MCP App StoreMCP App Store
from prompts12
Search and recall past Claude Code/agent conversation sessions to find decisions, code snippets, and context for continuation or reference.
This skill provides conversation-history search and recall across two backends (Scribe DB and JSONL fallback) so an agent can find past discussions, decisions, code snippets, and session context. It ranks results by relevance and recency and offers scripts to present summaries or full session transcripts on demand.
Use when the user asks to remember, find, or continue work from a previous session (e.g., 'remember when we...', 'what did we do about...', 'find that conversation where...'). Also useful when the agent needs to surface prior decisions, commands, or code examples not present in the current session.
Designed for Claude Code / local agent tooling that can access Scribe DB or JSONL files; compatible with agent runtimes that can run Python scripts and access local filesystem.
Conversation recall skill for Claude Code sessions using Scribe DB (FTS5) with JSONL fallback. The single script (search.py) is well-structured with dual backends, argparse CLI, and recency-weighted ranking. Script failed in DRY_RUN due to missing required query argument — expected behavior, not a real bug. No security concerns; reads only local files with parameterized SQL.
Solid, useful skill for conversation recall. FTS query terms built from user input but passed via parameterized MATCH clause — minimal risk. Script exits with error code 2 when no query provided (expected argparse behavior). Dual-backend design (Scribe + JSONL) provides good resilience.
Hunter–Skeptic–Referee Code Review
Orchestrates a three-phase adversarial code review (Hunter, Skeptic, Referee) to find, challenge, and verify bugs with high precision and reduced bias.
Humanize
Revision and editing rules to remove AI-like patterns from prose so output reads more natural and human — applied automatically to any human-facing text before
Runtime Context
Detects which execution environment an agent is running in (Claude Code, Vercel Sandbox, or local dev) and exposes available tools and capabilities for safe, en
Retriever (Membrane CLI)
Integrate Retriever search and discovery via the Membrane CLI — manage connections and run queries across Retriever data sources.
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
ClawPod / Massive Unblocker
Bypass anti-bot restrictions and fetch rendered HTML or structured search results via Massive's Unblocker API (handles CAPTCHAs, JS rendering, geo-restrictions)
Retriever (Membrane) Integration
Integrate with Retriever via the Membrane CLI to search, query, and proxy Retriever data (documents, snippets, queries) with built-in auth and pagination.
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
Algolia Cost Tuning
Practical guide to reduce Algolia billing by auditing records/requests, switching to virtual replicas, multi-query usage, caching, and cleanup strategies.
Memory Search
Search past coding sessions and observations using natural-language queries to retrieve decisions, notes, and context.