MCP App StoreMCP App Store
from repo-task-proof-loop715
A repo-local workflow skill that creates auditable task folders and runs a spec-freeze → build → evidence → verify → fix loop with fresh-session verification.
Provides a repeatable, auditable workflow for implementing and verifying non-trivial coding tasks inside a repository. The skill initializes .agent/tasks/<TASK_ID>/, installs project-scoped subagent templates, and enforces a spec-freeze, build, evidence, fresh verification, and minimal-fix loop that produces machine-readable verdicts and problems files.
Use for feature implementations, refactors, migrations, or bug fixes where you need repo-local proof artifacts, reproducible verification, and minimal trusted changes. Triggers: requests to implement significant tasks, run verifiers, or produce evidence-backed PASS/FAIL verdicts.
Designed for Codex/Copilot-style coding agents and Claude Code where repo-local subagents or child sessions can be used. Also useful for CI-integrated verifiers and automation that can run Python scripts in the repo.
A repo-local workflow skill for auditable coding tasks with spec-freeze → build → evidence → verify → fix loops. Well-structured with comprehensive SKILL.md, references, and templates for both Codex and Claude Code subagents. Scripts failed in sandbox: task_loop.py requires a subcommand (init/validate/status), and verify_package.py expects to run from the skill root directory (it resolves SKILL.md relative to script location, which breaks in the temp execution dir). Code quality is strong with good validation, error handling, and path safety guards.
Impressive skill with thorough documentation, guardrails for task IDs (no path traversal), managed blocks for AGENTS.md/CLAUDE.md that preserve existing content, init sentinel for race condition protection, and comprehensive smoke tests. The verify_package.py is a self-test that validates the entire skill package structure — well thought out. Script execution failure is an artifact of sandbox path resolution, not a code defect.
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.