behavior
Manage AIWG behavior bundles that bind reactive directives and toolset configurations to specific agent types
What this skill does
# Behavior You manage AIWG behavior bundles — YAML artifacts that bind reactive directives and toolset configurations to specific agent types. Behaviors are the newest AIWG artifact type and are primarily deployed to OpenClaw (`~/.openclaw/behaviors/`). ## Triggers Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description): - "what behaviors are installed" → list subcommand - "show me the coding-strict behavior" → info subcommand - "apply strict mode to the software-implementer" → apply subcommand - "remove the no-internet behavior from my agent" → remove subcommand - "behavior bundles" → list subcommand ## Trigger Patterns Reference | Pattern | Example | Action | |---------|---------|--------| | List behaviors | "list behaviors" | Run `aiwg behavior list` | | Show detail | "show behavior coding-strict" | Run `aiwg behavior info coding-strict` | | Apply behavior | "apply coding-strict to software-implementer" | Run `aiwg behavior apply coding-strict --to software-implementer` | | Remove behavior | "remove coding-strict from software-implementer" | Run `aiwg behavior remove coding-strict --from software-implementer` | | Inspect source | "where are behaviors stored?" | Check `agentic/code/*/behaviors/` and `~/.openclaw/behaviors/` | ## Behavior When triggered: 1. **Extract intent**: - Which subcommand: `list`, `info`, `apply`, or `remove`? - Is a behavior name mentioned? - Is an agent type mentioned (for `apply`/`remove`)? 2. **Run the appropriate command**: ```bash # List all available behaviors aiwg behavior list # Show details for a specific behavior aiwg behavior info <name> # Apply a behavior to an agent type aiwg behavior apply <name> --to <agent-type> # Remove a behavior from an agent type aiwg behavior remove <name> --from <agent-type> ``` 3. **Understand behavior structure**: A behavior YAML bundle contains three sections: - `directives` — What the agent should always do or avoid in this operational context - `toolset` — Tool permissions and configuration overrides for this context - `inputs` — Variable parameters the behavior accepts at apply time 4. **Know the storage locations**: - **Source**: `agentic/code/*/behaviors/` (version-controlled, ships with framework) - **Deployed**: `~/.openclaw/behaviors/` (active, read by OpenClaw at runtime) - Deployment happens automatically during `aiwg use` for OpenClaw targets 5. **Report results** — For `list`, show name and description for each. For `info`, show the full bundle structure. For `apply`/`remove`, confirm the change. ## Examples ### Example 1: List available behaviors **User**: "What behaviors are available?" **Extraction**: List request, no filter **Action**: ```bash aiwg behavior list ``` **Response**: "3 behaviors available: - `coding-strict` — Enforce code review, no direct pushes, require tests before merge - `no-external-calls` — Block all outbound HTTP; toolset restricted to Read/Write/Edit/Bash(local) - `audit-mode` — Read-only directives, all writes logged to `.aiwg/audit/`, no destructive operations" --- ### Example 2: Inspect a specific behavior **User**: "Show me what coding-strict does" **Extraction**: Info request for `coding-strict` **Action**: ```bash aiwg behavior info coding-strict ``` **Response**: Shows the full YAML bundle — directives (require tests, no force push, enforce PR review), toolset (Read, Write, Edit, Bash with git restrictions), and any input variables. --- ### Example 3: Apply a behavior **User**: "Apply no-external-calls to the software-implementer agent" **Extraction**: Apply `no-external-calls` to `software-implementer` **Action**: ```bash aiwg behavior apply no-external-calls --to software-implementer ``` **Response**: "Applied `no-external-calls` to `software-implementer`. Deployed to `~/.openclaw/behaviors/software-implementer/no-external-calls.yaml`. Outbound HTTP is now blocked for that agent type." --- ### Example 4: Remove a behavior **User**: "Remove coding-strict from the test-engineer" **Extraction**: Remove `coding-strict` from `test-engineer` **Action**: ```bash aiwg behavior remove coding-strict --from test-engineer ``` **Response**: "Removed `coding-strict` from `test-engineer`. The behavior file has been deleted from `~/.openclaw/behaviors/test-engineer/`." ## Clarification Prompts If the user's intent is ambiguous: - "Which behavior would you like to inspect? (run `aiwg behavior list` to see all available)" - "Which agent type should this behavior be applied to?" - "Did you mean to `apply` this behavior or just view it with `info`?" ## References - @$AIWG_ROOT/src/cli/handlers/daemon.ts — Behavior command handler - @$AIWG_ROOT/docs/cli-reference.md — CLI reference - @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/agent-deployment.md — Agent deployment rule - @$AIWG_ROOT/docs/development/aiwg-development-guide.md — Source vs output boundary (behaviors are source artifacts in `agentic/code/*/behaviors/`)
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.