crazy-skills-catalog
Skill0 starsChanged 3 months agoMITView on GitHub
Use when you need a skill not in Core, want to browse all 60+ extended skills, or don't know which skill fits — discover and install on demand.
In this repository64 other files it gives its agents.
- subagent-driven-developmentSkill
- frontend-designSkill
- system-architectureSkill
- git-workflow-and-versioningSkill
- using-git-worktreesSkill
- documentation-and-adrsSkill
- readme-generationSkill
- accessibilitySkill
- adverse-reviewSkill
- aeoSkill
- agent-designerSkill
- api-and-interface-designSkill
- best-practicesSkill
- browser-testing-with-devtoolsSkill
- canvas-designSkill
- ceo-advisorSkill
- ci-cd-and-automationSkill
- content-creatorSkill
- context-engineeringSkill
- create-voltagentSkill
- cto-advisorSkill
- deep-researchSkill
- doubt-driven-developmentSkill
- frontend-ui-engineeringSkill
- gdprSkill
- idea-refineSkill
- incremental-implementationSkill
- interview-meSkill
- iso27001Skill
- local-seo-managerSkill
- mcp-server-builderSkill
- observability-and-instrumentationSkill
- performanceSkill
- planning-and-task-breakdownSkill
- product-manager-toolkitSkill
- research-orchestratorSkill
- saas-metrics-coachSkill
- seoSkill
- soc2Skill
- source-driven-developmentSkill
- spec-driven-developmentSkill
- tech-debt-trackerSkill
- voltagent-best-practicesSkill
- voltagent-core-referenceSkill
- voltagent-docs-bundleSkill
- web-quality-auditSkill
- using-crazy-skillsSkill
- writing-skillsSkill
- core-web-vitalsSkill
- performance-optimizationSkill
- context-compressionSkill
- prompt-enhancementSkill
- token-efficiencySkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- verification-before-completionSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- security-and-hardeningSkill
- brainstormingSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 66
After --pick, confirm: Test-Path .opencode/skills/<name>/SKILL.md → True
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Crazy Skills Catalog
Discover and install any Extended skill on demand. Core (18 skills) is always advertised; this catalog is the gateway to the remaining 40+.
When to use
- You need a skill not in Core (e.g.,
readme-generation,voltagent-observability,adverse-review) - You want to browse the full library by category
- You don't know which skill fits — search the table
Workflow
- Find — Scan the table below (or
docs/CATALOG.mdfor the full auto-generated index). - Pick — Choose the skill name.
- Install — In a terminal at the repo or project root:
Or globally:.\scripts\install.ps1 --pick <skill-name> # current project → .opencode/skills/<name>/ .\scripts\install.ps1 --pick <skill-name> --dryRun # preview.\scripts\install.ps1 --all(addsskillsarray toopencode.json).
Catalog (Core + Extended — grouped by hybrid category)
This table is a summary. The canonical auto-generated index is
docs/CATALOG.md(run.\scripts\generate-catalog.ps1after any skill change).
| Category | Skill | Tier | Purpose | Install |
| design | frontend-design | Core | Production-grade UI generation (anthropics 818k + vercel guidelines) | — (Core) |
| design | system-architecture | Core | Microservices/scalability review | — (Core) |
| workflow | brainstorming | Core | Socratic idea → sectioned design doc | — (Core) |
| workflow | writing-plans | Core | Spec → 2-5 min executable plan | — (Core) |
| workflow | executing-plans | Core | Execute plan in parallel session | — (Core) |
| workflow | dispatching-parallel-agents | Core | Delegate independent tasks concurrently | — (Core) |
| workflow | finishing-a-development-branch | Core | Verify → present merge/PR options → cleanup | — (Core) |
| build | subagent-driven-development | Core | One subagent per task + 2-stage review | — (Core) |
| quality | test-driven-development | Core | RED-GREEN-REFACTOR, pyramid 80/15/5 | — (Core) |
| quality | systematic-debugging | Core | 4-phase root-cause Iron Law | — (Core) |
| quality | verification-before-completion | Core | Fresh verification before any success claim | — (Core) |
| review | requesting-code-review | Core | Dispatch code-reviewer subagent | — (Core) |
| review | receiving-code-review | Core | Verify feedback before implementing | — (Core) |
| security | security-and-hardening | Core | OWASP Top 10, auth, secrets | — (Core) |
| performance | performance-optimization | Core | Measure-first, bundle, Core Web Vitals | — (Core) |
| performance | core-web-vitals | Core | LCP ≤2.5s, INP ≤200ms, CLS ≤0.1 | — (Core) |
| productivity | token-efficiency | Core | Bash over Read, model routing (90-95% saving) | — (Core) |
| productivity | prompt-enhancement | Core | RSCIT auto-enhance input prompts (always-on) | — (Core) |
| devops | using-git-worktrees | Core | Isolated worktree + setup | — (Core) |
| devops | git-workflow-and-versioning | Core | Trunk-based, atomic commits | — (Core) |
| meta | using-crazy-skills | Core | How to find and use Crazy Skills | — (Core) |
| meta | writing-skills | Core | TDD for process docs | — (Core) |
| _catalog | crazy-skills-catalog | Core | This index — browse Extended | — (Core) |
| docs | readme-generation | Extended | High-converting README + badges + SVG logo | install.ps1 --pick readme-generation |
| docs | documentation-and-adrs | Extended | ADRs, API docs, why-not-what | install.ps1 --pick documentation-and-adrs |
| productivity | context-compression | Extended | 3-layer Micro/Auto/Full Compact (30/60/85%) | install.ps1 --pick context-compression |
| data | voltagent-best-practices | Extended | Agents vs workflows, memory, observability | install.ps1 --pick voltagent-best-practices |
| data | voltagent-core-reference | Extended | VoltAgent API reference | install.ps1 --pick voltagent-core-reference |
| review | adverse-review | Extended | 3-persona adversarial review | install.ps1 --pick adverse-review |
| ... | ... | Extended | See docs/CATALOG.md for remaining 30+ | install.ps1 --pick <name> |
Verification
- After
--pick, confirm:Test-Path .opencode/skills/<name>/SKILL.md→ True - Run:
.\scripts\audit-skills.ps1 --skill <category>/<name>→ PASS - Next turn, the skill is discoverable via the
skilltool.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

