skills.rest
contexthub-md
contexthub-mdOFFICIAL
Explore all skills by this author →
GitHub

reflect

Captures post-run product feedback and process lessons into dated markdown reflection files.

Updated May 12, 2026
Search Tags:#feedback#markdown#retrospective#reflection#post-run#contexthub#process lessons
One-click install
npx skills add https://github.com/contexthub-md/marketplace --skill reflect-contexthub-md
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reflect
Source: https://github.com/contexthub-md/marketplace/tree/main/contexthub/skills/reflect
Command: npx skills add https://github.com/contexthub-md/marketplace --skill reflect-contexthub-md

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After a large mission, research run, or work session, valuable feedback about tool performance and lessons about how to work are easily lost. This Skill turns the end of a run into a structured reflection, separating product feedback on ContextHub/OCXP tools from process lessons, and persists it as a dated markdown file so feedback accumulates over time. ## Core Features & Use Cases - Structured Run Retrospective: Recalls the run's goal, difficulties, and tools used, then assesses each ContextHub/OCXP tool for usefulness, friction, and token cost. - Feedback vs. Lessons Separation: Distinguishes concrete, prioritized product improvements from process lessons about how to work, which are often the most valuable and easiest to lose. - Dated Feedback Archive: Writes a structured markdown file to contexthub-docs/feedback/<area>-<YYYY-MM-DD>-<topic>.md so reflections accumulate and never overwrite each other. - Use Case: After finishing an auth refactor mission, run the reflection to document which code intelligence tools helped, where they returned too much output, and what workflow lesson was learned, saved as a permanent dated record. ## Quick Start Ask the assistant to reflect on the work session just completed, for example by saying "reflect on the auth refactor mission", and it will produce a dated feedback file in contexthub-docs/feedback/.

Frequently Asked Questions about reflect

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

FAQPage Schema
How do I run a post-run reflection after a mission?▼

Invoke the reflect skill with a topic, such as "reflect memory research" or "reflect how did the auth refactor mission go". With no argument it reflects on the current session's work, then writes a dated markdown file to contexthub-docs/feedback/.

What does a reflection feedback file contain?▼

Each file includes context about the run, where tools were useful, where they created friction, a prioritized table of suggested improvements, and a verdict with the meta-lesson. Files are named by area, date, and topic so they accumulate without overwriting.

Do I need a connected project to write a reflection?▼

No prerequisites are required to write a reflection since it is just a markdown file. An active project connection can enrich the reflection with project context, but it is optional.

Where are reflection files stored?▼

Reflections are saved to contexthub-docs/feedback/ using the naming pattern <area>-<YYYY-MM-DD>-<topic>.md. The date is obtained from the time MCP server to ensure accurate dating.

Can reflections become searchable memory instead of files?▼

Currently reflections are file-based only. The skill notes a forward-looking hook where reflections would persist via ch_record_decision or a future ch_record_feedback tool, making them queryable memory injected into future runs.

Related Skills

Explore More Product & Management Skills→
Thanh-aperoThanh-apero
1

ck:journal

Generate structured journal entries from memories and recent code changes.

Community
Intermediate
IceWhaleTechIceWhaleTech
4

self_reflect

Extract actionable lessons from completed tasks and persist them to memory backends.

Official
Intermediate
mpazarynampazaryna
1

Weekly Summary

Generate weekly retrospective reports from daily notes, Clockify, project files, and GitHub metrics.

Community
Advanced
vellum-aivellum-ai
1.2k

memory-corpus-ingest

Ingest large document corpora into memory as compact map pages with cold-stored raw files.

Official
Advanced