OpenClaw Feishu Reasoning UX
v0.1.0Improve OpenClaw's Feishu reply experience by customizing streaming cards, raw reasoning visibility, card 2.0 layouts, collapsible panels, titles, colors, an...
⭐ 0· 134·0 current·0 all-time
by@doashoi
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (Feishu reply UX, card 2.0, raw reasoning visibility, collapsible panels, streaming) match the SKILL.md and reference docs. The skill is instruction-only and does not request unrelated binaries, environment variables, or credentials.
Instruction Scope
SKILL.md sensibly focuses on diagnosis-first steps (check runtime hooks, raw-stream.jsonl, session transcript, Feishu channel path) and prescribes phased, consented edits with backups. This is expected for a UX/runtime customization skill, but it does instruct the agent to read logs/session files and to guide edits to runtime/session code — actions that require file/system access and operator approval. The skill explicitly requires user consent and backup-before-change, which reduces concern.
Install Mechanism
No install spec, no downloads, and no code files executed by the platform — instruction-only skill. README suggests providing the repository URL to OpenClaw (normal for an operator-driven install).
Credentials
The skill requests no environment variables, credentials, or config paths. Although it directs checks of session files/logs and may direct edits to OpenClaw files, those are coherent with the stated debugging/customization purpose and do not demand extraneous secrets.
Persistence & Privilege
Flags are default (always:false, user-invocable:true, autonomous invocation allowed). The skill does not request permanent platform-level presence or modify other skills' configs and emphasizes asking user consent before restarts or persistent changes.
Assessment
This skill is internally consistent and designed as an operator-facing diagnostic/customization guide. Before using it, confirm you are on OpenClaw's built-in Feishu channel, and be prepared to grant the operator access to session logs and the OpenClaw file paths being edited. Follow the skill's backup-and-rollback steps exactly, prefer the low-risk phased rollout (card appearance first), and do not allow unattended automatic changes or service restarts without explicit consent. If you want an extra safety check, ask for a dry-run that only inspects logs/transcripts and reports findings without modifying files.Like a lobster shell, security has layers — review code before you run it.
feishuvk97dy9vwn5k4mx01str70j0gvh839qgflarkvk97dy9vwn5k4mx01str70j0gvh839qgflatestvk97fe4fqwhhcfp0yk95xd4qv8s83fzvtopenclawvk97dy9vwn5k4mx01str70j0gvh839qgfreasoningvk97dy9vwn5k4mx01str70j0gvh839qgfstreamingvk97dy9vwn5k4mx01str70j0gvh839qgfuxvk97dy9vwn5k4mx01str70j0gvh839qgf
License
MIT-0
Free to use, modify, and redistribute. No attribution required.