Skip to content

Part of Run AI-Assisted Development Workflows End to End

Engineering Blueprint

Capture Learnings and Run Retrospectives

0June 2026

Persistent memory and process reflection that compounds across sessions.

What problem does this solve?

Captures what works and what doesn't so every session builds on the last. /retro runs a weekly engineering retrospective with shipping streaks, test health trends, and growth opportunities. /learn lets you manage what gstack learned (patterns, pitfalls, preferences) across sessions. Together they turn ad-hoc debugging into a knowledgebase that speeds up future work.

How does it work?

  1. Run /retro weekly to see what your team shipped, test health trends, and growth signals. 2. During work, use /learn to review, search, or prune project-specific patterns that gstack discovered. 3. On bugs or design decisions, gstack auto-logs learnings (confidence 1-10) for future sessions. 4. Learnings compound: next time you hit a similar bug, gstack suggests the pattern from the knowledgebase. Output: a retrospective report and an ever-growing project knowledge base that makes future work faster.

Included Skills

No skills in this group

What's required to run this?

Learnings persist in ~/.gstack/projects/{slug}/learnings.jsonl (JSONL format, one learning per line). Learning decay is time-based (updated on each query). Cross-project learnings require opt-in via gstack-config set cross_project_learnings true. Retro data comes from the project's git log, test output, and gstack timeline logs.

Key Features

/retro

Weekly engineering retrospective: shipping streaks, test health trends, per-person breakdowns, cross-project patterns, growth opportunities.

/learn

Manage project learnings: review what gstack discovered (patterns, pitfalls, preferences), search by keyword, prune stale entries, export.

Learning Decay

Learnings decay 5% per week automatically, so recent patterns stay hot while old patterns fade. Confidence scores help you trust or ignore a pattern.

Cross-Project Recall

Learnings from other projects on your machine can feed into new projects (opt-in). Similar bugs across repos become visible patterns.

About This Blueprint

Industry
Technology
1 File
Productivity

Business Automation & Productivity Workflow

Reduce hours lost to repetitive admin without adding a complicated stack. Prioritized, tested workflows automate routine research, client communication, project tracking, and website tasks while keeping people in control of important decisions.

1 File
Engineering

Business Technology & Digital Solutions Workflow

Avoid costly, fragmented digital projects with a plan that connects business goals to practical tools, implementation steps, and measurable results. It also flags performance, security, accessibility, and SEO checks before launch.

WordPressGoogle AnalyticsGoogle Search Console+2 more
Sales

ICP-Filtered Outreach Lists from G2 Buyer Intent

Stop wasting rep time on weak intent signals and mismatched accounts. The workflow ranks ICP-fit buyers by readiness, finds the right contact, and supplies tailored outreach angles for the strongest opportunities.

ClaudeClaudeG2 Buyer Intent (G2 MCP Server)ZoomInfo (MCP)+3 more

Ishani D.

Account Manager at G2