agentleFS
viasrijanviasrijan/crazy-skills/skills/_catalog/crazy-skills-catalog/SKILL.md

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.

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
  1. Very specific:

    After --pick, confirm: Test-Path .opencode/skills/<name>/SKILL.md → True

    line 66

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

  1. Find — Scan the table below (or docs/CATALOG.md for the full auto-generated index).
  2. Pick — Choose the skill name.
  3. Install — In a terminal at the repo or project root:
    .\scripts\install.ps1 --pick <skill-name>          # current project → .opencode/skills/<name>/
    .\scripts\install.ps1 --pick <skill-name> --dryRun # preview
    Or globally: .\scripts\install.ps1 --all (adds skills array to opencode.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.ps1 after any skill change).

CategorySkillTierPurposeInstall
designfrontend-designCoreProduction-grade UI generation (anthropics 818k + vercel guidelines)— (Core)
designsystem-architectureCoreMicroservices/scalability review— (Core)
workflowbrainstormingCoreSocratic idea → sectioned design doc— (Core)
workflowwriting-plansCoreSpec → 2-5 min executable plan— (Core)
workflowexecuting-plansCoreExecute plan in parallel session— (Core)
workflowdispatching-parallel-agentsCoreDelegate independent tasks concurrently— (Core)
workflowfinishing-a-development-branchCoreVerify → present merge/PR options → cleanup— (Core)
buildsubagent-driven-developmentCoreOne subagent per task + 2-stage review— (Core)
qualitytest-driven-developmentCoreRED-GREEN-REFACTOR, pyramid 80/15/5— (Core)
qualitysystematic-debuggingCore4-phase root-cause Iron Law— (Core)
qualityverification-before-completionCoreFresh verification before any success claim— (Core)
reviewrequesting-code-reviewCoreDispatch code-reviewer subagent— (Core)
reviewreceiving-code-reviewCoreVerify feedback before implementing— (Core)
securitysecurity-and-hardeningCoreOWASP Top 10, auth, secrets— (Core)
performanceperformance-optimizationCoreMeasure-first, bundle, Core Web Vitals— (Core)
performancecore-web-vitalsCoreLCP ≤2.5s, INP ≤200ms, CLS ≤0.1— (Core)
productivitytoken-efficiencyCoreBash over Read, model routing (90-95% saving)— (Core)
productivityprompt-enhancementCoreRSCIT auto-enhance input prompts (always-on)— (Core)
devopsusing-git-worktreesCoreIsolated worktree + setup— (Core)
devopsgit-workflow-and-versioningCoreTrunk-based, atomic commits— (Core)
metausing-crazy-skillsCoreHow to find and use Crazy Skills— (Core)
metawriting-skillsCoreTDD for process docs— (Core)
_catalogcrazy-skills-catalogCoreThis index — browse Extended— (Core)
docsreadme-generationExtendedHigh-converting README + badges + SVG logoinstall.ps1 --pick readme-generation
docsdocumentation-and-adrsExtendedADRs, API docs, why-not-whatinstall.ps1 --pick documentation-and-adrs
productivitycontext-compressionExtended3-layer Micro/Auto/Full Compact (30/60/85%)install.ps1 --pick context-compression
datavoltagent-best-practicesExtendedAgents vs workflows, memory, observabilityinstall.ps1 --pick voltagent-best-practices
datavoltagent-core-referenceExtendedVoltAgent API referenceinstall.ps1 --pick voltagent-core-reference
reviewadverse-reviewExtended3-persona adversarial reviewinstall.ps1 --pick adverse-review
......ExtendedSee 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 skill tool.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.