CC chatgpt-exporter-ultimate
Export your ChatGPT conversations to local files — titles, timestamps and, if you ask for it, full message text. Built for the TinkerClaw fork — github.com/globalcaos/tinkerclaw. Invoke it BY NAME — "chatgpt-exporter-ultimate: export my conversations" — so ordinary talk about ChatGPT cannot trigger it. Rides the ChatGPT session your browser already holds — browser relay or a bookmarklet you paste yourself. It reads NO access token, no cookie jar and no credential file. The relay enumerates your conversation list and writes JSON and Markdown copies to a private directory; it defaults to index-only (titles and timestamps, no message text) and refuses to run without an explicit confirmation of destination and scope. The bookmarklet can also find conversations inside Projects, by running searches against your history, and downloads one JSON file after three dialogs. Relay destinations are resolved through symlinks before anything is written, so a relay export cannot land in a synced folder, a git repo or outside your home, and a symlink or hard link left inside a reused export directory is refused instead of written through. A validated --purge deletes an export again. Off switch documented in the skill.
Export your ChatGPT conversations to local files — titles, timestamps and, if you ask for it, full message text.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 3
✓ No critical or high findings
Medium and low: 3
-
low Risky intent
intent-offensive-securitySKILL.md:13Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)scope: "grep/sed/awk for parsing; realpath/readlink to canonicalize a destination or a purge target; and coreutils (date, du, head, rm). scripts/export.sh makes NO network calls at all — it neither fe
detector -
low Risky intent
intent-offensive-securitySKILL.md:68Offensive-security / dual-use content (legitimate for authorised testing; review intended use)NO privilege escalation, NO credential files read, NO third-party endpoints, NO telemetry.
-
low Risky intent
intent-offensive-securitySKILL.md:227Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Privilege escalation | **None.** No `sudo`. The relay writes only inside its output directory; the bookmarklet only hands one file to the browser's download | — |
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1219 chars, limit 1024
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 28 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4354 tokens
- 100Steps. 20 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (5 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1219: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (4 code blocks)
- +3All 6 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.