week-retro

Analyzes weekly agent sessions to promote or reject reusable workflow rules.

1|Updated Feb 2, 2026
One-click install
npx skills add https://github.com/rockcookies/skills --skill week-retro-rockcookies
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: week-retro
Source: https://github.com/rockcookies/skills/tree/main/skills/custom/week-retro
Command: npx skills add https://github.com/rockcookies/skills --skill week-retro-rockcookies

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Weekly agent work produces scattered sessions and plans, making it hard to tell which workflow habits actually helped, which frictions keep recurring, and which lessons deserve to become durable rules versus one-off incidents. ## Core Features & Use Cases - Evidence-graded learning loop: Runs an Evidence → Friction/Success → Root Cause → Candidate → Promote/Reject → Eval pipeline with E0–E4 evidence grading so only repeated, costly patterns become rules. - Skill routing and context hygiene audit: Separates Skill Selection failures from Execution failures and checks context pollution, session boundaries, and verification gaps. - Promotion discipline: Distinguishes cross-project reusable constraints from project-specific exceptions, and never edits global files like AGENTS.md or CLAUDE.md without explicit approval. - Use Case: After a week of AI-assisted development, run a retrospective that reconstructs 1–3 workstreams, lists top frictions with root causes, proposes 2 promotable workflow constraints with triggers and scope, and defines next-week verification hypotheses. ## Quick Start Run a week retrospective over my sessions and plans from the last 7 days and report frictions, root causes, and candidate workflow rules.

Frequently Asked Questions about week-retro

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

FAQPage Schema
How do I run a weekly retrospective on my AI agent workflow?▼

Invoke the week-retro skill and it collects evidence from the last 7 days of sessions and plan files, reconstructs workstreams, grades friction by evidence level, and outputs promoted rules plus next-week verification hypotheses.

How to decide which workflow lessons should become permanent rules?▼

Each candidate must pass an Observation → Pattern → Root Cause → Candidate chain with evidence grade E2 or higher, a repeated pattern, cross-project reusability, and a clear trigger. One-off incidents and project-specific details are rejected and kept as local documentation.

Does week-retro automatically edit my AGENTS.md or global config files?▼

No. The skill only reports and recommends; it never modifies AGENTS.md, CLAUDE.md, global rules, or skills unless you explicitly authorize a specific change in the current session.

What is the difference between skill selection and execution problems?▼

Selection problems mean the wrong skill was triggered or the right one was missed, fixed via descriptions and trigger words. Execution problems mean the correct skill ran poorly, fixed via instructions. The audit records these two failure types separately.

When should I not use a weekly workflow retrospective?▼

Do not use it as a weekly diary of completed tasks or for live incident troubleshooting, which should route to a dedicated debugging skill. It also skips community-trend-driven suggestions that lack local evidence.