session-search
For CLI agents WITHOUT subagent support (e.g., Codex CLI). Search previous code agent sessions for specific work, decisions, or code patterns.
What this skill does
> **If you are Claude Code:** Do NOT use this skill directly. Use the > `session-searcher` subagent via the Task tool instead - it handles this more > efficiently without polluting your context. # session-search Search and find previous code agent sessions (Claude-Code or Codex-CLI) for specific work, decisions, or code patterns. ## Workflow 1. **Understand the query**: Identify what the user is looking for (code patterns, decisions, specific work, design direction) 2. **Search with aichat**: Run `aichat search --json -n 10 "[query]"` (use `-g "project"` to filter by project) 3. **Parse results**: Use `jq` to extract fields from JSONL output (session_id, project, created, snippet, file_path) 4. **Deep dive if needed**: Read session files at `~/.claude/projects/*/[session-id].jsonl` (max 3 files) 5. **Summarize**: Return a focused summary with key findings and references Run `aichat search --help` to see all options (date filters, branch filters, etc.) and JSONL field names. ## Output Format Return a concise summary containing: 1. **Key Findings**: 2-3 bullet points answering the query 2. **Relevant Sessions**: Session IDs and dates for reference 3. **Specific Content**: Code snippets or quotes if directly relevant Format as clean markdown, not raw JSON. ## Example Query: "Find sessions where we discussed authentication design" ```bash aichat search --json -n 10 "authentication design" ``` Summary: - **Session abc123** (Dec 10): Discussed JWT vs session-based auth, decided on JWT - **Session def456** (Dec 8): Implemented refresh token rotation pattern ## Constraints - ALWAYS use `--json` flag with aichat search (otherwise it spawns interactive UI) - NEVER return raw JSON output to the user - summarize and distill findings - NEVER read more than 3 session files per query - If no results found, suggest alternative search terms - ONLY report information directly observed in files - never infer or extrapolate ## Error Handling If `aichat search` command fails or is not found, ask user to install: ```bash uv tool install claude-code-tools # Python package cargo install aichat-search # Rust search TUI ``` Prerequisites: - Node.js 16+ (for action menus) - Rust/Cargo (for aichat-search) If user doesn't have uv or cargo: ```bash curl -LsSf https://astral.sh/uv/install.sh | sh # uv curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh # Rust ```
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.