跳到正文
cccskills
免费在 GitHub 公开

export-session-log

Export the current chat session as a structured Markdown work timeline or blog-draft seed. Use when the user asks for a session log, work log, timeline, 作業ログ, ブログネタ, blog draft, article seed, Zenn, Qiita, or はてな. Do not use for verbatim dialogue export or distilled reusable knowledge only.

中文简介正在准备中。当前显示原文说明。

集成工具QiitaZenn
查看安装方法

包含的文件(5)

  • SKILL.md4.3 KB
  • LICENSE.txt5.2 KB
  • PROVENANCE.md635 B
  • references/session-log-template.md1.3 KB
  • skill-license.json842 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Export Session Log

Turn the available conversation, tool results, changed files, and commands into a concise Markdown work log that supports handoff, resumption, or article drafting.

When to Use

  • The user asks for a session log, work log, timeline, 作業ログ, or to save the current session.
  • The user asks for ブログネタ, a blog draft, an article seed, or material for Zenn, Qiita, or Hatena.
  • The work history, decisions, validation results, and next steps need to be preserved for later use.

Do Not Use For

  • A transcript that reproduces every message in dialogue order.
  • Knowledge extraction that intentionally omits the session history.
  • Reconstructing work that is not present in the available conversation or evidence.

Workflow

  1. Infer the topic, standard or blog intent, and any explicit destination from the request.
  2. Read the current local time from the system and use the actual value in yyyy-MM-ddTHH:mm:ss format. With PowerShell, run Get-Date -Format "yyyy-MM-ddTHH:mm:ss".
  3. Resolve the output root using the priority rules below. Ask before creating anything only when no root can be resolved.
  4. Extract the summary, phases, changed files, learnings, useful commands, references, outcome, and unfinished work from available evidence.
  5. Create or append the log using session-log-template.md.
  6. Read the saved file back and verify its frontmatter, title, Timeline, actual exported_at, and any required References.
  7. Report the saved path and the final success, partial, or failed status.

Output Root Resolution

An explicit destination always wins. Otherwise resolve by intent:

IntentEnvironment variableWorkspace fallback
StandardEXPORT_SESSION_LOG_DIR{workspace}/output_sessions/
BlogEXPORT_SESSION_BLOG_DIRExisting {workspace}/drafts_topic/
  • For blog output, ask for a destination when the environment variable is unset and drafts_topic/ does not exist.
  • Ask for a destination when there is no workspace and the applicable environment variable is unset.
  • Do not create a directory or file before resolving the output root.

File Naming And Append Rules

  • Name new files YYYYMMDD-NN--{topic}.md.
  • Use a short, descriptive, lowercase kebab-case topic.
  • Append to an existing same-day, same-topic file in the resolved destination.
  • Otherwise increment the highest same-day NN; start at 01 when none exists.
  • When appending, preserve the existing frontmatter and body, then add the append block from the template.

Content Rules

  • Choose type from coding, research, debug, design, or discussion.
  • Record only tools that were actually used.
  • Use Phase N - {phase name} headings rather than invented timestamps.
  • Compress three or more repeated attempts into N attempts plus the final resolution.
  • Prefer workspace-relative Markdown links for changed files.
  • When external pages informed a conclusion, list only the pages actually used, with title and URL, under References.
  • When another workspace file informed the work or is needed to resume it, list a sufficiently identifying path under References.
  • Include only reusable commands. Remove secrets, tokens, passwords, personal data, and sensitive local values.
  • Never present guessed times, unexecuted commands, unused search candidates, or hidden reasoning as session evidence.

Success Contract

  • The Markdown file exists at the resolved destination and follows the requested intent and naming rules.
  • The log captures the current session outcome, verification evidence, and remaining work at a resumable level.
  • External sources and cross-workspace files have corresponding References when they were used.
  • The result contains no secrets, sensitive data, or hidden reasoning.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Design, review, and debug agent workflows, and decide when a request should use a prompt, instruction, skill, agent, or hook before escalating to multi-agent design. Use for .agent.md / .instructions.md / .prompt.md / AGENTS.md work, workflow architecture, orchestration planning, scheduled automation model allocation, or when agent workflows may be overkill. Triggers on 'agent workflow', 'create agent', 'automation models', 'ワークフロー設計', 'orchestrator'.

中文简介正在准备中。当前显示原文说明。

aktsmm/Agent-Skills262026年10月19日 更新

Design, run, and review fair performance, token, and cost comparisons across GitHub Copilot CLI, Codex CLI, and direct model APIs. Use for AI CLI benchmark, Copilot vs Codex, prompt-cache diagnosis, cache read/write analysis, fresh-process latency measurement, token-cost comparison, or when a benchmark must separate provider caching from local CLI caches.

中文简介正在准备中。当前显示原文说明。

aktsmm/Agent-Skills262026年10月19日 更新

Analyze historical VS Code GitHub Copilot Chat sessions by model, reasoning effort, AIU, time, reliability, workflow behavior, and external quality evidence, or safely prune workspace-scoped local chat history by age. Use for session analysis, repeated-task retrospectives, model evaluation, cost/performance analysis, and old session cleanup.

中文简介正在准备中。当前显示原文说明。

aktsmm/Agent-Skills262026年10月19日 更新

Create reproducible animated infographic GIFs from structured data or measured results, with audience-language labels, explicit timing semantics, representative-frame QA, and a static fallback. Use when asked for GIF生成, animated infographic, 動的インフォグラフィック, 結果が流れる図, animated benchmark, or a blog/SNS animation whose displayed metrics must remain traceable to source data.

中文简介正在准备中。当前显示原文说明。

aktsmm/Agent-Skills262026年10月19日 更新

archify

免费

Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and stateDiagram input; inspect repository evidence when the diagram must reflect real code. Use when the user asks to visualize system architecture, infrastructure, cloud/security/network topology, technical workflows, API call sequences, request lifecycles, data pipelines, ETL/ELT, data lineage, state machines, or to convert/beautify Mermaid. Also use for Archify, interactive or animated HTML diagrams, インタラクティブ図, 動く構成図. When an editable .drawio file is required, use the draw.io workflow instead and treat Archify HTML only as a supplement.

中文简介正在准备中。当前显示原文说明。

aktsmm/Agent-Skills262026年10月19日 更新

Generate ASCII-art text banners for terminals, READMEs, and CLI startup messages. Use when a user asks for an ASCII banner, text art, バナー, アスキーアート, or a decorative header for a script/README.

中文简介正在准备中。当前显示原文说明。

aktsmm/Agent-Skills262026年10月19日 更新

查看 aktsmm 的全部技能

报告此技能的问题