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
70,704 results · page 1640 of 2,357
- View details
apt-threat-huntSkillSecurity
Lets your agent hunt for signs of advanced persistent threat (APT) actor activity in your systems.
Ready to connect★ 88
- View details
arkts-syntax-assistantSkillFiles & storage
Gives your agent ArkTS syntax help, TypeScript migration guidance, and performance tips for HarmonyOS development.
Ready to connect★ 88
- View details
asset-creatorSkillFiles & storage
Lets your agent create visual assets like SVG icons, social banners, and OG image templates as code files.
Ready to connect★ 88
- View details
autopsySkillDev tools
Lets your agent assess a codebase's health, finding complexity, dead code, tech debt, and git hotspots.
Ready to connect★ 88
- View details
baSkillSearch
Lets your agent act as a business analyst, asking questions to turn a feature idea into a requirements document.
Ready to connect★ 88
- View details
basic-endpoint-triage-isolationSkillDev tools
Lets your agent triage a suspicious computer and isolate it from the network during a security incident.
Ready to connect★ 88
- View details
basic-ioc-enrichmentSkillSecurity
Lets your agent look up the reputation and threat intelligence of suspicious IPs, domains, or other indicators.
Ready to connect★ 88
- View details
browser-pilotSkillWeb & browsing
Lets your agent open web pages in a browser, click elements, take screenshots, and report what it finds.
Ready to connect★ 88
- View details
case-event-timeline-analysisSkillDev tools
Lets your agent reconstruct chronological timelines of events from case data.
Ready to connect★ 88
- View details
case-reportSkillDev tools
Lets your agent draft detailed case closure reports and root cause analysis documents.
Ready to connect★ 88
- View details
check-duplicate-casesSkillDev tools
Lets your agent check SOAR cases for overlapping entities to spot duplicates.
Ready to connect★ 88
- View details
close-duplicate-casesSkillDev tools
Lets your agent find duplicate SOAR cases and close them by linking them to the original case.
Ready to connect★ 88
- View details
close-soar-artifactSkillMonitoring & ops
Lets your agent set the closure status and root cause reason for a SOAR alert or case.
Ready to connect★ 88
- View details
cloud-vulnerability-triageSkillSecurity
Lets your agent triage cloud security vulnerabilities and add context to findings.
Ready to connect★ 88
- View details
coderabbit-setupSkillDatabases & data
Creates a project stack-tailored .coderabbit.yaml file so CodeRabbit performs automatic AI code review of every pull request before merge. Detects the stack (Expo/RN, Next.js, React+Vite, Node, Supabase), assembles the config from a base template + per-stack blocks, and validates the YAML. Use when:
Ready to connect★ 88
- View details
compare-gti-collectionSkillDev tools
Lets your agent match threat intelligence indicators against your local security telemetry to find related activity.
Ready to connect★ 88
- View details
completion-gateSkillAI & models
Checks that your agent really finished its work by requiring proof before it can claim a task is done.
Ready to connect★ 88
- View details
compromised-user-account-responseSkillDev tools
Lets your agent contain, eradicate, and recover from a confirmed compromised user account.
Ready to connect★ 88
- View details
confirm-actionSkillDev tools
Makes your agent pause and ask a human for approval before running disruptive fixes.
Ready to connect★ 88
- View details
constraint-checkSkillDev tools
Lets your agent audit whether a skill's mandatory constraints were actually followed during a workflow, not just claimed.
Ready to connect★ 88
- View details
correlate-ioc-with-alerts-casesSkillMonitoring & ops
Lets your agent cross-reference extracted IOCs against recent SIEM alerts.
Ready to connect★ 88
- View details
create-investigation-reportSkillMonitoring & ops
Lets your agent create claude skill outputs that compile incident investigation findings into a report.
Ready to connect★ 88
- View details
deep-dive-ioc-analysisSkillDev tools
Lets your agent run deep forensic analysis on indicators of compromise like suspicious IPs, domains, and file hashes.
Ready to connect★ 88
- View details
dependency-doctorSkillSecurity
Lets your agent check your project's packages for outdated versions and security issues, then suggest an update plan.
Ready to connect★ 88
- View details
detection-as-code-rule-tuningSkillDev tools
Lets your agent submit and verify pull requests that tune security detection rules.
Ready to connect★ 88
- View details
detection-as-code-workflowsSkillDev tools
Lets your agent author, test, and manage security detection rules using Git-based workflows.
Ready to connect★ 88
- View details
detection-engineering-coverage-evaluationSkillSecurity
Lets your agent evaluate threat detection coverage, generate synthetic test events, and draft YARA-L rules for Chronicle.
Ready to connect★ 88
- View details
detection-reportSkillDev tools
Lets your agent document detection coverage assessments and test results in a structured report.
Ready to connect★ 88
- View details
detection-rule-validation-tuningSkillDev tools
Lets your agent test security detection rules and tune them to cut down false positives.
Ready to connect★ 88
- View details
dev-brainstormSkillAI & models
Validate and refine an idea before planning. Interactive dialogue, pressure testing, exploring approaches, requirements doc. Use for "I have an idea", "let's brainstorm", "what do you think about", "help me think through", "I want to build", unclear scope, multiple possible solutions.
Ready to connect★ 88
Popular skills lists
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
- Best Claude skills for superpowers
- Best Claude skills for obsidian
- Best Claude skills for frontend design
- All best lists
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.
68,574 of the 70,704 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 workspace 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.