All skills
simota avatar

/builder

@c805268
by shingo imotasimota/agent-skills85 stars
15

Implementing robust business logic, API integrations, data models, and reproducible AI image-generation code with type safety. Use for production implementation, Gemini image API pipelines, or interactive pair programming.

Use this Skill: https://skilld.dev/gh/simota/agent-skills/builder

This session only. Nothing lands on disk.

referencerecipes-index.md

≈838 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Builder Recipe Registry

The full Recipe table for builder. builder/SKILL.md carries only the dispatch allowlist; this file holds what is needed to execute a Recipe — activation condition and the files to read first.

Read this when a subcommand matched and you need its row, or when scanning what Recipes exist at all.


Recipe Subcommand Default? When to Use Read First
Bug Fix fix ✓ Scoped fix after Scout handoff, target <50 lines —
CRUD crud Single-aggregate CRUD, no invariants, 30-60 lines reference/implementation-policy.md
API Integration api REST/GraphQL/WS client/server, idempotency critical reference/implementation-policy.md
Domain Model ddd Aggregate root, invariants, domain events, multi-file reference/implementation-policy.md
Prototype Harden harden Productionize Forge output, raise quality L0-L3 reference/implementation-policy.md
Cross-Language Port port Port between languages / frameworks (semantic equivalence tests, Parallel Run) reference/cross-language-port.md
External API Integrate integrate External service integration (auth, webhook, sandbox verification, vendor-specific retry) reference/external-integration.md
Targeted Patch patch Scoped fix under 30 lines / 3 files (smaller than fix, lighter than harden) reference/targeted-patch.md
Pair Programming pair Interactive co-implementation — write production code together, confirming each increment (INTERACTIVE) reference/pair-programming.md
Image Generate image Gemini text-to-image or grounded-generation Python implementation reference/image-generation-prompts.md, reference/image-generation-api.md
Image Edit image-edit Reference-based or iterative image-editing code reference/image-generation-api.md
Image Prompt image-prompt JP-to-EN prompt optimization and parameter design reference/image-generation-prompts.md
Image Batch image-batch Seeded, resumable, rate-limit-aware asset generation reference/image-generation-batch.md, reference/image-generation-api.md
Image Style image-style Reference-style anchoring and reusable style-token extraction reference/image-generation-style-transfer.md
Image Postprocess image-postprocess Upscale, inpaint, outpaint, artifact checks, and export formats reference/image-generation-postprocess.md
Image Cinematic image-cinematic Camera, lens, lighting, film-stock, and composition prompt design reference/image-generation-cinematic-prompts.md
Image Provenance image-provenance C2PA, SynthID, EXIF/XMP disclosure, and takedown flow reference/image-generation-provenance.md
Image Policy image-policy Content-policy, likeness, brand-safety, and regional compliance gates reference/image-generation-content-safety.md
Grammar & Parser grammar Author a regex, parser, or DSL and its AST reference/grammar/regex-safety.md, reference/grammar/parser-generators.md
CLI & TUI cli Implement a command-line or terminal-UI tool reference/cli-tui/tui-components.md, reference/cli-tui/cli-design-anti-patterns.md

Source: SKILL.md on GitHub

No alerts13d5 checks · Risk SAFE
  • Gen Agent Trust Hub13d

    The skill provides a comprehensive environment for production-grade software development, API integration, and AI image-generation pipelines. It enforces strict engineering standards, including type safety, boundary validation, and secure secret management. While it recommends several external libraries for CLI development and image processing, all targeted resources are well-known and reputable. No malicious patterns, obfuscation, or unauthorized data access were detected.

  • Socket13d

    No alerts

  • Snyk13d

    Risk: LOW · No issues

  • Runlayer6mo

    3/8 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at c805268. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 2 weeks ago

README badge

README badge for simota/agent-skills/builder