Agent skill
pmtl-production-baseline
PMTL_VN production-grade coding and runtime baseline. Use when implementing or refactoring features that need repo-specific defaults for logging, validation, security posture, caching, monitoring, deployment boundaries, and documentation sync.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/pmtl-production-baseline
SKILL.md
PMTL Production Baseline
Purpose
Provide the non-negotiable PMTL repo defaults for production-grade implementation, runtime safety, validation, logging, and documentation sync.
Use When
- Implementing or refactoring features that affect real runtime behavior.
- Changing logging, env contracts, validation, caching, or request boundaries.
- You need the default PMTL baseline before applying narrower skills.
- The task spans multiple apps or modules and needs one shared runtime policy anchor before deeper specialization.
Required Inputs
- touched app/package/module
- relevant owner docs or design files for the changed runtime rule
- expected verification scope
Expected Output
- Code and docs that follow the same repo-wide production baseline.
- No silent runtime policy drift across apps, packages, and docs.
Read first
- Read
AGENTS.md. - Read
docs/architecture/conventions.md. - Read
docs/architecture/skills-taxonomy.mdwhen changing AI workflow or skill routing. - Read
docs/runbooks.mdanddocs/troubleshooting.mdwhen the task touches monitoring or recovery.
Execution Approach
- Confirm the touched layer and keep logic in the correct package or app boundary.
- Validate user input and env contracts before changing runtime behavior.
- Add or preserve structured logging at real operational boundaries.
- Update docs and skill routing in the same task when rules change.
- Hand off to narrower PMTL skills when the task becomes mostly frontend behavior, auth verification, search verification, or incident recovery.
Baseline rules
- Preserve monorepo boundaries from
pmtl-vn-architecture. - Validate user input and env contracts with Zod.
- Log operational failures with structured context using pino.
- Keep Vietnamese text fully accented in UI, API messages, and seeded content.
- Keep Next.js request-boundary logic in
apps/web/src/proxy.tsunless official versioned guidance proves otherwise. - Prefer
"use cache"helpers and data-layer caching over page-level cache flags. - Do not leave runtime rule changes undocumented. Update
AGENTS.md, local skills, and affected docs together.
Verification
- Re-read the touched docs and confirm the rule still matches code.
- Pair with
pmtl-verify-quality-gateafter meaningful edits. - If auth or search contracts changed, pair with the dedicated verification skill for that area.
Quality Criteria
- Runtime policy stays aligned across docs, code, and skill routing.
- Boundary ownership remains explicit; no logic leaks into the wrong app or package.
- Rule changes are documented in the same task instead of becoming tribal knowledge.
Edge Cases
- Older audit notes can conflict with current repo reality; prefer verified 2026 docs.
- Convenience fixes in one app can accidentally break monorepo boundaries or request ownership.
References
docs/architecture/conventions.mddocs/architecture/skills-taxonomy.mddocs/runbooks.mddocs/troubleshooting.md
Use this skill with
pmtl-fe-implementationfor frontend code changes.pmtl-ui-behaviorandpmtl-ui-style-systemfor UI work.pmtl-verify-quality-gateafter meaningful edits.pmtl-runbook-docker-dev-recoverywhen the task is a local/dev incident.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?