AF read-claude-web-conversation
Read or export the COMPLETE transcript of a Claude.ai web conversation — both private claude.ai/chat/... and public claude.ai/share/... links — by calling Claude.ai's internal API from inside the user's logged-in Chrome, and download its FILES too (uploads, deliverables). Use whenever the user pastes a claude.ai conversation or share link and asks to read, summarize, export, archive, or extract it — "read this Claude conversation", "导出这个网页版对话", "把这个对话拉到本地". Every naive approach fails SILENTLY: curl/WebFetch hit a Cloudflare challenge; get_page_text sees only the last message; the default API rendering collapses tool calls into placeholders (~5% of it); a share payload uses block shapes a /chat/-only renderer drops without error. Works even when the claude-in-chrome extension cannot pair (different account), via CDP or a macOS AppleScript fallback. Scope: ONLINE claude.ai. For LOCAL Claude Code sessions use read-claude-code-history; for an exported .txt/.json file use claude-export-txt-better.
Read or export the COMPLETE transcript of a Claude.ai web conversation — both private claude.ai/chat/... and public claude.ai/share/... links — by calling…
As a process F 55/100 · Will not run — References files that are not bundled: scripts/runjs.applescript
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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 · 0
✓ No critical or high findings
Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6252 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/runjs.applescript
Process rating: all ten parameters 55/100
- 0Tools and files. 1 referenced file(s) missing: scripts/runjs.applescript
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 6252 tokens
- 85Steps. 17 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (9 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1007: 120–800 characters recommended
- -31 of 7 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Structure: 14 headings
- +3Step-by-step instructions: 17 items
- +3Output format is stated explicitly
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.