Explore the full catalog
Explore skills, repositories and creators
Search the catalog or browse with filters. Checks are automated signals, not a safety guarantee.
Page 28 · 50 results shown
Skill
cso
garrytan/gstack · cso
Security audit: supported static findings; qualified profiles add reproduction and repair candidates. (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
plan-ceo-review
garrytan/gstack · plan-ceo-review
CEO/founder-mode plan review. (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
design-consultation
garrytan/gstack · design-consultation
Design consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview... (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
health
garrytan/gstack · health
Code quality dashboard. (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
design-motion
garrytan/gstack · design-motion
Design motion: animate an approved design into a seamless MP4 and GIF loop. (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
context-save
garrytan/gstack · context-save
Save working context. (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
office-hours
garrytan/gstack · office-hours
YC Office Hours — two modes. (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
ios-design-review
garrytan/gstack · ios-design-review
Visual design audit for iOS apps on real hardware. (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
eval-plan
garrytan/gstack · eval-plan
Preregister a paid eval (bars, arms, decoys, stop rules), dry-run it at zero cost, then run a three-item priced pilot whose spend table gates approval. (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
gstack-openclaw-ceo-review
garrytan/gstack · openclaw/skills/gstack-openclaw-ceo-review
Use when asked to review a plan, challenge a proposal, run a CEO review, poke holes in an approach, think bigger about scope, or decide whether to expand or reduce the plan.
Repository stars: 140,535 · Incomplete scan
Skill
gstack
garrytan/gstack · capy/skill/gstack
Install and use gstack in Capy and Claude Code. Load at session start to check this machine, and for gstack planning, code review, debugging, QA, design, security, documentation, and shipping workflows.
Repository stars: 140,535 · Incomplete scan
Skill
design-review
garrytan/gstack · design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
canary
garrytan/gstack · canary
Post-deploy canary monitoring. (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
deslop-shared-libs
garrytan/gstack · deslop-shared-libs
Find worthwhile shared-code extractions in recent work. (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
plan-devex-review
garrytan/gstack · plan-devex-review
Interactive developer experience plan review. (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
setup-browser-cookies
garrytan/gstack · setup-browser-cookies
Import cookies from your real Chromium browser into the headless browse session. (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
land-and-deploy
garrytan/gstack · land-and-deploy
Land and deploy workflow. (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
browse
garrytan/gstack · browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack)
Repository stars: 140,535 · Incomplete scan
Skill
caveman-evidence-review
JuliusBrussee/caveman · skills/caveman-evidence-review
Read-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.
Repository stars: 118,057 · Incomplete scan
Skill
megacave
JuliusBrussee/caveman · plugins/caveman/skills/megacave
Caveman 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".
Repository stars: 118,057 · Incomplete scan
Skill
caveman-review
JuliusBrussee/caveman · skills/caveman-review
Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".
Repository stars: 118,057 · Incomplete scan
Skill
lean-build
JuliusBrussee/caveman · skills/lean-build
Build 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.
Repository stars: 118,057 · Incomplete scan
Skill
caveman-discover
JuliusBrussee/caveman · skills/caveman-discover
Find 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.
Repository stars: 118,057 · Incomplete scan
Skill
caveman-learn
JuliusBrussee/caveman · skills/caveman-learn
Act 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.
Repository stars: 118,057 · Incomplete scan
Skill
caveman-help
JuliusBrussee/caveman · skills/caveman-help
Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".
Repository stars: 118,057 · Incomplete scan
Skill
migration
JuliusBrussee/caveman · skills/migration
Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.
Repository stars: 118,057 · Incomplete scan
Skill
cavecrew
JuliusBrussee/caveman · skills/cavecrew
When 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.
Repository stars: 118,057 · Incomplete scan
Skill
verify-and-stop
JuliusBrussee/caveman · skills/verify-and-stop
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
Repository stars: 118,057 · Incomplete scan
Skill
safe-refactor
JuliusBrussee/caveman · skills/safe-refactor
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
Repository stars: 118,057 · Incomplete scan
Skill
caveman-setup
JuliusBrussee/caveman · skills/caveman-setup
Wire 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.
Repository stars: 118,057 · Incomplete scan
Skill
caveman
JuliusBrussee/caveman · skills/caveman
Terse 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".
Repository stars: 118,057 · Incomplete scan
Skill
caveman-optimize
JuliusBrussee/caveman · skills/caveman-optimize
Turn 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.
Repository stars: 118,057 · Incomplete scan
Skill
ultracave
JuliusBrussee/caveman · skills/ultracave
Caveman 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".
Repository stars: 118,057 · Incomplete scan
Skill
ultracave
JuliusBrussee/caveman · plugins/caveman/skills/ultracave
Caveman 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".
Repository stars: 118,057 · Incomplete scan
Skill
caveman-stats
JuliusBrussee/caveman · plugins/caveman/skills/caveman-stats
Show 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.
Repository stars: 118,057 · Incomplete scan
Skill
megacave
JuliusBrussee/caveman · skills/megacave
Caveman 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".
Repository stars: 118,057 · Incomplete scan
Skill
caveman
JuliusBrussee/caveman · plugins/caveman/skills/caveman
Terse 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".
Repository stars: 118,057 · Incomplete scan
Skill
caveman-commit
JuliusBrussee/caveman · skills/caveman-commit
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
Repository stars: 118,057 · Incomplete scan
Skill
caveman-stats
JuliusBrussee/caveman · skills/caveman-stats
Show 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.
Repository stars: 118,057 · Incomplete scan
Skill
investigate-first
JuliusBrussee/caveman · skills/investigate-first
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
Repository stars: 118,057 · Incomplete scan
Skill
caveman-manage
JuliusBrussee/caveman · skills/caveman-manage
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.
Repository stars: 118,057 · Incomplete scan
Skill
cavecrew
JuliusBrussee/caveman · plugins/caveman/skills/cavecrew
When 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.
Repository stars: 118,057 · Incomplete scan
Skill
caveman-compress
JuliusBrussee/caveman · skills/caveman-compress
Compress 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.
Repository stars: 118,057 · Incomplete scan
Skill
caveman-compress
JuliusBrussee/caveman · plugins/caveman/skills/caveman-compress
Compress 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.
Repository stars: 118,057 · Incomplete scan
Skill
surgical-patch
JuliusBrussee/caveman · skills/surgical-patch
Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.
Repository stars: 118,057 · Incomplete scan
Skill
caveman-explore
JuliusBrussee/caveman · skills/caveman-explore
Read-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.
Repository stars: 118,057 · Incomplete scan
Skill
ci-cd-and-automation
addyosmani/agent-skills · skills/ci-cd-and-automation
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
Repository stars: 113,785 · Incomplete scan
Skill
debugging-and-error-recovery
addyosmani/agent-skills · skills/debugging-and-error-recovery
Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need to figure out what broke and why — a systematic approach to finding and fixing the root cause rather than guessing.
Repository stars: 113,785 · Incomplete scan
Skill
security-and-hardening
addyosmani/agent-skills · skills/security-and-hardening
Hardens code against vulnerabilities. Use when auditing an input handler for vulnerabilities, when handling user input, authentication, data storage, or external integrations, or when checking a login flow is safe against the OWASP Top Ten. Use when building any feature that accepts untrusted data, manages user sessions or session cookies, or interacts with third-party services. Use when auditing dependencies for known vulnerabilities, triaging package-manager audit findings, or assessing supply-chain risk in a new package. Use when personal data or privacy compliance (GDPR, CCPA) is involved.
Repository stars: 113,785 · Incomplete scan
Skill
api-and-interface-design
addyosmani/agent-skills · skills/api-and-interface-design
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
Repository stars: 113,785 · Incomplete scan
Automated signals, not a guarantee. How the checks work.
