sordi-ai
- 25 skills
- 0 followers
- 8 hours ago last updated
- ▌ Skill Everything · sordi-ai bundleGit-versioned agent memory — agents that never make the same mistake twice.
- ▌ Tdd · sordi-aiApply when adding new behavior or fixing a bug. Red-green-refactor cycle, test-first discipline, when TDD doesn't pay.
- ▌ React · sordi-aiApply when writing React components. Hook discipline, state placement, performance, async cleanup, and list keys.
- ▌ Docker · sordi-aiApply when writing or reviewing Dockerfiles, docker compose files, or container build pipelines. Covers layer caching, multi-stage builds, security hardening, and compose conventions.
- ▌ Drawio · sordi-aiApply when creating or reviewing architecture diagrams, Mermaid diagrams, or draw.io files.
- ▌ Python · sordi-aiApply when writing Python code. Type hints, error handling, mutable defaults, async patterns, and packaging conventions.
- ▌ Fastapi · sordi-aiApply when building FastAPI endpoints, Pydantic models, or async APIs. Covers routing, dependency injection, error handling, testing, and OpenAPI hygiene.
- ▌ Kebab Case Name · sordi-ai<one-sentence trigger condition — when should this skill be loaded? Start with "Apply when ..." for consistency.>
- ▌ DB Schema · sordi-aiApply when designing database schemas, writing migrations, or reviewing table structure. Covers naming, keys, indexes, constraints, nullability, and migration safety.
- ▌ Debugging · sordi-aiApply when diagnosing a bug, reproducing a failure, or performing root cause analysis. Covers systematic isolation, binary search, logging strategy, and hypothesis-driven investigation.
- ▌ Error Log · sordi-ai bundleApply when learning from a mistake. Central memory of past errors and derived rules; consult before logging a new error to avoid duplicates.
- ▌ Langchain · sordi-aiApply when building LangChain pipelines, LCEL chains, agents, or retrieval-augmented generation systems.
- ▌ Svg Check · sordi-ai bundleApply when editing, generating, or reviewing any SVG diagram. Pixel-perfect Playwright bbox-check is the acceptance test — eyeballing is not sufficient. Run on every SVG before declaring done.
- ▌ Github CLI · sordi-aiApply when using the gh CLI to manage pull requests, issues, releases, or CI workflows on GitHub.
- ▌ Typescript · sordi-aiApply when writing TypeScript code. Strict types, discriminated unions, async patterns, and runtime safety.
- ▌ Code Quality · sordi-aiApply when writing or refactoring code. Generic rules to prevent the most common review comments — function length, naming, error handling, security, and tooling.
- ▌ Brainstorming · sordi-aiApply when generating ideas, exploring solution space, or facilitating divergent thinking before committing to an approach.
- ▌ Domain Template · sordi-aiApply when documenting project-specific knowledge. Template for ADRs, naming conventions, business rules, and tech-stack quirks.
- ▌ Git Conventions · sordi-aiApply when committing, branching, or opening a pull request. Conventional commit format, branch naming, PR scope.
- ▌ Security Review · sordi-aiApply when performing a security review, checking for vulnerabilities, or implementing authentication and authorization logic.
- ▌ Shell Scripting · sordi-aiApply when writing or reviewing Bash or POSIX shell scripts — automation, CI steps, deploy scripts, or any shell-based tooling.
- ▌ Branch Finishing · sordi-aiApply when closing out a feature branch — pre-merge checklist, rebase, CI verification, cleanup, and post-merge steps.
- ▌ Review Deployment · sordi-aiApply when reviewing code or planning a deployment. Pre-merge checks, migration ordering, rollback strategy, post-deploy verification.
- ▌ Implementation Plan · sordi-aiApply when planning before writing code, defining scope, or producing an implementation plan for a feature or change.
- ▌ Self Extension Workflow · sordi-aiApply when executing the self-extension workflow. Six steps from a mistake to a merged rule, with CI gates and CODEOWNERS approval.