Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Project-wide coding standards and conventions specialist. Use PROACTIVELY when writing code, making architectural decisions, or establishing project conventions. Covers coding style, commenting, error handling, validation, tech stack consistency, and project conventions across all languages and frameworks.
.claude/skills/aiskillstore-global-standards/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | 112% | 0% |
| case-11 | ✓→✓ | = Same ✓ | 111% | 0% |
| case-01 | ✓→✓ | = Same ✓ | 66% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 89% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 76% | 0% |
This skill provides comprehensive guidance on project-wide coding standards, conventions, and best practices that apply across the entire codebase regardless of language or framework.
Use this skill when:
When to apply:
Principles:
Applies to: All code files (.py,.js, .ts,.jsx, .tsx,.vue, .rb,.go, .java,.rs, .cpp,.c, .swift,.kt)
When to apply:
Principles:
Applies to: All code files across the entire codebase
When to apply:
Principles:
Applies to: All code that may throw errors (API handlers, service functions, data processing, file operations, external integrations, network requests, database operations)
When to apply:
Principles:
Applies to: Form components, API handlers, request validators, input sanitizers, schema definitions, validation middleware, file uploads, webhooks, external API integrations
When to apply:
Principles:
Applies to: Frontend, backend, database, infrastructure, testing, deployment, third-party integrations
When to apply:
Principles:
Applies to: Configuration files (.env, package.json, requirements.txt, pyproject.toml, Dockerfile, docker-compose.yml, Makefile), directories (.github/, .gitlab-ci/, scripts/, docs/), documentation files (README.md, CHANGELOG.md, CONTRIBUTING.md)
For detailed standards documentation, load reference files as needed:
references/coding-style.md - Detailed coding style guidelines, naming conventions, formatting standardsreferences/commenting.md - Commenting best practices, docstring standards, when to commentreferences/error-handling.md - Error handling patterns, exception hierarchies, logging strategiesreferences/validation.md - Validation patterns, schema definitions, security considerationsreferences/tech-stack.md - Technology stack reference, framework patterns, dependency guidelinesreferences/conventions.md - Project conventions, file structure, git workflows, CI/CD standardsWhen working on specific areas, load the appropriate reference file for detailed guidance.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-10 | fail→pass | 6,289 | 3,249 | -48% | 1 | 1 | 0% | 964 | 2,040 | +112% | 0 | 0 | — |
case-11 | pass→pass | 7,069 | 6,301 | -11% | 1 | 1 | 0% | 1,252 | 2,646 | +111% | 0 | 0 | — |
case-01 | pass→pass | 8,086 | 5,173 | -36% | 1 | 1 | 0% | 1,482 | 2,466 | +66% | 0 | 0 | — |
case-02 | pass→pass | 7,618 | 5,742 | -25% | 1 | 1 | 0% | 1,338 | 2,531 | +89% | 0 | 0 | — |
case-03 | pass→pass | 12,885 | 12,658 | -2% | 1 | 1 | 0% | 2,146 | 3,782 | +76% | 0 | 0 | — |
case-04 | fail→fail | 9,799 | 6,604 | -33% | 1 | 1 | 0% | 1,537 | 2,655 | +73% | 0 | 0 | — |
case-20 | pass→pass | 18,221 | 11,967 | -34% | 1 | 1 | 0% | 3,447 | 4,123 | +20% | 0 | 0 | — |
case-05 | pass→pass | 6,177 | 6,178 | +0% | 1 | 1 | 0% | 951 | 2,596 | +173% | 0 | 0 | — |
case-06 | pass→pass | 11,284 | 7,971 | -29% | 1 | 1 | 0% | 1,851 | 2,924 | +58% | 0 | 0 | — |
case-07 | pass→pass | 6,867 | 6,078 | -11% | 1 | 1 | 0% | 1,308 | 2,714 | +107% | 0 | 0 | — |
case-08 | pass→pass | 13,012 | 9,516 | -27% | 1 | 1 | 0% | 2,178 | 3,198 | +47% | 0 | 0 | — |
case-09 | pass→pass | 8,733 | 6,502 | -26% | 1 | 1 | 0% | 1,593 | 2,671 | +68% | 0 | 0 | — |
case-12 | pass→pass | 8,998 | 10,954 | +22% | 1 | 1 | 0% | 1,455 | 3,201 | +120% | 0 | 0 | — |
case-13 | pass→pass | 12,496 | 12,401 | -1% | 1 | 1 | 0% | 2,336 | 3,966 | +70% | 0 | 0 | — |
case-14 | fail→fail | 8,725 | 5,389 | -38% | 1 | 1 | 0% | 1,634 | 2,494 | +53% | 0 | 0 | — |
case-15 | pass→pass | 9,498 | 9,995 | +5% | 1 | 1 | 0% | 1,710 | 3,272 | +91% | 0 | 0 | — |
case-16 | pass→pass | 8,712 | 5,536 | -36% | 1 | 1 | 0% | 1,441 | 2,512 | +74% | 0 | 0 | — |
case-17 | pass→pass | 12,704 | 9,114 | -28% | 1 | 1 | 0% | 1,968 | 3,023 | +54% | 0 | 0 | — |
case-18 | pass→pass | 10,279 | 6,774 | -34% | 1 | 1 | 0% | 1,857 | 2,848 | +53% | 0 | 0 | — |
case-19 | pass→pass | 10,333 | 6,376 | -38% | 1 | 1 | 0% | 1,611 | 2,601 | +61% | 0 | 0 | — |
case-21 | pass→pass | 7,025 | 6,114 | -13% | 1 | 1 | 0% | 1,492 | 2,673 | +79% | 0 | 0 | — |
case-22 | pass→pass | 2,860 | 2,897 | +1% | 1 | 1 | 0% | 523 | 2,028 | +288% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +5 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.