MCP App StoreMCP App Store
from controlkeel8
Capture and consult durable proof bundles, typed memories, and workspace snapshots to preserve evidence and context when closing or resuming work.
The Proof & Memory skill provides a workflow for creating, reviewing, and preserving durable system-of-record artifacts — proof bundles, typed memory records, workspace snapshots, and resume packets. It's designed for situations where ephemeral session state is insufficient and you need recoverable evidence of decisions, tests, or deploy-readiness.
Activate before closing a session, when resuming prior work, or whenever the user requests 'remember this', 'save proof', or a checkpoint. Use it to compile proof_summary, run memory searches, materialize resume packets, and archive stale entries so future agents can recover context reliably. Ideal for regulated pipelines, code reviews that require audit trails, or governance workflows.
Targeted at agent platforms and toolchains that support MCP-style tooling and proof surfaces (ControlKeel integrations, OpenClaw/ck_mcp tools, codex/claude-integrations, and other agent runtimes that can call ck_context and ck_memory APIs).
Proof & Memory is a ControlKeel skill for capturing durable proof bundles, typed memories, and workspace snapshots to preserve context across sessions. No bundled scripts — it's purely instructional, directing agents to use ControlKeel's proprietary MCP tools (ck_context, ck_memory_search, ck_memory_record, ck_memory_archive, ck_observability). Well-structured SKILL.md with clear workflow steps, but entirely dependent on the ControlKeel platform to function.
Clean skill with no security concerns. Utility is narrow — only valuable within the ControlKeel ecosystem. Broad compatibility list in frontmatter (23 platforms) seems aspirational since the skill relies entirely on ControlKeel-specific MCP tools. No scripts to test.
AWP (Agent Work Protocol)
Tooling and scripts for onboarding, staking, allocation, and managing agents on the AWP network (Base/Ethereum/Arbitrum/BSC). Includes safe, opt-in daemon and r
Maestro Orchestrate
Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.
Run Execute
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
Caveman Compress
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
Ip2Location IO Automation (Composio)
Automate Ip2location IO tasks via Composio's Rube MCP toolkit — discover tools, verify connections, and execute schema-compliant workflows safely.
OpenTestAI
Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.
Canary — Post-Deploy Visual Monitor
Run a short post-deploy monitor that captures screenshots, checks console errors, and compares performance against baselines to detect regressions and page fail
Minimal Run & Audit (repro reporting)
Execute a README-first smoke test and produce standardized reproducibility outputs (`repro_outputs/`) and PATCHES.md — trusted reporting for repo reproduction r