SkillAgentSearch skills...

session

Extract conversation turns from AI session history files (.jsonl)

Install / Use

npx skills add axoviq-ai/synthadoc --skill session

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

84/100

Supported Platforms

Claude Code
Cursor
OpenAI Codex

Tags

Our assessment of session

session scores 84/100 on our quality scale, 256th of 319 Customer Support skills we index.

Its SKILL.md is 3.5 KB long, well organised into 8 sections with 3 code examples: a solid amount of guidance for an agent.

With 1,351 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
18/20
Description
12/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so session is actively maintained.
  • Our last check on 2026-11-06 found the source still online.
  • It is released under AGPL-3.0, a copyleft license: you can use it, but modified versions you distribute must carry the same license.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-01. Automated pattern scan on 2026-10-01. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

session compared with similar skills

All 4 of these similar skills score higher than session; compare them before choosing.

SkillScoreStarsUpdatedFormat
session (this skill)by axoviq-ai841.4k54d agoSKILL.md
x402by browser-use100121.0k3d agoSKILL.md
algorithmic-artby anthropics100177.9k55d agoSKILL.md
pptxby anthropics100177.9k55d agoSKILL.md
designby nextlevelbuilder100149.0k6d agoSKILL.md

Frequently asked questions

How do I install session?
Run npx skills add axoviq-ai/synthadoc --skill session. The install tabs above show the steps for each supported agent.
Which AI agents does session work with?
It is written for Claude Code, Cursor and OpenAI Codex, as a SKILL.md file. Other agents that read the same format can often use it too.
Is session safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is AGPL-3.0-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is session still maintained?
The repository was last updated about 2 months ago, so session is actively maintained.

name: session version: "1.0" description: Extract conversation turns from AI session history files (.jsonl) entry: script: scripts/main.py class: SessionSkill triggers: extensions: - ".jsonl" intents: - "claude session" - "codex session" - "cursor session" - "ai session" - "session history" requires: [] author: axoviq.com license: AGPL-3.0-or-later

Session Skill

Extracts human-readable conversation turns from AI coding session history files (.jsonl). Supports two formats:

  • Claude Code — the JSONL format written by Anthropic's Claude Code CLI (~/.claude/projects/<hash>/<session-id>.jsonl)
  • Codex / Cursor — the simpler {"role": ..., "content": ...} per-line format used by OpenAI Codex and Cursor IDE sessions

Format is detected automatically from the first parseable line.

What gets extracted

Only substantive conversation turns are kept:

| Content type | Action | |---|---| | User text messages | Kept if ≥ 3 words | | Assistant text responses | Kept if ≥ 20 words | | Assistant thinking blocks | Skipped (internal reasoning, not final output) | | Tool use / tool result blocks | Skipped (avoids leaking file contents or credentials) | | Image / attachment blocks | Skipped | | Sub-agent scaffolding (isSidechain: true) | Skipped (internal sub-agent turns) | | Session metadata lines | Skipped (permission-mode, file-history-snapshot, system, last-prompt) |

The extracted text is then passed through Synthadoc's standard pre-LLM source sanitizer (zero-width characters, bidi overrides, HTML comments, hidden CSS spans, base64 blobs, instruction-override phrases), exactly like PDF, DOCX, URL, and every other source type.

Output format

Each turn is labelled [USER] or [ASSISTANT] and separated by ---:

[USER]
How do I implement a sliding window algorithm?

---

[ASSISTANT]
A sliding window algorithm maintains a contiguous subarray (the "window") …

suggested_slug

The skill returns a suggested_slug in metadata derived from the session file's modification time and the first substantive user message:

session-2026-07-15-how-do-i-implement-a-sliding

Large sessions — chunking

Sessions longer than 30 substantive turns are split into 30-turn chunks. Each chunk is labelled with a ## Part N of M header so the downstream LLM can process sections independently. The metadata dict includes chunk_total when chunking occurs; single-chunk sessions (≤ 30 turns) are unchanged.

Limitations

  • Tool output excluded — tool result blocks (shell output, file reads, etc.) are stripped. This is intentional: it avoids leaking file contents and credentials into the wiki.
  • Format auto-detection — detection inspects the first 30 parseable lines. Corrupt or empty files produce an empty ExtractedContent.
  • No deduplication across ingest runs — re-ingesting the same session file creates or updates the same wiki page (standard ingest dedup applies via source hash).

When this skill is used

  • Source path ends with .jsonl
  • Intent phrases: "claude session", "codex session", "cursor session", "ai session", "session history"

Standalone usage

import asyncio
from synthadoc.skills.session.scripts.main import SessionSkill

skill = SessionSkill()

async def main():
    result = await skill.extract("/path/to/session.jsonl")
    print(result.text)       # [USER]\n...\n\n---\n\n[ASSISTANT]\n...
    print(result.metadata)   # {"format": "claude_code", "turn_count": 42, "suggested_slug": "..."}

asyncio.run(main())

Related Skills

View on GitHub
GitHub Stars1.4k
CategoryCustomer
Updated1mo ago
Forks131

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions
session — Claude Code Skill: Install & Safety Check | SkillAgent