Kata has 106 completed plans across 15 milestones with rich structured data (deviations, timing, task counts, verification results) in SUMMARY.md and VERIFICATION.md files. Nobody is using this data. Questions like "why was v1.1.0 five times larger than v1.4.1?" and "which phase ordering produces fewer deviation corrections?" have answers extractable from existing artifacts.
Scanned 2/12/2026
Install via CLI
openskills install gannonh/kata-orchestrator---
created: 2026-02-05
title: Add kata-retrospective skill for milestone analysis
area: tooling
type: feature
provenance: github:gannonh/kata-orchestrator#98
---
## Problem
Kata has 106 completed plans across 15 milestones with rich structured data (deviations, timing, task counts, verification results) in SUMMARY.md and VERIFICATION.md files. Nobody is using this data. Questions like "why was v1.1.0 five times larger than v1.4.1?" and "which phase ordering produces fewer deviation corrections?" have answers extractable from existing artifacts.
## Solution
Create a `kata-retrospective` skill that reads all SUMMARY.md files from a completed milestone, extracts deviation patterns, timing data, plan sizing correlations, and verification outcomes, and generates a structured RETROSPECTIVE.md document.
### Scope
- Project-local output only (no cross-project infrastructure)
- Output uses standard Kata conventions (YAML frontmatter, markdown sections)
- Cross-project portability deferred until empirical data from multiple projects informs what generalizes
### Estimated Effort
1-2 plans (small milestone or quick task).
### First Step
Build the skill. Run it against Kata's own completed milestones. Evaluate whether the extracted patterns inform future planning.
### Source
Identified during explorer/challenger brainstorm session (radical ideas pair). Original proposal was a full cross-project learning system; descoped to project-local retrospective after challenge rounds.
No comments yet. Be the first to comment!
This skill helps you track, analyze, and report on keyword ranking positions over time. It monitors both traditional SERP rankings and AI/GEO visibility to provide comprehensive search performance insights.
Find and analyze YouTube competitor channels using YouTube Data API v3. Discover competitors through keyword search, category matching, content similarity, and related channel discovery. Compare metrics, content strategies, and market positioning. Use when users want to (1) Find competitors for their YouTube channel, (2) Analyze competitor performance metrics, (3) Compare their channel against competitors, (4) Identify content gaps and opportunities, (5) Benchmark against similar creators, (6...
Get current weather and forecasts (no API key required).
Focused Signals scout for PostHog projects using revenue analytics. Watches the derived revenue product for upstream failures (Stripe sync stalls, capture regressions), config drift (missing subscription property, currency mix surprises, broken Stripe↔person joins, deferred-revenue gaps), and goal-miss escalations. Emits findings only when they clear the confidence bar; otherwise writes durable memory and closes out empty. Self-contained peer in the signals-scout-* fleet — no dependencies on ...
Focused Signals scout for finding observability gaps in PostHog itself — significant event volumes the team isn't tracking, custom events with no insight or dashboard coverage, insights pointing at events that have stopped firing, dashboards missing related context, critical events with no alerts. Watches the event-stream-vs-saved- inventory delta as the team's product evolves and emits findings recommending new insights, dashboard additions, or alerts when gaps clear the confidence bar. Self...