Analysis Retrospective
Runs a short retro after a project so the same mistake, or the same win, doesn't get rediscovered from scratch next time.
Overview
Analysis Retrospective runs within a week of finishing a significant analysis project, while the details are still fresh, or right after one that went wrong, to keep the same failure from happening again.
What it covers
- Time-boxes the retro (30 minutes solo, 60 minutes for a team) using a structured format like Start/Stop/Continue or the 4Ls.
- Compares the actual timeline, scope, and effort against what was planned, and notes the gaps.
- Captures at least two things that went well, since those matter as much as the problems.
- Applies 5-whys to each issue to find the real cause instead of the symptom.
- Captures reusable learning into templates, reference docs, or team norms, and logs action items with owners and due dates.
Part of Data Analytics Skills
This is one of 31 skills in the Data Analytics Skills library, in the Workflow Optimization group.
Installation
- Clone the repo once:
git clone https://github.com/nimrodfisher/data-analytics-skills.git - Copy just this skill:
cp -r data-analytics-skills/06-workflow-optimization/analysis-retrospective ~/.claude/skills/(or~/.agents/skills/for Codex) - Ask your agent something like "run a retro on the analysis project we just wrapped up" and it activates on its own.
See the Data Analytics Skills entry for the full library.
Related assets
Frontend Design
Generates distinctive, production-grade UI that avoids generic "AI slop," with bold typography, cohesive color, and precise motion, implemented as real code.
Graphify
Turns a codebase, plus its docs, PDFs, images, and video, into a queryable knowledge graph that a coding agent can traverse instead of grepping raw files, and never guesses silently: every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS so you know what was found versus inferred.
Caveman
Makes your coding agent answer in a stripped down, high signal style that keeps every technical fact and cuts filler, saving output tokens on chat style questions.