NeVibeCode · 4,143 skills
Skills for Claude Code, Codex and Cursor
SKILL.md folders the agent loads on its own when a task matches the description.
pr-screenshots
official Gets the agent to write PR descriptions with before/after screenshot pairs, so reviewers see the visual change without checking out the branch.
GitHub Copilot
141installs
caveman Turns Claude Code into a terse communication mode that keeps technical meaning while cutting filler. Use it when short answers and lower token use matter.
Claude Code
493installs
chaos-engineering Plans resilience experiments and computes blast radius. Helpful when running Game Day tests or verifying fault injection safely.
Claude Code
486installs
pr-dashboard
official Opens a GitHub pull request dashboard in the browser. Use it to check authored PRs, review requests, assignments, or status for a selected period.
GitHub Copilot
138installs
convert-pdf-to-md
official Converts PDF files to Markdown for reading, search, table extraction, and analysis. It can process one document or a folder of PDFs.
GitHub Copilot
138installs
rfp-responder Parses an RFP, RFI or security questionnaire into tagged requirements, maps each one to a proof point, and estimates your winrate. Built for the bid-or-skip decision.
Claude Code
478installs
ship-gate Audits a codebase before release across security, database, deployment, and other checks. It pauses deploy intent until critical findings are cleared.
Claude Code
475installs
feature-flags-architect Runs feature flags through a full lifecycle: add, ramp, retire. Useful when flags pile up and nobody knows which ones still matter.
Claude Code
469installs
acreadiness-policy
official Guides the creation, configuration, and execution of AgentRC readiness policies. Useful for setting custom scoring weights, strict thresholds, and CI gating.
GitHub Copilot
133installs
general-counsel-advisor This skill scans startup contracts, evaluates investor term sheets, and maps regulatory risks before you talk to outside counsel.
Claude Code
461installs
aeo Audits and restructures content so LLMs cite it as an authoritative source. Useful for teams building content for AI-first search audiences.
Claude Code
459installs
slo-architect This skill designs, reviews, and operates SLOs, SLIs, and error budgets. Use it when you need burn-rate calculations and alerting rules.
Claude Code
458installs
managed-airflow-recommendations
official Analyzes telemetry and tunes Managed Service for Apache Airflow environments. It helps size infrastructure and stop worker restarts using real metrics.
Claude Code Gemini CLI CX Codex
107installs
content-management-systems
official Guides GitHub Copilot through CMS architecture, template hierarchies, custom extensions, and media routing. Useful when modifying themes or data models in WordPress, Shopify, or Drupal.
GitHub Copilot
128installs
agent-skill-stack
official Finds a small compatible set of AI Agent Skills for a multi-step goal. Use it to audit installed Skills or work out what a project still needs.
GitHub Copilot
128installs
procurement-optimizer Categorizes spend, analyzes purchasing cycle times, and finds overlapping suppliers. Use it to review SaaS costs and plan consolidation with risk flags.
Claude Code
437installs
handoff Turns the current conversation into a handoff document for another agent. Use it when work moves to a fresh session and existing artifacts should stay referenced.
Claude Code
427installs
performance-review-writer
official Drafts self-assessments, peer reviews, and manager feedback using the STAR framework. Pulls work history via WorkIQ or manual notes.
GitHub Copilot
121installs
c-level-agents Adds executive-role agents and commands for reviewing decisions or running a multi-role discussion. Use it when a project question needs a management perspective.
Claude Code
424installs
boardroom Runs a C-suite deliberation over one strategy brief and writes a board memo with a vote tally, recorded dissent and kill criteria.
Claude Code
421installs
founder-mode Routes founder questions to the right executive advisor or convenes a joint boardroom discussion. Useful when tackling strategic topics without knowing which specialized command to invoke.
Claude Code
418installs
chief-ai-officer-advisor Advises startup founders and CAIOs on API versus fine-tuning decisions, EU AI Act risk tiers, and self-hosting token economics.
Claude Code
418installs
litreview A skill that searches academic literature through PubMed and OpenAlex, builds a search plan, and produces a Word orientation guide.
Claude Code
417installs
chief-data-officer-advisor Advises startup founders and CDOs on AI training data rights, data product architecture, B2B customer data valuation for M&A, and hiring sequences.
Claude Code
410installs
inbox-triage Triages recent emails using a pre-configured knowledge base, evaluates senders, and creates draft replies. Designed for automated daily runs.
Claude Code
408installs
landing This skill creates a single-page HTML landing page with 3D CSS animation, GSAP scroll effects, and mouse parallax. It collects product and brand details before generating the page.
Claude Code
404installs
cfo-review This skill tests money-related plans through burn, unit economics, dilution, and downside survival. Use it before approving meaningful spend.
Claude Code
402installs
cto-review A slash command that asks six hard questions about your architecture before you approve it. Useful before a big change, a hiring push, or a build-vs-buy call.
Claude Code
399installs
chief-customer-officer-advisor A strategic advisor for retention, customer segmentation, CS coverage, and hiring decisions. Use it when customer success needs a clear operating model.
Claude Code
397installs
eu-ai-act-specialist Classifies AI systems under Regulation (EU) 2024/1689, outlines conformity routes, and maps role obligations. Essential for teams auditing models against EU AI Act rules.
Claude Code
394installs
ciso-review A Claude Code slash command that runs a plan through six CISO questions and ends with a verdict: ship it, close the gaps first, or block.
Claude Code
390installs
write-a-skill This skill guides the creation of new agent skills with a clear structure and review steps. Use it when a skill needs instructions, examples, references, or bundled scripts.
Claude Code
389installs
vpe-advisor Reviews engineering delivery, hiring flow and team design. Use it when sprint velocity drops or a team-management decision needs evidence.
Claude Code
389installs
cmo-review Reviews positioning, ICP and channel choices before a campaign launch or larger marketing spend. It returns a readiness verdict for the plan.
Claude Code
386installs
iso42001-specialist Reviews AI management system gaps, maps risks to Annex A controls, and drafts an internal audit plan. Use it when preparing for ISO 42001 certification.
Claude Code
385installs
post-mortem Runs a retrospective for an executed decision against pre-committed success and kill criteria. Use it at a review checkpoint or after a reversal.
Claude Code
385installs
doc-and-modernize
official Analyzes a local codebase to generate a cited architecture document and creates a phased migration plan for legacy stacks.
GitHub Copilot
108installs
inbox-setup This skill interviews you about email habits and builds the knowledge base used by inbox-triage. Run it before the first triage pass.
Claude Code
380installs
decide Logs an approved boardroom memo into Claude Code durable memory. It records the final decision along with binding kill criteria.
Claude Code
377installs
cpo-review Interrogates product roadmaps using JTBD, PMF signals, and retention curves. Helps decide which features to ship and which to kill before committing a quarter.
Claude Code
377installs
3,681–3,720 of 4,143