GitHub collection

kongfangxun/sofagent

Imported from GitHub — is this yours?

15 skills imported from this repository.

Claude Skill

cordis-plugin-sofagent

一次挂载 sofagent 全套能力——6 项能力一次到位(注入 · 审计与验收 · 经验 · 回溯 · 巡检 · FDE 三域)(seam: non-seam:plugin-suite)——只编排不重实现——sofagent 约束层在 DSH(DeepSeek Harness)生态的插件形态。

LLM Mart

Claude Skill

cordis-plugin-sofagent-audit

变更机器审阅 + 验收硬门禁——24 规则 + git diff 硬证据 + Turn 停止验收判定(验收不过不放行,开关独立可关)(seam: tools/result + tools/pre-execute + fs/write-intent + agent/turn-stopping)——桥接 @sofagent/audit runRules——DSH(DeepSeek Harness)cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

LLM Mart

Claude Skill

cordis-plugin-sofagent-daemon

7×24 巡检 + 健康监测 + webhook 推送(seam: non-seam:host-process)——桥接 @sofagent/daemon startCron——DSH(DeepSeek Harness)cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

LLM Mart

Claude Skill

cordis-plugin-sofagent-evolve

经验沉淀——think.md 反思 + Dream Cycle + evolve + instinct→skill + refine(seam: turn/end)——桥接 @sofagent/think generateThinkEntry——DSH(DeepSeek Harness)cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

LLM Mart

Claude Skill

cordis-plugin-sofagent-fde

FDE 进场与能力流通——把企业业务梳理成 AI 能力,并让这些能力在企业内被发布、发现、调用、评价、退役(seam: non-seam:tool-set)——桥接 @sofagent/orchestrator publishCapability / @sofagent/ontology generateOntologyView / @sofagent/core restoreSnapshot——DSH(DeepSeek Harness)cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

LLM Mart

Claude Skill

cordis-plugin-sofagent-inject

启动注入企业约束——四层加载链(seam: agent/pre-step)——桥接 @sofagent/harness buildConstrainedSystemPrompt——DSH(DeepSeek Harness)cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

LLM Mart

Claude Skill

cordis-plugin-sofagent-rollback

出错逆序撤销——git snapshot → effect disposer(seam: agent/error)——桥接 @sofagent/core getHistoryFilePath——DSH(DeepSeek Harness)cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。

LLM Mart

Claude Skill

enterprise-fde-识别AI节点

当 FDE 需要对工作流节点做 AI 分类判定时用这个 Skill—— 不是"它是干什么的",是"什么时候用"。 写错 description = Skill 永远不会被触发。

LLM Mart

Claude Skill

fresh-eyes-loop

发布后独立质量循环——单盲四角色流水线(A 审 12 视角 → B 修 → C 验 → D 复核),每轮新 session 保证零上下文,连续 2 轮无 P0/P1 即停。

LLM Mart

Claude Skill

release-gate-loop

发版前自动验证闸门——V 验证 + F 修复循环(verdict FAIL → F 改代码 → 跑 audit → V 重验),最大 3 轮直到 PASS。纯只读验证 + 最小修复。

LLM Mart

Claude Skill

codebase-design

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

LLM Mart

Claude Skill

domain-modeling

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.

LLM Mart

Claude Skill

grilling

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

LLM Mart

Claude Skill

grill-with-docs

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

LLM Mart

Claude Skill

improve-codebase-architecture

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

LLM Mart