feishu-cli-manager
Use when the user asks to install Feishu/Lark CLI, configure lark-cli, connect an agent with Feishu CLI, check or refresh lark-cli auth, recover expired tokens, or start a Feishu device-flow login.
What this skill does
# Feishu CLI Manager Use this skill to install, configure, and maintain local `lark-cli` for agent workflows. ## Core Rules - Never print app secrets, access tokens, refresh tokens, cookies, or credential files. - Treat `which lark-cli`, `lark-cli --version`, and `npm list -g --depth=0` as installation evidence. - Treat `lark-cli auth status` as the first source of truth for local auth state. - Use `lark-cli auth status --verify` only when network verification is needed. - User auth and bot auth are different. Do not run `auth login` for bot-only permission issues. - `lark-cli auth login` must request an explicit range with `--domain`, `--scope`, or `--recommend`. - When command output contains a verification URL, copy that URL exactly as returned. Do not rewrite or re-encode it. - Do not run `lark-cli config bind`, `lark-cli config init --new`, or `lark-cli config init --force-init` unless the user confirms the intended app/config identity. ## Install Check Prefer the bundled helper when available from this skill directory: ```bash python3 scripts/feishu_cli_setup.py --check ``` Manual checks: ```bash node --version npm --version which lark-cli lark-cli --version ``` `lark-cli` is normally installed as the global npm package `@larksuite/cli`. ## Install Or Update Install only when `lark-cli` is missing: ```bash python3 scripts/feishu_cli_setup.py --install ``` Equivalent direct command: ```bash npm install -g @larksuite/cli ``` Update an existing install: ```bash lark-cli update ``` Use `lark-cli update --check --json` when only checking update availability. ## Configure If `lark-cli` is installed but not configured, inspect before changing anything: ```bash lark-cli auth status lark-cli config init --help lark-cli config bind --help ``` Inside an agent workspace, prefer `lark-cli config bind` only after the user confirms the target app and identity mode. Use `bot-only` unless the task needs personal resources; use `user-default` only when the user explicitly needs user-resource access. For a brand-new standalone app setup, and only after the user confirms that intent: ```bash lark-cli config init --new ``` ## Auth Check Run: ```bash lark-cli auth status ``` Use server verification only when needed: ```bash lark-cli auth status --verify ``` If an environment reports `keychain not initialized`, first suspect that the current process cannot access the local keychain. Re-run the check in an environment with normal keychain access before assuming the Feishu account or token is broken. ## Refresh Or Reconnect If the token is expired, missing, revoked, or too close to expiry, start a scoped login: ```bash lark-cli auth login --domain all --scope offline_access ``` Use narrower domains or scopes when the task is limited: ```bash lark-cli auth login --domain docs --domain drive lark-cli auth login --scope "docs:document.content:read drive:file:download offline_access" ``` The bundled helper can summarize expiry and decide whether login is needed, but it must run with the same keychain access as `lark-cli`: ```bash python3 scripts/feishu_auth_refresh.py --login-if-needed --domain all --scope offline_access ``` ## Agent Workflow 1. Check whether `lark-cli` is installed. 2. If missing, install `@larksuite/cli` with npm after confirming Node/npm are available. 3. If installed but not configured, decide between binding an existing agent app and creating a new app; do not guess this choice. 4. Check auth state with `lark-cli auth status`. 5. If `tokenStatus` is valid and `refreshExpiresAt` is not close, report that no reconnect is needed. 6. If access token expiry is close but refresh token is still valid, run `lark-cli auth status --verify` once and re-check. 7. If refresh token is expired, missing, or revoked, start `lark-cli auth login` with the smallest explicit domain/scope that fits the task. 8. If a device-flow URL is returned, present it exactly and wait for the user to authorize. 9. Verify completion with `lark-cli auth status --verify`.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.