session-to-workflow
从 session 历史、实际产物与反馈恢复全貌，反思并简化阶段、步骤、资产和流程，构建工作流报告、业务 skill 与共享工作台，并组织同题重做验证。用于总结或重建历史工作流；单纯续做业务任务不必调用。
Skill by cyl19970726
Chalk Labs
Need help deploying session-to-workflow?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/cyl19970726-session-to-workflow
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/session-to-workflow
What's inside
- Skill name
session-to-workflow- Description
- 从 session 历史、实际产物与反馈恢复全貌，反思并简化阶段、步骤、资产和流程，构建工作流报告、业务 skill 与共享工作台，并组织同题重做验证。用于总结或重建历史工作流；单纯续做业务任务不必调用。
- License
- unknown
- Instructions
- 44 lines in SKILL.md · view on GitHub
Files (7)
- SKILL.md
- openai.yaml · agents/
- forensics-cooperation.md · references/
- intent-and-collaboration-audit.md · references/
- mental-model.md · references/
- workflow-report-template.md · references/
- workspace-and-topic-intake.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from cyl19970726/reuse-agent-infra
- 0.587score
session-forensics-v4-2
cyl19970726
会话观察者（v4.2 草案）：为一段 agent 工作（Claude Code、Codex、Kimi、dsh 会话，可以多个）建立并维护一份认知——任务地图：你要什么 → 走到哪 → 还在主线上吗 → 卡在哪 → 下一步，项目里现成的…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
session-handoff-v4-2
cyl19970726
接手一段 agent 工作（v4.2 草案）：压缩之后、换人、换 CLI、中断后续做时使用。先拿到任务地图，再核对现场， 把答案写成接手型（主线、第一件事、现场核对、已失效），交出给下一个人的精简地图，然后直接续做。 依赖底座 session-forensics-v4-2（装在本 skill 旁边的同级目录）。
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
session-audit-v4-2
cyl19970726
审计定责（v4.2 草案）：判断一段 agent 工作哪里做错了、主因是什么、本该在哪停。用于「为什么一直失败」「这次是谁的问题」。 要防再犯时，答案改成底座的改流程型。先建任务地图并请一位核对者核，再对照项目规范定责。 依赖底座 session-forensics-v4-2（装在本 skill 旁边的同级目录）。
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
session-forensics
cyl19970726
给 agent 会话配「观察者」：读完整会话历史（Codex rollout JSONL、Claude Code transcript、 Kimi wire、DeepSeek Harness / dsh 的 zstd 会话，含 subagent/team 日志）， 用「物证流 vs 叙事流」对质，找出执行…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
x-grok-chat
cyl19970726
Use ego-browser to chat with Grok inside X at x.com/i/grok, retrieve complete answers and every cited X post/profile and web source URL, and preserve context…
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
xhs-ai-chat
cyl19970726
Use ego-browser to chat with 小红书点点 at xiaohongshu.com/ai_chat, retrieve complete replies, and preserve context across multi-turn follow-ups.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
unknowns-to-gates
cyl19970726
未知→决策→执行→固化的全链路防错总纲(地图≠疆域):四象限错误发生学(KK/KU/UK/UU)+ 授权三档(C档未知必须问不许猜) + 决策闭包覆盖表 + 探索深挖判断力 + 洞见固化成闸防复发。合并自 decision-closure / exploration-judgment /…
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 15, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/cyl19970726/reuse-agent-infra
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from cyl19970726
- 0.587score
session-forensics-v4-2
cyl19970726
会话观察者（v4.2 草案）：为一段 agent 工作（Claude Code、Codex、Kimi、dsh 会话，可以多个）建立并维护一份认知——任务地图：你要什么 → 走到哪 → 还在主线上吗 → 卡在哪 → 下一步，项目里现成的…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
session-handoff-v4-2
cyl19970726
接手一段 agent 工作（v4.2 草案）：压缩之后、换人、换 CLI、中断后续做时使用。先拿到任务地图，再核对现场， 把答案写成接手型（主线、第一件事、现场核对、已失效），交出给下一个人的精简地图，然后直接续做。 依赖底座 session-forensics-v4-2（装在本 skill 旁边的同级目录）。
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
session-audit-v4-2
cyl19970726
审计定责（v4.2 草案）：判断一段 agent 工作哪里做错了、主因是什么、本该在哪停。用于「为什么一直失败」「这次是谁的问题」。 要防再犯时，答案改成底座的改流程型。先建任务地图并请一位核对者核，再对照项目规范定责。 依赖底座 session-forensics-v4-2（装在本 skill 旁边的同级目录）。
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
session-forensics
cyl19970726
给 agent 会话配「观察者」：读完整会话历史（Codex rollout JSONL、Claude Code transcript、 Kimi wire、DeepSeek Harness / dsh 的 zstd 会话，含 subagent/team 日志）， 用「物证流 vs 叙事流」对质，找出执行…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
x-grok-chat
cyl19970726
Use ego-browser to chat with Grok inside X at x.com/i/grok, retrieve complete answers and every cited X post/profile and web source URL, and preserve context…
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
xhs-ai-chat
cyl19970726
Use ego-browser to chat with 小红书点点 at xiaohongshu.com/ai_chat, retrieve complete replies, and preserve context across multi-turn follow-ups.
SkillBFreshness: B★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get session-to-workflow running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
session-to-workflow skill. Agent Mart. https://agentmart.dev/skills/cyl19970726-session-to-workflow (last updated 2026-10-24)