Shape rough requests into evidence-backed /goal completion contracts — an Agent Skill for Claude Code and Codex

Give text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解插件（场景感知抽帧 + VLM + 可选语音转录）

Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files c

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with command, config, seed, log, checkpoint, status, and metric evidence written to st

Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning

AI made building cheap. It didn't make deciding cheap. Mycelium is a Claude Code harness that makes your agent run discovery and weigh evidence before it writes code. It earns the right to start. Built for software, courses, AI tools, and services.

Agentic Version Control System — an AI-native VCS where intent, session, operation, evidence and decision are first-class objects and code is a materialized projection of an operation graph.

Evidence-first reading for AI agents — turn articles, books and PDFs into traceable claims, evidence, source locations and knowledge maps.

Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.

A minimal, evidence-gated harness for Codex and Claude Code: reuse what works, add only what is missing, verify before evolving.

Local history ingestion, storage, evidence, SDK, CLI and MCP server.

AI agent 通用任务治理框架：对齐目标与事实，规划和调度能力，守住授权与风险边界，治理任务执行到真实验收与交付。Governance framework for evidence-driven planning, orchestration, and verified delivery.

How often ChatGPT, Claude, Gemini and Perplexity name and cite your brand, with the evidence.

CertScore website risk-signal tools for scans, findings, evidence, and latest-domain lookups.

Audit AI applications and agents for security risks before commit, PR, merge, or deployment. Deterministic findings with coverage and evidence receipts.

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

Project memory and workflows for Claude Code and Codex. Keep stories, plans, handovers, and review evidence in your repo. Resume across sessions and follow progress in the Mac app.

Контроль качества 1С-разработки для Claude Code: стандарты, принципы ООП и паттерны, XML метаданных, блокирующие гейты и проверяемый след прогона · Claude Code plugin for 1C:Enterprise (BSL) code quality: development standards, SOLID and design patterns, metadata XML, blocking session gates and a machine-readable evidence trail.

Multi-language repository map for agents and humans: MCP tools, dependency graphs, symbol indexes, impact review, and bounded source evidence.

Merge autonomy for AI-authored code. Turn your repo's standards into evidence-backed readiness reports the agent reads back.

Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.

【EMNLP 2026 Demo】A debugging framework for agentic AI systems: diagnose failures, attribute root causes, recover with evidence, and validate fixes through reruns.

蒸留蔵 — distilled long-term memory for agents: recall by meaning, writing gated by evidence, one kura per agent mode. Ships as a DeepSeek Harness plugin and an MCP server.