agentleFS
cyhhaocyhhao/vibe-remote/skills/use-avibe/SKILL.md

use-avibe

Skill638 starsChanged 7 days agoMITView on GitHub

Safely inspect and modify local Avibe configuration, routing, runtime settings, watches, scheduled tasks, Avibe Cloud remote access, and operational state. Also use it to report an Avibe bug, send product feedback, or file a feature request from the current conversation.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 1

    1. avibe-bot/avibe★ 63899% same

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

Show its rules and text

We split this skill into the rules it gives an agent

32 rules. About 0 are common, 19 are distinctive, and 13 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈19

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 13

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user asks you to configure, repair, explain, or operate a local Avibe installation.

    line 10
  2. Very specific:

    create, update, inspect, pause, resume, or remove a managed background watch with vibe watch

    line 21
  3. Very specific:

    create, inspect, run, pause, resume, or remove a scheduled task with vibe task

    line 22
  4. Very specific:

    run a one-shot Agent job with vibe agent run, including async background runs

    line 23
  5. Very specific:

    check or apply Avibe updates (vibe check-update, vibe upgrade)

    line 25
  6. Distinctive:

    Follow this skill as an operations playbook for agents, not as end-user marketing copy.

    line 30
  7. Distinctive:

    Prefer the Web UI API for Avibe configuration changes.

    line 34
  8. Distinctive:

    Read current API state before mutating.

    line 35
  9. Distinctive:

    Treat secrets as opaque. Do not print, invent, rotate, or overwrite tokens unless the user explicitly provides replacements.

    line 37
  10. Distinctive:

    Use the smallest viable API call and verify by reading back the API response.

    line 38
  11. Very specific:

    Do not restart the service by default.

    line 43
  12. Distinctive:

    Only start, stop, restart, or reload Avibe when the user explicitly asks or when a change cannot take effect otherwise.

    line 44
  13. Very specific:

    If an agent must restart Avibe from an active conversation, use vibe restart --delay-seconds 60 so the current session can receive the …

    line 45
  14. Distinctive:

    Use this order when changing Avibe configuration:

    line 50
  15. Very specific:

    If the user has a custom UI host or port (from ui.setup_host / ui.setup_port), use that exact origin.

    line 54
  16. Very specific:

    When Avibe Cloud remote access is active, the public origin (e.g.

    line 55
  17. Very specific:

    Check liveness with GET /health or GET /status.

    line 56
  18. Distinctive:

    Read back the changed resource and verify the effective payload.

    line 66
  19. Very specific:

    Run POST /api/doctor only when the change affects runtime health, platform credentials, or backend availability.

    line 67
  20. Very specific:

    Read only the reference needed for the current task, before composing its calls.

    line 72
  21. Distinctive:

    Always follow these constraints:

    line 92
  22. Distinctive:

    never delete unrelated platform scopes

    line 94
  23. Distinctive:

    never blank out tokens or secrets as part of an unrelated config task

    line 95
  24. Distinctive:

    never claim a backend feature exists if current Avibe behavior does not support it

    line 96
  25. Very specific:

    never read, query, or hand-edit Avibe's internal state storage — go through the Web UI API or vibe CLI

    line 97
  26. Distinctive:

    never expose bind codes, pairing keys, tunnel tokens, instance secrets, or session secrets unless the user explicitly asks

    line 98
  27. Very specific:

    never paste a credentialed proxy_url (user:pass@host) back into chat — mask the credentials portion when echoing the value

    line 99
  28. Distinctive:

    always say when a requested change actually belongs in OpenCode, Claude Code, or Codex config instead of Avibe

    line 100
  29. Distinctive:

    never splice a generated or user-supplied value into a shell command string.

    line 102
  30. Distinctive:

    When the user has approved the sanitized content and public consent, use the official route in the feedback reference when commissioning …

    line 115
  31. Distinctive:

    If the user wants to contribute back with code, suggest a pull request in that repository.

    line 127
  32. Distinctive:

    When you complete an Avibe maintenance task, report back with:

    line 131

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Use Avibe

Use this skill when the user asks you to configure, repair, explain, or operate a local Avibe installation.

Typical requests include:

  • enable a Slack, Discord, Telegram, Lark/Feishu, or WeChat scope
  • route one channel or DM user to OpenCode, Claude, or Codex
  • set a working directory for a channel or DM user
  • choose a backend model, subagent, or reasoning level
  • show or hide intermediate message types
  • configure an outbound proxy (proxy_url) for an IM platform that cannot reach its API directly
  • pair, start, stop, or inspect Avibe Cloud remote Web UI access
  • create, update, inspect, pause, resume, or remove a managed background watch with vibe watch
  • create, inspect, run, pause, resume, or remove a scheduled task with vibe task
  • run a one-shot Agent job with vibe agent run, including async background runs
  • inspect or cancel concrete Agent Run records with vibe runs
  • check or apply Avibe updates (vibe check-update, vibe upgrade)
  • inspect logs, run doctor, check service status, or explain where Avibe stores state
  • decide whether a requested change belongs in Avibe config or in the host backend's own config
  • report an Avibe bug, send product feedback, or file a feature request from the current conversation ("report this to Avibe", "submit a bug", "request a feature")

Follow this skill as an operations playbook for agents, not as end-user marketing copy.

Core Rules

  1. Prefer the Web UI API for Avibe configuration changes. Do not hand-edit config files for routine work.
  2. Read current API state before mutating. Merge the user's requested change into the current payload.
  3. Preserve unrelated scopes, platforms, users, and secrets.
  4. Treat secrets as opaque. Do not print, invent, rotate, or overwrite tokens unless the user explicitly provides replacements.
  5. Use the smallest viable API call and verify by reading back the API response.
  6. Change one channel, topic, or DM user with PATCH /api/settings/scope, which writes only the named fields; POST /api/settings replaces the platform's whole channel map.
  7. Change a bound DM user's fields with PATCH /api/settings/scope ("scope": "user"); POST /api/users writes each included user as a whole row.
  8. Make every persistent-state change through the Web UI API or the vibe CLI. Avibe's internal storage is opaque — do not read, query, or hand-edit it.
  9. POST /api/config persists the new payload but does not restart running platform adapters by itself. When the change is platform credentials, proxy_url, or other transport-level settings, plan an explicit restart afterwards; prefer the delayed CLI form (vibe restart --delay-seconds 60) when triggering it from inside an active conversation. The only credential save that restarts on its own is the WeChat QR-login completion through POST /api/wechat/qr_login/poll.
  10. Do not restart the service by default. Use POST /api/doctor, GET /status, and read-back checks first.
  11. Only start, stop, restart, or reload Avibe when the user explicitly asks or when a change cannot take effect otherwise; explain why before doing it.
  12. If an agent must restart Avibe from an active conversation, use vibe restart --delay-seconds 60 so the current session can receive the reply before the restart lands.
  13. Tell the user whether the change is global or scope-specific.

API First Workflow

Use this order when changing Avibe configuration:

  1. Determine the Web UI base URL.
    • Default is http://127.0.0.1:5123.
    • If the user has a custom UI host or port (from ui.setup_host / ui.setup_port), use that exact origin.
    • When Avibe Cloud remote access is active, the public origin (e.g. https://<slug>.avibe.bot) also speaks the same API and requires OIDC session cookies — prefer the local origin from the host running Avibe.
    • Check liveness with GET /health or GET /status.
  2. Decide whether the request belongs in:
    • POST /api/config for global defaults, platform credentials, runtime config, agent defaults, UI config, remote-access provider settings, update policy, or global display toggles
    • PATCH /api/settings/scope for one channel's, topic's, or DM user's routing, working directory, visibility, enablement, and mention policy
    • /api/users and /api/bind-codes for DM user binding and user-scope settings
    • /api/remote-access/* for Avibe Cloud pairing and tunnel control
    • host backend config instead of Avibe when the request is OpenCode, Claude Code, or Codex native behavior
  3. Fetch the current state from the matching GET endpoint.
  4. Merge the requested change in memory.
  5. Send the mutating request through the Web UI API with CSRF protection.
  6. Read back the changed resource and verify the effective payload.
  7. Run POST /api/doctor only when the change affects runtime health, platform credentials, or backend availability.
  8. Report the changed scope or global keys and whether a restart was avoided or still required.

Task References

Read only the reference needed for the current task, before composing its calls. Paths below are relative to this Skill directory; scripts remain under scripts/, not under references/.

TaskReference
Send API requests with CSRF, cookies, JSON payloads, or the bundled helperAPI client
Change global defaults, platform credentials, proxies, or discover IM channelsGlobal configuration and platforms
Change channel/DM routing, models, cwd, visibility, mention policy, or bind usersScopes and routing
Pair, inspect, repair, or control the Avibe Cloud tunnelRemote access
Run or delegate Agent work, schedule tasks, manage watches or Session queuesLoad the use-avibe-harness Skill
Choose backend/subagent settings or change native OpenCode, Claude, or Codex configBackends
Inspect runtime paths, logs, or health; restart or upgrade the serviceOperations and troubleshooting
Turn a problem or a wish in this conversation into a bug report, feedback, or feature requestFeedback and feature requests

For multi-step API work, use the bundled scripts/vibe_api.py helper. The API client reference contains its exact invocations and fetch/merge examples.

Safety Boundaries

Always follow these constraints:

  • never delete unrelated platform scopes
  • never blank out tokens or secrets as part of an unrelated config task
  • never claim a backend feature exists if current Avibe behavior does not support it
  • never read, query, or hand-edit Avibe's internal state storage — go through the Web UI API or vibe CLI
  • never expose bind codes, pairing keys, tunnel tokens, instance secrets, or session secrets unless the user explicitly asks
  • never paste a credentialed proxy_url (user:pass@host) back into chat — mask the credentials portion when echoing the value
  • always say when a requested change actually belongs in OpenCode, Claude Code, or Codex config instead of Avibe
  • never publish anything derived from this conversation until that exact content, destination, and posting identity are authorized — a destination is a host, a repository, and an acting account, never whatever the environment happens to supply; sanitize first, and keep the authorization to one concrete yes rather than a prompt per step; ordinary reads and generic public searches are already covered by the task
  • never splice a generated or user-supplied value into a shell command string; pass it as its own argument

Escalation

Some requests are not local maintenance at all. Switch to the feedback workflow in Feedback and feature requests when:

  • the behavior looks like a real bug rather than a local misconfiguration
  • the user is asking for a feature Avibe does not support yet
  • backend integration behavior appears inconsistent with the documented configuration surface
  • the user simply asks to report something or request a change, with or without prior diagnosis

That reference owns the whole path: gathering facts from this conversation, drafting a short English report, sanitizing it, getting approval, and submitting it to https://github.com/avibe-bot/avibe through an already authorized channel. Do not stop at "open an issue yourself", and do not treat diagnosis, a restart, or a repair as a precondition for filing.

When the user has approved the sanitized content and public consent, use the official route in the feedback reference when commissioning has marked it available. Its packaged scripts/feedback_intake.py helper is distributed inside this existing Skill by the normal wheel skills/ inclusion and built-in snapshot publication path. A development checkout or a deployed receiver alone does not update a client's installed Skill. The helper is bound to the operator's HTTPS Show share and cs-agent-bot posting identity; it creates one UUIDv4, persists the exact payload in its local outbox, and reads the separate public receipt before claiming an Issue URL. resume <request_id> only reads receipts; explicit delivery recovery requires saved POST429 evidence and a fresh minimal404.

If the user wants to contribute back with code, suggest a pull request in that repository.

Response Pattern

When you complete an Avibe maintenance task, report back with:

  1. which API endpoint changed the state
  2. whether the change is global or scope-specific
  3. which keys changed
  4. the read-back or doctor evidence
  5. whether a restart was avoided, deferred, or still required and why

A feedback or feature-request task reports something different: the verified issue URL, or the finished draft plus an explicit statement that it was not submitted.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.