Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Echovic/Tech Lead Technical Standards — measured AI agent skill | DecimalAI

echovic/tech-lead-technical-standards

SkillScore95Maintained

技术规范和最佳实践，确保代码质量和一致性

codingby echovic

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/echovic-tech-lead-technical-standards/SKILL.md

decimalai skills pull echovic-tech-lead-technical-standards --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/echovic-tech-lead-technical-standards/SKILL.md https://app.decimal.ai/s/echovic-tech-lead-technical-standards/SKILL.md

Raw file: /s/echovic-tech-lead-technical-standards/SKILL.md ↗ · machine-readable summary at /s/echovic-tech-lead-technical-standards.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 2h ago

Yes — +18% lift-27% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	-50%	0%
case-05	✗→✓	▲ Improved	-70%	0%
case-15	✗→✓	▲ Improved	-31%	0%
case-17	✗→✓	▲ Improved	2%	0%
case-03	✓→✓	＝ Same ✓	-22%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

echovic / boss-skill

skill/skills/tech-lead/technical-standards/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

技术规范与最佳实践

命名规范

| 类型 | 规范 | 示例 | |------|------|------| | 变量 | camelCase | userName, isActive | | 常量 | UPPER_SNAKE_CASE | MAX_COUNT, API_URL | | 函数 | camelCase | getUserById, calculateTotal | | 类 | PascalCase | UserService, OrderController | | 文件 | kebab-case | user-service.ts, order-controller.ts |

代码组织

单一职责：每个函数/类只做一件事
DRY原则：不要重复代码
KISS原则：保持简单
YAGNI原则：不要过度设计

错误处理

使用try-catch捕获异常
提供有意义的错误信息
记录错误日志
优雅降级

测试要求

单元测试覆盖率 ≥ 70%
关键路径必须有测试
测试要独立、可重复

Want to see if echovic/tech-lead-technical-standards would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.