Skip to content

Explore skills

Search every indexed skill by name, description, repository or instructions, then narrow the results.

Showing 52921–52950 of 58158 skills

idea-refineaktonay/skillzRefines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or "stress-test my plan".Stars: 0Updated Claude CodeCodexUnverifiedInstall
performance-optimizationaktonay/skillzOptimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when Core Web Vitals or load times need improvement. Use when profiling reveals bottlenecks that need fixing.Stars: 0Updated Claude CodeCodexUnverifiedInstall
reviewaktonay/skillzStructured code review that reports correctness, security, performance, and maintainability findings before any fix. Use when you need concrete review findings, not implementation.Stars: 0Updated Claude CodeCodexUnverifiedInstall
security-and-hardeningaktonay/skillzHardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.Stars: 0Updated Claude CodeCodexUnverifiedInstall
shipping-and-launchaktonay/skillzPrepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 0Updated Claude CodeCodexUnverifiedInstall
testaktonay/skillzGenerate comprehensive tests for code and features. Use when writing new tests or improving test coverage for a behavior, bug fix, or regression.Stars: 0Updated Claude CodeCodexUnverifiedInstall
UI/UX Pro Maxaktonay/skillzDesign and polish beautiful, accessible, product-ready frontend UI.Stars: 0Updated Claude CodeCodexUnverifiedInstall
cavecrewaktonay/skillzWhen to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.Stars: 0Updated Claude CodeCodexUnverifiedInstall
cavemanaktonay/skillzTerse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".Stars: 0Updated Claude CodeCodexUnverifiedInstall
caveman-commitaktonay/skillzWrite a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.Stars: 0Updated Claude CodeCodexUnverifiedInstall
caveman-compressaktonay/skillzCompress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Sends the file's text to the configured model provider. Trigger: /caveman-compress.Stars: 0Updated Claude CodeCodexUnverifiedInstall
caveman-discoveraktonay/skillzFind and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.Stars: 0Updated Claude CodeCodexUnverifiedInstall
caveman-evidence-reviewaktonay/skillzRead-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.Stars: 0Updated Claude CodeCodexUnverifiedInstall
caveman-exploreaktonay/skillzRead-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.Stars: 0Updated Claude CodeCodexUnverifiedInstall
caveman-helpaktonay/skillzQuick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".Stars: 0Updated Claude CodeCodexUnverifiedInstall
caveman-learnaktonay/skillzAct on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.Stars: 0Updated Claude CodeCodexUnverifiedInstall
caveman-manageaktonay/skillzInspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.Stars: 0Updated Claude CodeCodexUnverifiedInstall
caveman-optimizeaktonay/skillzTurn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs explicit approval.Stars: 0Updated Claude CodeCodexUnverifiedInstall
caveman-reviewaktonay/skillzCompressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".Stars: 0Updated Claude CodeCodexUnverifiedInstall
caveman-setupaktonay/skillzWire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.Stars: 0Updated Claude CodeCodexUnverifiedInstall
caveman-statsaktonay/skillzShow recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report. Trigger: /caveman-stats.Stars: 0Updated Claude CodeCodexUnverifiedInstall
investigate-firstaktonay/skillzDiagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.Stars: 0Updated Claude CodeCodexUnverifiedInstall
lean-buildaktonay/skillzBuild feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.Stars: 0Updated Claude CodeCodexUnverifiedInstall
megacaveaktonay/skillzCaveman in Classical Chinese: 文言文 register, far fewer characters, technical terms verbatim. Invoke only with /megacave or /caveman wenyan. Stays on until "stop caveman" or "normal mode".Stars: 0Updated Claude CodeCodexUnverifiedInstall
migrationaktonay/skillzImplement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.Stars: 0Updated Claude CodeCodexUnverifiedInstall
safe-refactoraktonay/skillzRestructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.Stars: 0Updated Claude CodeCodexUnverifiedInstall
surgical-patchaktonay/skillzFix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.Stars: 0Updated Claude CodeCodexUnverifiedInstall
ultracaveaktonay/skillzCaveman at maximum compression: fragments, one word when one word is enough, each fact once. Invoke only with /ultracave or /caveman ultra. Stays on until "stop caveman" or "normal mode".Stars: 0Updated Claude CodeCodexUnverifiedInstall
verify-and-stopaktonay/skillzProve existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.Stars: 0Updated Claude CodeCodexUnverifiedInstall
graphifyaktonay/skillzUse for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.Stars: 0Updated Claude CodeCodexUnverifiedInstall