skills.rest
Fatih0234
Fatih0234COMMUNITY
Explore all skills by this author →
WebsiteGitHub

retro

Conducts a retrospective on a coding session to suggest agent environment improvements.

Updated Aug 27, 2026
Search Tags:#coding standards#retrospective#process improvement#session analysis#agents.md#coding agent#agent environment
One-click install
npx skills add https://github.com/Fatih0234/mattpocock-skills-pi --skill retro-fatih0234
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: retro
Source: https://github.com/Fatih0234/mattpocock-skills-pi/tree/main/skills/in-progress/retro
Command: npx skills add https://github.com/Fatih0234/mattpocock-skills-pi --skill retro-fatih0234

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After a coding session with an AI agent, it is hard to know why the agent struggled, made mistakes, or wasted tokens. This Skill reviews session logs and proposes concrete improvements to the agent's environment so future runs go better. ## Core Features & Use Cases - Session Analysis: Reads primary sources and session logs for a specified or current coding session to find friction points. - Categorized Improvement Candidates: Identifies issues across navigation, automated checks, coding standards, AGENTS.md bloat, tool economy, no-op instructions, and information access. - Prioritized Recommendations: Presents improvement candidates to the user ordered by severity. - Use Case: After an agent repeatedly failed to find the right config file during a long session, run a retrospective to add a navigation pointer to AGENTS.md and a lint check that would have caught the agent's error. ## Quick Start Ask the agent to run a retrospective on the current coding session and suggest improvements to its environment.

Frequently Asked Questions about retro

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a retrospective on an AI coding session?▼

Invoke the retro skill and optionally specify which session to review. It reads the session logs, identifies improvement candidates across categories like navigation and automated checks, and presents them ordered by severity.

What kinds of improvements does a coding session retrospective suggest?▼

It suggests navigation pointers for hard-to-find files, automated checks like linting and tests to catch agent mistakes, new or clarified coding standards for the reviewer agent, AGENTS.md cleanup, tool economy fixes, and better information access such as teed dev server logs.

Can I run a retrospective on a past session instead of the current one?▼

Yes. Specify the session you want reviewed and the skill will search through session logs on the machine for those primary sources. If you do not specify one, it defaults to the current session.

When should rules go in AGENTS.md versus CODING_STANDARDS.md?▼

AGENTS.md is pushed into every agent's context, so it should stay minimal, mostly navigation pointers. CODING_STANDARDS.md is read during review, not implementation, so enforcement rules belong there since the review agent has the least context pressure.

Why does the retrospective assign coding standards to the reviewer agent?▼

The implementation agent has the most context pressure from exploration, coding, and debugging, while the review agent only receives a diff. Assigning standards enforcement to the reviewer keeps the implementer's context lean.

Related Skills

Explore More Software Engineering Skills→
mt-krainskimt-krainski
1

retro

Analyzes Claude Code session transcripts to identify friction, successes, and rule adherence.

Community
Advanced
mattpocockmattpocock
242.8k

retro

Conducts a retrospective on a coding session to suggest agent environment improvements.

Community
Intermediate
bradoctechbradoctech
1

docs-write

Write and edit markdown and MDX documentation following Metabase style guidelines.

Official
Basic
HerxinsasaHerxinsasa
1

requesting-code-review

Dispatch a code-reviewer subagent to evaluate code changes with severity-categorized feedback.

Community
Intermediate