Ready to supercharge your AI agents?

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

Get Started Free →

Ralphinho RFC 管道 — measured AI agent skill | DecimalAI

affaan-m/ralphinho-rfc-pipeline

SkillScore91Maintained

RFC駆動の複数エージェントDAG実行パターン、品質ゲート、マージキュー、ワークユニットオーケストレーション。

agent-toolingby affaan-m

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

Automatic

Coding pack

decimalai skills pull affaan-m-ralphinho-rfc-pipeline

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/affaan-m-ralphinho-rfc-pipeline/SKILL.md

Raw file: /s/affaan-m-ralphinho-rfc-pipeline/SKILL.md ↗ · machine-readable summary at /s/affaan-m-ralphinho-rfc-pipeline.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

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago

Yes — +57% lift-6% tokens0% turns91% of whole cases pass with skill (21/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-3%	0%
case-02	✗→✓	▲ Improved	6%	0%
case-03	✗→✓	▲ Improved	3%	0%
case-08	✗→✓	▲ Improved	5%	0%
case-09	✗→✓	▲ Improved	-30%	0%

Showing 5 of 23 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

affaan-m / ecc

docs/ja-JP/skills/ralphinho-rfc-pipeline/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v4

Skill contents

SKILL.md

Ralphinho RFC 管道

灵感来源于 humanplane 风格的 RFC 分解模式和多单元编排工作流。

当一个功能对于单次代理处理来说过于庞大，必须拆分为独立可验证的工作单元时，请使用此技能。

管道阶段

RFC 接收
DAG 分解
单元分配
单元实现
单元验证
合并队列与集成
最终系统验证

单元规范模板

每个工作单元应包含：

id
depends_on
scope
acceptance_tests
risk_level
rollback_plan

复杂度层级

层级 1：独立文件编辑，确定性测试
层级 2：多文件行为变更，中等集成风险
层级 3：架构/认证/性能/安全性变更

每个单元的质量管道

研究
实现计划
实现
测试
审查
合并就绪报告

合并队列规则

永不合并存在未解决依赖项失败的单元。
始终将单元分支变基到最新的集成分支上。
每次队列合并后重新运行集成测试。

恢复

如果一个单元停滞：

从活动队列中移除
快照发现结果
重新生成范围缩小的单元
使用更新的约束条件重试

输出

RFC 执行日志
单元记分卡
依赖关系图快照
集成风险摘要

Want to see if affaan-m/ralphinho-rfc-pipeline 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.