fixing-claude-export-conversations
An agent skill by daymade, from daymade/claude-code-skills. Tags: debugging, documentation, documents, local-workflow, validation.
What it does
Fixes broken line wrapping in Claude Code exported conversation files (.txt), reconstructing tables, paragraphs, paths, and tool calls that were hard-wrapped at fixed column widths. Includes an automated validation suite (generic, file-agnostic checks). Triggers when the user has a Claude Code export file with broken formatting, mentions "fix export", "fix conversation", "exported conversation", "make export readable", references a file matching YYYY-MM-DD-HHMMSS-*.txt, or has a .txt file with broken tables, split paths, or mangled tool output from Claude Code.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add daymade/claude-code-skills --skill fixing-claude-export-conversationsOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/daymade-claude-code/claude-export-txt-better ~/.claude/skills/fixing-claude-export-conversationsSafety box score
Grade B, low risk: 19 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill only manipulates Claude Code exported conversation text files and validates the result. Its main risks are local code execution through shipped Python scripts and reading/writing files chosen by the user, including a lookup under `~/.claude` to locate the skill directory.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 2 (moderate) | It runs shipped Python with `uv run .../scripts/fix-claude-export.py` and `uv run .../scripts/validate-claude-export-fix.py`, so installing it grants local script execution. |
| Network access | 0 (none) | No remote downloads, API calls, or network sends appear in `SKILL.md` or the Python scripts; dependencies are stdlib-only. |
| Filesystem reach | 2 (moderate) | It reads an export file you point it at, writes a `*-fixed.txt` output, and `SKILL.md` tells the agent to search `~/.claude` for the skill path. |
| Secrets & credentials | 1 (low) | It processes conversation exports, which may contain pasted secrets, but it does not access keychains, `.env` files, browser sessions, or credential stores. |
| Privilege & persistence | 0 (none) | There is no sudo, service registration, global install, or shell/OS settings change. |
| Instruction hijack surface | 0 (none) | I found no instructions to ignore safety rules, fetch remote prompts, or hide behavior; the workflow is explicit and local. |
| Irreversible actions | 0 (none) | The skill only fixes and validates text files; it does not post, deploy, pay, book, or delete anything. |
| Transparency | 0 (none) | All shipped files are plain-text Markdown and Python; there are no binaries, installers, or decoded-at-runtime blobs. |
Before installing
- Read `SKILL.md` and both Python scripts; confirm you are comfortable with `~/.claude` being read during skill lookup.
- Test it on a throwaway export first and compare the `*-fixed.txt` output before using it on sensitive conversations.
- Run `uv run scripts/validate-claude-export-fix.py <original> <fixed>` on a sample file to confirm the checks behave as expected.
Rated 2026-10-19 by an automated review of 4 files from the skill's repository.
Source
- Repository
- daymade/claude-code-skills (all skills from this repository)
- Path
- daymade-claude-code/claude-export-txt-better/SKILL.md
- Branch
- main
- Updated
- 2026-09-20
Related skills
- E2E Testing Nori Skillsets Subcommands — Use when you need to interactively test a nori-skillsets CLI subcommand end-to-end via tmux, with full filesystem isolation
- srdf — MoveIt2 SRDF authoring, validation, and planning-semantics workflow.
- blast-radius — Find what a change could break somewhere else before it ships, beyond the diff.
- caveman-compress — Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.
- check-compiler-errors — Run compile and type-check commands and report failures
- control-cli — Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services.