shan
- Repo stars 330
- License MIT
- Author updated Live
- Author repo claude-skill-registry
- Domain
- Data
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @majiayu000 · MIT
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- macOS · Linux · Windows
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Shell exec
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: shan
description: Dump a Claude Code session transcript as navigable Markdown. Use when user wants to review, anal…
category: data
runtime: no special runtime
---
# shan output preview
## PART A: Task fit
- Use case: Dump a Claude Code session transcript as navigable Markdown. Use when user wants to review, analyze, or export a session transcript. Claude Code tooling CLI (named after Claude Shannon). runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Execute / Commands / transcript dump [session-id]” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Dump a Claude Code session transcript as navigable Markdown. Use when user wants to review, analyze, or export a session transcript. Claude Code tooling CLI (named after Claude Shannon). runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Execute / Commands / transcript dump [session-id]” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, run shell commands, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, run shell commands, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source mentions slash commands such as `/shan`; use them first when your agent supports command triggers.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, run shell commands, write/modify files.
Start with a small task and check whether the result follows “Execute / Commands / transcript dump [session-id]”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: shan
description: Dump a Claude Code session transcript as navigable Markdown. Use when user wants to review, anal…
category: data
source: majiayu000/claude-skill-registry
---
# shan
## When to use
- Dump a Claude Code session transcript as navigable Markdown. Use when user wants to review, analyze, or export a sessi…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Execute / Commands / transcript dump [session-id]” and keep inference separate from source facts.
- read files, run shell commands, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "shan" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Execute / Commands / transcript dump [session-id]
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, run shell commands, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Shan
Claude Code tooling CLI (named after Claude Shannon).
Execute
Run the shan CLI with provided arguments:
bun ~/projects/jasonkuhrt/dotfiles/packages/shan/src/bin/shan.ts $ARGUMENTSCommands
transcript dump [session-id]
Convert JSONL transcripts to navigable Markdown with columnar headings for editor outline navigation.
Arguments:
| Argument | Description |
|---|---|
[session-id] |
Optional. Partial UUID prefix (e.g., dc8ffe42). Defaults to current session. |
Output: .claude/transcripts/<session-id>.transcript.md in project directory
Examples:
/shan transcript dump # dump current session
/shan transcript dump dc8ffe42 # dump specific sessionOutput Format:
Headings use monospace columns with underscore padding for editor outline alignment:
# `001` `01/25/2026 22:45` `file-history-snapshot` `snapshot______________________`
# `002` `01/25/2026 22:45` `progress_____________` `SessionStart:clear____________`
# `003` `01/25/2026 22:46` `user_________________` `sync__________________________`
Decide Fit First
Design Intent
How To Use It
Boundaries And Review