- View details
follow-prSkillMonitoring & ops
Lets your agent watch a PR's GitLab CI pipeline to the end and report or investigate failures.
Ready to connect★ 4k
- View details
injector-devSkillCloud & infra
Lets your agent build, deploy, and test Datadog Agent components on a local Kubernetes cluster with one command.
Ready to connect★ 4k
- View details
locate-config-settingSkillAI & models
Lets your agent find where a Datadog Agent config setting is defined in the YAML schemas, with file, line, and full definition.
Ready to connect★ 4k
- View details
propagateSkillFiles & storage
Lets your agent generate test files, including property-based and state machine tests, from an Allium specification.
Ready to connect★ 4k
- View details
quality-gate-size-analysisSkillDocs & knowledge
Lets your agent analyze software package size changes and match them to exception records and pull requests.
Ready to connect★ 4k
- View details
run-e2eSkillAI & models
Lets your agent run claude skill e2e tests locally and fix setup failures before tests start.
Ready to connect★ 4k
- View details
run-jiraSkillProductivity
Lets your agent run claude skill to fetch a Jira issue and propose an implementation plan from the codebase.
Ready to connect★ 4k
- View details
run-windows-e2eSkillCloud & infra
Lets your agent run claude skill tasks that execute Windows E2E tests on AWS-provisioned VMs.
Ready to connect★ 4k
- View details
triage-ci-failureSkillMonitoring & ops
Lets your agent investigate a failed CI run and tell you if it is your PR, flakiness, or an outage.
Ready to connect★ 4k
- View details
update-3rd-party-libsSkillAI & models
Update claude skill lets your agent bump a C/C++ third-party library under deps/ and fix the build.
Ready to connect★ 4k
- View details
update-otel-depsSkillFiles & storage
Lets your agent update claude skill tasks for bumping and troubleshooting OpenTelemetry Collector dependencies in datadog-agent.
Ready to connect★ 4k
- View details
write-agent-health-e2eSkillAI & models
Lets your agent write claude skill content that creates an E2E lifecycle test for a new health platform issue.
Ready to connect★ 4k
- View details
write-e2eSkillAI & models
Write claude skill e2e tests: your agent authors new Datadog Agent E2E tests, fakeintake coverage and GitLab wiring.
Ready to connect★ 4k
- View details
agent-experienceSkillDocs & knowledge
Lets your agent audit how easy a product's docs and SDK are to use by having subagents attempt a real setup task.
Ready to connect★ 4k
- View details
cc-sdd-new-agentSkillAI & models
Lets your agent extend cc-sdd's sdd claude skill setup to support new coding agents by following a documented SOP.
Ready to connect★ 4k
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.
55,004 of the 55,435 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.