agent-integrator
Use this skill to create or update the root AGENTS.md file to register AgenticDev skills for AI agent discovery. Triggers include "register AgenticDev", "update AGENTS.md", "setup agent guide", or initializing a new project.
What this skill does
# Agent Integrator Skill ## Purpose Idempotently create or update the AGENTS.md file in a project to register AgenticDev skills for discovery by AI agents. This skill ensures that any compatible AI agent working in the repository can discover and use the AgenticDev methodology and available skills. ## When to Use Use this skill in the following situations: - After running project-init to initialize AgenticDev in a new project - When installing AgenticDev skills in an existing project - After adding new skills to the `.claude/skills/` directory - Updating the agent guide with new workflow information - Ensuring AI agents can discover available AgenticDev capabilities ## Prerequisites - Project has `.claude/skills/` directory with AgenticDev skills installed - Write permissions to project root directory - Optional: Existing AGENTS.md file (script creates if missing) ## AGENTS.md Purpose The AGENTS.md file serves as a discovery mechanism for AI agents: - **Agent Discovery**: AI agents read this file to learn about available workflows - **Methodology Documentation**: Explains AgenticDev philosophy and core principles - **Skill Catalog**: Lists all available skills and their purposes - **Getting Started**: Provides entry point for new agents working in the project ## Workflow ### Step 1: Determine If Update Is Needed Check if AGENTS.md needs to be created or updated: ```bash # Check if file exists ls -la AGENTS.md # Check if AgenticDev section exists grep "SYNTHESIS_FLOW" AGENTS.md ``` ### Step 2: Run the Helper Script Execute the script to update AGENTS.md: ```bash # Use default location (AGENTS.md in project root) bash scripts/update-agents-file.sh # Or specify custom location bash scripts/update-agents-file.sh -f path/to/custom-agents.md ``` ### Step 3: Understand What the Script Does The helper script uses an idempotent update strategy: 1. **Creates file if missing**: - Uses `touch` to ensure target file exists - Safe to run even if file doesn't exist yet 2. **Checks for existing content**: - Looks for `<!-- SYNTHESIS_FLOW_START -->` marker - Determines if this is an update or initial creation 3. **Updates existing content**: - If markers found, replaces content between markers - Preserves any other content in the file - Uses awk to safely replace marked section 4. **Adds new content**: - If markers not found, appends AgenticDev guide to end of file - Adds both start and end markers for future updates 5. **Preserves other content**: - Only modifies content between markers - Safe to run multiple times (idempotent) - Won't overwrite other project documentation ### Step 4: Verify the Update Check that AGENTS.md was updated correctly: ```bash # View the file cat AGENTS.md # Verify markers are present grep -A 5 "SYNTHESIS_FLOW_START" AGENTS.md ``` ### Step 5: Commit the Changes If the update looks correct, commit to the repository: ```bash git add AGENTS.md git commit -m "docs: Update AGENTS.md with AgenticDev guide" git push ``` ## Error Handling ### Permission Denied **Symptom**: Script cannot write to AGENTS.md **Solution**: - Check file permissions: `ls -la AGENTS.md` - Ensure you have write access to project root - Run with appropriate permissions ### Marker Corruption **Symptom**: Content between markers is malformed **Solution**: - Manually edit AGENTS.md to fix markers - Ensure both `<!-- SYNTHESIS_FLOW_START -->` and `<!-- SYNTHESIS_FLOW_END -->` are present - Re-run script to regenerate content ### Custom File Path Issues **Symptom**: Script creates file in wrong location **Solution**: - Use `-f` flag with full path: `bash scripts/update-agents-file.sh -f /full/path/to/file.md` - Verify path exists: `mkdir -p /path/to/directory` - Check current working directory ## Notes - **Idempotent design**: Safe to run multiple times without side effects - **Preserves other content**: Only updates content between markers - **Marker-based**: Uses HTML comments as markers (invisible in rendered markdown) - **Default location**: AGENTS.md in project root (standard convention) - **Custom locations**: Use `-f` flag for alternative file paths - **Run after setup**: Typically run once after project-init, then rarely - **Update when skills change**: Re-run if new skills are added or removed - **AI agent discovery**: Helps agents understand available AgenticDev capabilities - **Version control**: Commit AGENTS.md so all contributors see the guide
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.