Algis DumbrisandClaude Opus 4.6 e77fd7afdf spec(017): MuSiQue MAS benchmark harness ...

Feature spec for Python benchmark that integration-tests 016 marketplace
against a real multi-hop reasoning task. 4 prioritized user stories:
P1 single-shot Pareto verification, P2 curated trio with dedup,
P3 learning tier, P1 rich HTML report. 23 FRs, 7 success criteria.

Also: brainstorming design doc at docs/superpowers/specs/ capturing
the 6 clarifying questions and chosen decisions (mixed-tier pool,
curated trio, tiered run modes, wait-for-016 execution strategy).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-11 15:02:59 +03:00

..

001-production-readiness

feat: webhooks & Kubernetes Job runner for event-driven agents

2026-03-14 18:14:04 +02:00

002-mcp-auth-ux-polish

feat: OAuth 2.1 with PKCE, MCP auth, dead letters, channel management, and UX polish

2026-03-14 12:54:02 +02:00

003-webhooks-k8s-runner

feat: webhooks & Kubernetes Job runner for event-driven agents

2026-03-14 18:14:04 +02:00

004-embeddings-retention-inbox

fix: workflow UI only on enabled channels, add reaction picker, update protocol docs

2026-03-18 09:45:55 +02:00

005-hybrid-mcp-tools

plan: implementation plan for 005-hybrid-mcp-tools

2026-03-15 07:48:50 +02:00

006-admin-cli-docker-fixes

feat: admin CLI & Docker fixes — alpine base, channels create/join, absolute socket path

2026-03-15 14:54:13 +02:00

007-platform-features-bundle

plan: 007 platform features — research, data model, contracts, quickstart

2026-03-16 20:17:08 +02:00

008-webui-pwa-analytics

feat: v0.7.0 — analytics dashboard, PWA, UX fixes, MCP prompts

2026-03-17 10:36:58 +02:00

009-attachments-threads

feat: file attachments and thread visibility (009-attachments-threads)

2026-03-17 16:36:21 +02:00

010-reactions-workflows

feat: message reactions and workflow states (010-reactions-workflows)

2026-03-18 09:30:06 +02:00

011-trust-claims-triggers

feat: trust scores, claim semantics, state-change webhooks (011-trust-claims-triggers)

2026-03-18 21:41:54 +02:00

012-agent-onboarding

feat: agent onboarding — archetype selector, CLAUDE.md generator, skills library (012-agent-onboarding)

2026-03-20 09:57:49 +02:00

013-linkedin-approval-workflow

feat: MCP tool fixes + LinkedIn approval workflow (013)

2026-03-22 09:19:26 +02:00

014-reactive-agent-triggers

feat(014): add implementation plan, research, data model, and contracts

2026-03-25 17:23:48 +02:00

015-sql-query-split-pools

feat(015): add spec for SQL query interface + split connection pools

2026-03-26 07:04:55 +02:00

016-agent-marketplace

spec(016): agent marketplace spec + research reports

2026-04-11 14:59:51 +03:00

017-musique-benchmark

spec(017): MuSiQue MAS benchmark harness

2026-04-11 15:02:59 +03:00