zeno-stack
Skill1 starsChanged 8 days agoMITView on GitHub
Stack-and-domain coverage dispatcher for the zeno loop. Routes to the correct infra/tooling/domain leaf for the technology in use; how code is written per language belongs to `code-standards`. Use whenever a task needs React, Postgres operations, Redis, Docker, Kubernetes, deployment (cloud or self-hosted), testing-execution, accessibility, security review, git workflow, or harness-maintenance guidance. Trigger on: any mention of React, Next.js, Angular, Postgres, Redis, Docker, Kubernetes, Playwright, pytest, accessibility/a11y, API design, error handling, rate limiting, security review, git branching, GitHub PR/issue automation, Jira backlog structure, destructive migrations, /compact, design systems, motion/animation, codebase onboarding, or Claude Code harness maintenance (skill audits, context budget, config cleanup). Also routes build-error resolution, comment-rot audits, performance profiling, implementation planning, dead-code cleanup, cost reporting, and model-tier routing.
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 19
When a task needs stack-specific or cross-cutting domain guidance, identify the technology/domain and load the matching nested leaf below …
- Distinctive: line 84
If multiple technologies are in scope (e.g.
- Distinctive: line 91
If the technology isn't listed above, apply general clean-code/SOLID principles and say so — don't force-fit an unrelated leaf.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Zeno Stack Dispatcher — stack & domain coverage
When a task needs stack-specific or cross-cutting domain guidance, identify the technology/domain
and load the matching nested leaf below before writing or reviewing anything. Every leaf here
starts with zeno-, per the zeno-family naming rule.
Routing Table
| Technology / Domain | Leaf to load |
| React component/state/hook patterns | zeno-react-patterns/SKILL.md |
| React/Next.js performance (memoization, code splitting, bundle size) | zeno-react-performance/SKILL.md |
| React component testing (RTL, Vitest/Jest) | zeno-react-testing/SKILL.md |
| Accessibility (WCAG 2.2, cross-platform + React/Next.js implementation) | zeno-accessibility/SKILL.md |
| Angular | zeno-angular-developer/SKILL.md |
| Design tokens / design-system audits | zeno-design-system/SKILL.md |
| Building actual UI with deliberate visual design | zeno-frontend-design/SKILL.md |
| Animation / motion patterns | zeno-motion-ui/SKILL.md |
| REST API design (resources, status codes, pagination, versioning) | zeno-api-design/SKILL.md |
| Error handling (typed errors, retries, circuit breakers) | zeno-error-handling/SKILL.md |
| Python idioms, PEP 8, type hints | code-standards/python — route there |
| FastAPI | code-standards/python/frameworks/fastapi.md — route there |
| Python testing (pytest, fixtures, mocking) | zeno-python-testing/SKILL.md |
| Redis (caching, distributed locks, rate limiting — the one source of truth) | zeno-redis-patterns/SKILL.md |
| PostgreSQL / relational data modeling | zeno-postgres-patterns/SKILL.md |
| Schema/data migrations | zeno-database-migrations/SKILL.md |
| Docker / Compose | zeno-docker-patterns/SKILL.md |
| Kubernetes | zeno-kubernetes-patterns/SKILL.md |
| Deployment / CI-CD / rollback strategy | zeno-deployment-patterns/SKILL.md |
| Self-hosted / home-lab deployment topology (NAT'd targets, single-host Compose) | zeno-self-hosted-deployment/SKILL.md |
| End-to-end testing (Playwright specs, CI) | zeno-e2e-testing/SKILL.md |
| Live/interactive browser QA | zeno-browser-qa/SKILL.md |
| Application security review (SQLi, XSS, CSRF, secrets, auth) | zeno-security-review/SKILL.md |
| Claude Code harness/config security scan | zeno-security-scan/SKILL.md |
| Git branching, commits, merge/rebase | zeno-git-workflow/SKILL.md |
| GitHub issue/PR/release automation | zeno-github-ops/SKILL.md |
| Jira backlog hierarchy review (Epic/Story/Task/Bug/Sub-task structure) | zeno-jira-structure-review/SKILL.md |
| Execution tripwires: new service/DB/broker/dependency, destructive migration, breaking API change, conflicting sources | zeno-implementation-guardrails/SKILL.md |
| Compacting or handing off a long session (keep/compress/drop, Task-State summary) | zeno-context-compaction/SKILL.md |
| Pre-launch / post-merge production readiness audit | zeno-production-audit/SKILL.md |
| Multi-source web research | zeno-deep-research/SKILL.md |
| Onboarding to an unfamiliar codebase | zeno-codebase-onboarding/SKILL.md |
| Guided code walkthroughs (CodeTour) | zeno-code-tour/SKILL.md |
| Harness skill-library cleanup | zeno-config-gc/SKILL.md |
| Harness context/token-cost audit | zeno-context-budget/SKILL.md |
| Skill quality audit (keep/improve/retire/merge) | zeno-skill-stocktake/SKILL.md |
| Skill/rule compliance visualization | zeno-skill-comply/SKILL.md |
| Cross-skill rule extraction | zeno-rules-distill/SKILL.md |
| Per-response token-depth selection | zeno-token-budget-advisor/SKILL.md |
| Local skill-library discovery | zeno-find-skills/SKILL.md |
| External (marketplace/GitHub) skill discovery | zeno-skill-scout/SKILL.md |
| TS/build error resolution + formatter gate | zeno-build-resolver/SKILL.md |
| Inline comment accuracy/rot audit | zeno-comment-analysis/SKILL.md |
| Harness reliability/cost/throughput tuning | zeno-harness-optimizer/SKILL.md |
| Cross-layer, profiling-driven performance work | zeno-performance-profiling/SKILL.md |
| File-level implementation planning | zeno-planning/SKILL.md |
| Dead-code/duplication cleanup | zeno-refactor-cleanup/SKILL.md |
| Local cost-tracking report | zeno-cost-report/SKILL.md |
| Model-tier recommendation | /model-route command owns the heuristic; zeno-model-route/SKILL.md is a thin router (and the Codex fold home) |
Session save/resume/list/alias (repos with no tracked .zeno/) | zeno-sessions/SKILL.md |
Instructions
- Identify the technology or domain from the request or the codebase's existing imports/config.
- Load and apply only the matching leaf above. Each carries its own complete standards and both required enforcement sections (Anti-pattern quick reference, Pre-flight checklist) — this dispatcher holds routing only.
- If multiple technologies are in scope (e.g. a FastAPI backend + React frontend), apply each relevant leaf to its own layer.
- For rate limiting specifically, always defer to
zeno-redis-patterns— it is the single source of truth; no other leaf should carry its own rate-limiter implementation. - For local-vs-external skill discovery,
zeno-find-skillscovers what's already installed;zeno-skill-scoutcovers marketplace/GitHub search and itself delegates local search tozeno-find-skillsrather than duplicating it. - If the technology isn't listed above, apply general clean-code/SOLID principles and say so — don't force-fit an unrelated leaf.
In this repository91 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- goSkill
- json-standardsSkill
- pythonSkill
- rabbitmqSkill
- rSkill
- rustSkill
- code-standardsSkill
- software-architectureSkill
- swiftSkill
- typescript-code-standardsSkill
- architecture-documentation-and-decision-recordsSkill
- business-requirements-standardsSkill
- developer-handoff-standardsSkill
- development-planning-standardsSkill
- document-writer-reviewerSkill
- feature-planning-standardsSkill
- functional-specification-standardsSkill
- non-functional-requirements-standardsSkill
- operations-standardsSkill
- product-requirements-standardsSkill
- documentationSkill
- solution-architecture-standardsSkill
- technical-requirements-standardsSkill
- documenting-codeSkill
- github-circleci-standardsSkill
- graphifySkill
- puml-diagramsSkill
- software-architecture-progressionSkill
- testingSkill
- software-test-specificationSkill
- zeno-councilSkill
- zeno-debugSkill
- zeno-insightSkill
- zenoSkill
- zeno-accessibilitySkill
- zeno-angular-developerSkill
- zeno-api-designSkill
- zeno-browser-qaSkill
- zeno-build-resolverSkill
- zeno-codebase-onboardingSkill
- zeno-code-tourSkill
- zeno-comment-analysisSkill
- zeno-config-gcSkill
- zeno-context-budgetSkill
- zeno-context-compactionSkill
- zeno-cost-reportSkill
- zeno-database-migrationsSkill
- zeno-deep-researchSkill
- zeno-deployment-patternsSkill
- zeno-design-systemSkill
- zeno-docker-patternsSkill
- zeno-e2e-testingSkill
- zeno-error-handlingSkill
- zeno-find-skillsSkill
- zeno-frontend-designSkill
- zeno-github-opsSkill
- zeno-git-workflowSkill
- zeno-harness-optimizerSkill
- The first 60 shown.
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.