MCP App StoreMCP App Store
from bkit-gemini59
Run prompts or shell commands on a recurring interval (seconds/minutes/hours) with safety limits and optional stop conditions — useful for monitoring and period
An interval-based runner that executes a prompt or shell command repeatedly according to a user-provided cadence (e.g., 5m, 1h, 30s). It captures per-iteration output, supports stop conditions, enforces safety limits (max iterations, min interval), and provides a summary when the loop finishes.
Use this skill for lightweight monitoring, polling external systems, periodic status checks, automated PDCA tasks, or scheduled data collection where a simple built-in loop is sufficient. Not intended for high-frequency production jobs.
Works with agents that can run shell commands and manage long-running operations (Gemini CLI integrations, local runners, Claude Code).
bkit-loop is a prompt-only skill (no bundled scripts) that instructs an agent to run commands on a recurring interval with configurable timing, safety limits (max 100 iterations, min 10s interval), and stop conditions. The SKILL.md is well-documented with multilingual triggers and clear usage examples, but lacks any implementation code — it relies entirely on the agent to interpret and execute the looping logic.
Pure prompt-template skill with no executable scripts. The shell command allowance is the main security surface, but the safety limits (max iterations, min interval, timeout) are thoughtfully designed. Multilingual trigger support is a nice touch.
Batch
Run PDCA workflow commands across multiple features in parallel or bulk, with progress tracking, fail-forward behavior, and retry options.
BTW (By-The-Way) Suggestion Collector
Capture lightweight improvement suggestions while you work and store them locally in .bkit/btw.json for later review, analysis, or promotion into PDCA planning.
PDCA (Plan-Do-Check-Act) Workflow
Manage Plan → Design → Do → Check → Act cycles: create plan/design docs, run gap analysis, iterate fixes, and generate completion reports.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
ds-fix — data-science mid-analysis fixer
Orchestrates diagnosis and targeted fixes mid-analysis: diagnose root cause, apply fixes with output-first verification, and update project learnings.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi
Feishu Voice Sender
Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.