.claude/skills/chat-share-readerRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Export, backup, or archive AI chat conversations to markdown. Two inputs: public share links (ChatGPT, Claude, Gemini, Grok, Perplexity, DeepSeek, Kimi, Qwen, WorkBuddy, biji.com) and 15 local agent session stores (Claude Code, Codex, Cursor, opencode, Cline, Gemini CLI and more). Use when the user asks to save a shared conversation, export the chat they are in now (no args), search past sessions, filter by directory, batch export a site, read a compressed .jsonl.zst archive, or feed a session into another agent.…
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/chat-share-readerRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/chat-share-readerRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/chat-share-readerRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @mapleleo-hub/chat-share-readerclawhub inspect @mapleleo-hub/chat-share-reader --version 0.5.3This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
eval(eval(eval(eval(exec(exec(eval(eval(eval(eval(base64base64This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:c1b8b43088a9d55c503c6c023ff11082a8e6475a72bdd29c27d12687d7dfeca3package.jsonreferences/sessions.mdreferences/sites.mdscripts/biji-notes.mjsscripts/bulk.mjsscripts/lib/backend/cdp.mjsscripts/lib/backend/index.mjsscripts/lib/backend/opencli.mjsscripts/lib/config.mjsscripts/lib/dom-to-md.jsscripts/lib/http.mjsscripts/lib/i18n.mjsscripts/lib/local/claude.mjsscripts/lib/local/cline.mjsscripts/lib/local/codex.mjsscripts/lib/local/cursor.mjsscripts/lib/local/gemini-cli.mjsscripts/lib/local/hermes.mjsscripts/lib/local/jsonl-generic.mjsscripts/lib/local/opencode.mjsscripts/lib/local/pi.mjsscripts/lib/local/qwen.mjsscripts/lib/local/workbuddy.mjsscripts/lib/local/zcode.mjsscripts/lib/local/zst.mjsscripts/lib/md.mjsscripts/lib/merge.mjsscripts/lib/redact.mjsscripts/lib/vendor.mjsscripts/lib/which.mjsSecurity remediation for the ClawScan findings. Secrets (API keys, JWTs, bearer tokens, cloud credentials) are now masked at every redaction level except off; previously only strict did it while the description claimed default coverage. The uvx fallback pins convolvger==0.7.0 instead of resolving the newest release at call time. The DevTools channel no longer attaches to a Chrome debug port it did not start: it reuses only when port and profile match a marker it wrote itself. SKILL.md now declares BIJI_TOKEN and the override env vars, and states what the skill reads and never does.
Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.
These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.
sha256:0a98721330036ac5eb95e1eb177da4336721e0b96c7badfa6e97667a4d6e800csha256:51312c6bdba056722103d9823447acbd008e4bce6409f3a3f9fb2dd60654536e