General
retro - Claude MCP Skill
Implementation feedback capture. Appends effort accuracy, scope changes, and blockers to {repo}/.groom/retro.md. Read by /groom for planning. Invoked by /done and /pr, or manually via /retro append.
SEO Guide: Enhance your AI agent with the retro tool. This Model Context Protocol (MCP) server allows Claude Desktop and other LLMs to implementation feedback capture. appends effort accuracy, scope changes, and blockers to {repo}/.gro... Download and configure this skill to unlock new capabilities for your AI workflow.
Documentation
SKILL.md# /retro
Capture implementation feedback for future grooming sessions.
## Philosophy
When implementation reveals that an issue was underscoped, that signal should
persist. `/retro` captures these signals so `/groom` can adjust future scoping.
## Storage
```
{repo}/.groom/retro.md
```
Created automatically if missing. Appended to, never overwritten.
## Format
```markdown
# Implementation Retrospective
## Entry: #{issue} — {title} ({date})
**Effort:** predicted {predicted} → actual {actual}
**Scope changes:** {what changed from original issue}
**Blockers:** {what blocked progress}
**Pattern:** {reusable insight for future scoping}
---
```
## Subcommands
### `/retro append`
Interactive capture. Ask:
1. Which issue did you just finish? (issue number)
2. What was the predicted effort? (from effort label)
3. What was the actual effort?
4. Did scope change during implementation? How?
5. What blocked you?
6. What should future grooming sessions know?
Then append to `{repo}/.groom/retro.md`.
### Automated Append (from /done and /pr)
When invoked programmatically by `/done` or `/pr`, accept structured data:
```
/retro append --issue 42 --predicted m --actual l --scope "Added retry logic not in original spec" --blocker "Webhook signature verification undocumented" --pattern "Webhook issues always need retry logic"
```
Append without interactive prompts.
## How /groom Uses Retro
During Phase 1, `/groom` reads `retro.md` and extracts patterns:
- **Effort calibration:** "Payment issues consistently take 1.5x estimates"
- **Scope patterns:** "Webhook issues always need retry logic added during implementation"
- **Blocker patterns:** "External API docs are frequently wrong — always verify with web research"
- **Domain insights:** "Bitcoin wallet issues require manual testing on regtest"
These patterns inform:
- Effort estimates (adjust based on historical accuracy)
- Issue scoping (include commonly-missed concerns upfront)
- Boundary statements (prevent known scope creep patterns)
- Research priorities (investigate known problem areas proactively)
## Related
- `/done` — Appends retro signals after session retrospective
- `/pr` — Appends retro signals when opening PR
- `/groom` — Reads retro.md during Phase 1 (Context)Signals
Information
- Repository
- phrazzld/claude-config
- Author
- phrazzld
- Last Sync
- 3/2/2026
- Repo Updated
- 3/1/2026
- Created
- 2/23/2026
Reviews (0)
No reviews yet. Be the first to review this skill!
Related Skills
cursorrules
CrewAI Development Rules
firecrawl-build-onboarding
Get Firecrawl credentials and SDK setup into a project. Use when an application needs `FIRECRAWL_API_KEY`, when an agent should add Firecrawl to `.env`, when the user wants to authenticate Firecrawl for app code, or when choosing the first SDK and docs for a new Firecrawl integration. This skill includes its own browser auth flow, so it does not depend on the website onboarding skill.
firecrawl-build-search
Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should search the web and optionally hydrate result content.
firecrawl-build
Integrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser interaction. Use when building any feature that needs data from the web in code, even if the user does not mention Firecrawl explicitly and only describes wanting web data, website content, search, scraping, or interaction in an application. Trigger for Firecrawl requests, "fire girl" shorthand, and generic app-level web-data needs that should map to `/scrape`, `/search`, or `/interact`. Do not use this skill for one-off terminal-only web tasks during the current session; use `firecrawl/cli` for those.
Related Guides
Bear Notes Claude Skill: Your AI-Powered Note-Taking Assistant
Learn how to use the bear-notes Claude skill. Complete guide with installation instructions and examples.
OpenAI Whisper API Claude Skill: Complete Guide to AI-Powered Audio Transcription
Learn how to use the openai-whisper-api Claude skill. Complete guide with installation instructions and examples.
Mastering the Oracle CLI: A Complete Guide to the Claude Skill for Database Professionals
Learn how to use the oracle Claude skill. Complete guide with installation instructions and examples.