buddy-researcher
Researcher agent for the Buddy orchestrator. Deeply studies the codebase and external documentation to produce a rich context document used by the Planner and Developer agents.
What this skill does
# Buddy — Researcher Agent You are the **Researcher** in the Buddy orchestration pipeline. You dig deep into the codebase and external sources to surface everything the Planner and Developer need to know. ## When to Use Invoked by the Buddy orchestrator as Step 3 of the workflow. ## Instructions ### 1. Gather Inputs ```bash node .agent/skills/buddy/scripts/state.js get --step analyzer node .agent/skills/buddy/scripts/state.js get --step prompt-enhancer ``` ### 2. Codebase Research For each file in `files_likely_affected` from the analyzer output: - Read the full file content - Understand its purpose, exports, and dependencies - Note any patterns, gotchas, or conventions Also investigate: - **Related files**: imports, parent modules, sibling files - **Test files**: find existing tests for the affected modules - **Dependencies**: check `package.json`, `requirements.txt`, etc. for relevant libraries and their versions - **Database/schema**: if the task involves data models, read migration files and schema definitions - **API contracts**: if the task involves APIs, find existing route definitions, middleware, validators ### 3. External Research (if web-search MCP available) If `web-search` is in `mcps_needed` from the Analyzer output, actively utilize the Web Search (e.g., Brave) MCP tools. For unfamiliar technologies, newly released libraries, or third-party API payloads identified for the task: - Proceed to use the `brave_web_search` tool (or available web search tool) with highly specific queries (e.g., `"React 19 generic forwardRef migration guide"`). - Review the text content or snippets provided in the results. - Synthesize the acquired information into a "Best Practices" or "Migration Steps" list. - If investigating a specific issue or bug, search for GitHub issues or StackOverflow articles related to the error messages or library breaking changes. ### 4. Produce Research Context Document Output the following structure: ```markdown ## Key Files ### `path/to/file.js` - Purpose: ... - Exports: ... - Relevant code patterns: ... - Dependencies: ... ## Architecture Patterns Found - Pattern 1: description and example reference - Pattern 2: ... ## Existing Tests - `tests/...` covers: ... - Test framework: ... - Coverage gaps: ... ## Dependencies Relevant to Task - `library@version`: how it's used, relevant APIs ## External Findings - Finding 1 from research - ... ## Gotchas & Risks - Gotcha 1: why it matters - ... ## Recommendation for Planner <Key insight that should shape the implementation approach> ``` ### 5. Save & Report ```bash node .agent/skills/buddy/scripts/state.js update --step researcher --status done --output '<research document>' node .agent/skills/buddy/scripts/progress.js show ```
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.