AGENT SKILL

write-conformant-code

Write code in any language that matches project conventions exactly. Reads CODING_REQUIREMENTS.md, prior review output, or built-in defaults before writing. Part of Codecraft pipeline: analyze → write → review → audit. Use when implementing features, functions, or any code that should fit seamlessly into an existing codebase.

License 许可
MIT
所属仓库
dasobral/skills
最近更新
2026-08-15
Stars
★ 0
Forks
0

01 前言 Front Matter

name
write-conformant-code
description
Write code in any language that matches project conventions exactly. Reads CODING_REQUIREMENTS.md, prior review output, or built-in defaults before writing. Part of Codecraft pipeline: analyze → write → review → audit. Use when implementing features, functions, or any code that should fit seamlessly into an existing codebase.

02 资源文件 5

03 SKILL.md 正文

Write Conformant Code

Write code that belongs in the codebase — every line should look like it was written by a senior engineer already on the team.

Pipeline Position

analyze-codebase → write-conformant-code → review-quality → audit-cognitive-debt

Step 1 — Load Style Context

Read references/repository-conventions.md before selecting a style source.

Priority Source
1 CODING_REQUIREMENTS.md (docs/ or repository root)
2 review-quality output in current conversation
3 User-provided style notes
4 references/default-style.md for detected language

Announce which source was used. If no requirements file exists:

No CODING_REQUIREMENTS.md found — using defaults. Run analyze-codebase first.

Step 2 — Read Before Writing

Glob and read 2–3 files in the target module. Match:

  • Naming (functions, types, files)
  • Error handling patterns
  • Import/module structure
  • Test placement and style
  • Comment density

Step 3 — Plan the Change

State: files to create/modify, public API surface, error cases, test approach. Keep scope minimal — only what the user asked for.

Step 4 — Implement

Output code-first. For each file:

  • Full implementation (not stubs)
  • Imports matching project style
  • Tests when the project has a test culture

See references/task-patterns.md for common task shapes.

Step 5 — Self-Check

Before finishing, verify against loaded conventions:

  • [ ] Naming matches surrounding code
  • [ ] Error handling follows project pattern
  • [ ] No unnecessary abstractions
  • [ ] Tests included if project tests similar code

Suggest running review-quality on the diff.

Rules

  • Never invent conventions — infer from code or requirements file
  • Minimize diff scope
  • See references/pipeline-integration.md for full pipeline usage

04 同仓库更多 Skills

dasobral
dasobral/skills

fixture-skill

Fixture skill used to prove trust inventory coverage.

Skill与智能体开发
★ 0
dasobral
dasobral/skills

test-crypto-interoperability

Record reproducible cryptographic interoperability cases, including negotiation, fallback, sizes, latency, fragmentation, and negative tests.

测试与质量
★ 0
dasobral
dasobral/skills

scientific-platform-architect

Design scientific computing platforms combining HPC kernels with modern infrastructure. Enforces compute-layer separation (Rust/PyTorch/Python), emulator-first thinking, and right-sized infrastructure. Use for MCMC pipelines, neural emulators, platform design, or scientific code review.

设计师代码审查视觉设计
★ 0
dasobral
dasobral/skills

rust-systems

Rust systems engineering for daemons, HTTP APIs, and AOS components. Enforces Tokio/Axum async-first, LiteLLM-compatible OpenAI APIs, workspace layouts, tracing, and systemd-compatible daemon design. Part of AOS Stack plugin. Use for .rs files, Cargo.toml, daemons, or Rust orchestrator services.

视觉设计
★ 0
dasobral
dasobral/skills

run-agent-attack-replay

Aggregate isolated agent attack trials with deterministic side-effect assertions, Wilson intervals, and preserved trace evidence.

Skill与智能体开发
★ 0
dasobral
dasobral/skills

review-quality

Language-agnostic code review across four pillars: Clarity, Simplicity, Good Practices, and Security. Produces severity-tagged findings (CRITICAL/WARNING/SUGGESTION). Complements audit-cognitive-debt for dead code and duplication. Part of Codecraft plugin. Use when asked to review code quality, audit security, check best practices, or find code smells.

代码审查
★ 0