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 707 of 2,357
- View details
research-schematic-designSkillMedia
Create publication-quality, editable scientific and engineering schematics with explicit physical meaning, exact labels, visual hierarchy, and provenance. Use for experimental facilities, thermal-fluid mechanisms, workflows, graphical abstracts, system architectures, or research diagrams.
Ready to connect★ 1k
- View details
research-slide-designSkillDocs & knowledge
Design clean, graphics-first technical presentations and posters with logical slide progression, visual hierarchy, purposeful motion, and complementary speaker notes. Use for research talks, conference slides, seminars, defenses, posters, or figure-focused presentations.
Ready to connect★ 1k
- View details
research-writing-literatureSkillDev tools
Write and revise rigorous research narratives, literature reviews, manuscript sections, citations, and figure discussions. Use for technical introductions, methods, results, discussions, review articles, abstracts, or related-work sections.
Ready to connect★ 1k
- View details
resolve-mergeSkillDev tools
Resolve an active merge or rebase conflict, including safe renumbering of colliding plans and chronicles.
Ready to connect★ 1k
- View details
responsive-layout-mathSkillDev tools
Derive, review, and debug responsive web layout math for fluid widths, media query ranges, viewport units, percentages, and CSS clamp() formulas. Use when building responsive layouts, converting fixed designs to fluid CSS, calculating breakpoints, choosing vw/svw/lvw/dvw units, or deciding whether C
Ready to connect★ 1k
- View details
restricted-accessSkillDev tools
Use when a val's HTTP endpoints should not be open to the whole internet — limiting an app to a team, understanding why an endpoint redirects to a login page, letting a webhook through, or identifying which Val Town user is viewing an app. Covers app access (`httpPrivacy`), org grants, bypass tokens
Ready to connect★ 1k
- View details
resumeSkillDev tools
Resume an interrupted AgenTeam run with verify-first strategy.
Ready to connect★ 1k
- View details
resume-crSkillDev tools
Continues an existing Clean Room run from durable artifacts without relying on prior chat history.
Ready to connect★ 1k
- View details
resumingSkillDev tools
Resume an interrupted workflow run with verify-first strategy — loads sidecar state, verifies the last step, and continues execution.
Ready to connect★ 1k
- View details
retargeting-strategySkillMedia
Designs a retargeting playbook with audience segments, ad sequencing, budgets, and KPI triggers.
Ready to connect★ 1k
- View details
retrospectiveSkillDev tools
Audit whether prior learnings actually fired, then install mechanisms for this run's recurrences. No finding without an install path and a firing test. Triggers: retrospective, reflect, what did we learn, patterns, post-mortem, why does this keep happening.
Ready to connect★ 1k
- View details
review-securitySkillMonitoring & ops
Review application and infrastructure changes for exploitable security risks by tracing assets, trust boundaries, attacker-controlled input, authorization, sensitive data, and dangerous sinks. Use for security reviews, threat-focused PR reviews, authentication or authorization changes, input handlin
Ready to connect★ 1k
- View details
review-teamSkillDev tools
Your agent can use this review claude skill when assigned a review or reaching a review boundary.
Ready to connect★ 1k
- View details
reviewable-design-docSkillDocs & knowledge
Use this skill when you want to organize requirements, design, architecture, and unresolved issues into a review-ready HTML design document. After the review is complete, it reads HTML comments, reflects them into the design, and, when confirmation is needed, writes agent replies back into the HTML
Ready to connect★ 1k
- View details
reviewer-author-loopSkillAI & models
Iterative manuscript improvement workflow where a reviewer agent critiques, an author agent revises, a verifier checks the revision, and the loop repeats until acceptance or a human-pause condition is reached. Use for virtual peer review, reviewer-author revision loops, rebuttal preparation, resubmi
Ready to connect★ 1k
- View details
reviewing-gitlab-mr-commentsSkillDev tools
Use when reviewing GitLab merge request comments via glab in the current repo, including extracting line ranges and code snippets from inline discussions, then deciding next actions with a checklist or plan before execution
Ready to connect★ 1k
- View details
revisionSkillMonitoring & ops
Trace bugs and manual fixes back to kits and prompts, then fix at the source so the iteration loop can reproduce the fix autonomously. Covers the 6-step revision process for commit sweeps AND the single-failure backpropagation protocol (six steps: TRACE, ANALYZE, PROPOSE, GENERATE, VERIFY, LOG) that
Ready to connect★ 1k
- View details
revoke-overrideSkillDev tools
Revoke a previously-created AxonFlow session override — emits an audit event and ensures subsequent policy evaluations no longer consult it
Ready to connect★ 1k
- View details
rework-loopSkillDev tools
Structured rework with git blame attribution for failed goal iterations. Maps failures to responsible changes and routes targeted fix briefs.
Ready to connect★ 1k
- View details
rg-budget-searchSkillSearch
In large or many-file projects, prefer cxs over raw rg/grep to reduce context waste.
Ready to connect★ 1k
- View details
river-reviewSkillDev tools
Main entry point for River Review. An improvement-loop orchestrator that handles the full flow: intent classification of review requests → selecting a specialized skill → execution → finding verification → feedback classification → feeding results back into fixtures / references / suppressions.
Ready to connect★ 1k
- View details
river-review-architectureSkillMedia
Review agent for design and architecture perspectives. Routes to individual skills such as dependencies, boundary design, data models, and API design.
Ready to connect★ 1k
- View details
river-review-codeSkillMonitoring & ops
General code quality review agent. The default fallback. Routes to individual skills such as readability, maintainability, type safety, logging, etc.
Ready to connect★ 1k
- View details
river-review-docsSkillDocs & knowledge
Documentation-focused review agent. Verifies consistency between README / docs / AGENTS.md and the implementation, correspondence between API docs and code, accuracy of usage and examples, i18n (JA/EN) consistency, and terminology unification.
Ready to connect★ 1k
- View details
river-review-frontendSkillMedia
Frontend review agent. Routes accessibility, design system compliance, Tailwind class hygiene, UI state design, and Next.js / React Router framework boundaries to individual skills.
Ready to connect★ 1k
- View details
river-review-performanceSkillDocs & knowledge
Performance-focused review agent. Evaluates code changes from the perspectives of N+1 queries, memory efficiency, caching strategy, and observability.
Ready to connect★ 1k
- View details
river-review-securitySkillSecurity
Security-focused standard review agent. Routes to individual skills for basic security checks, authentication/authorization design, and privacy design. Explicit repository/subsystem security audits are delegated to river-review-security-audit.
Ready to connect★ 1k
- View details
river-review-security-auditSkillSecurity
Entry skill that performs a source-only, explicit security audit on a repository or subsystem. Kept separate from normal PR security review, it handles reconnaissance, scope fixing, delegation to existing security skills, evidence and unresolved hypotheses, observe-only SecurityAuditCoverage, the co
Ready to connect★ 1k
- View details
river-review-testingSkillAI & models
Test-perspective review agent. Routes to individual skills covering test coverage, naming conventions, flaky tests, and coverage gaps.
Ready to connect★ 1k
- View details
roast-my-codeSkillDev tools
Roast code with aggressive humor while preserving a factual staff review; --fix can apply selected CRITICAL/HIGH fixes.
Ready to connect★ 1k
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.