Parse the task file and append session learnings under future-agent-notes.
npx skills add https://github.com/benredmond/apex --skill compound-benredmond
Please help me install this Agent Skill. Skill: compound Source: https://github.com/benredmond/apex/tree/main/skills/compound Command: npx skills add https://github.com/benredmond/apex --skill compound-benredmond
Capture learnings (problems, decisions, gotchas) from AI sessions to improve future agents by preserving context and insights for reuse.
Invoke the skill after completing a session, using a task identifier, for example: /apex:compound TASK-IDENTIFIER
High-intent search queries and answers about installing and using this skill.
To capture learnings from AI sessions, you parse the current task file and append detailed notes under a future-agent-notes section. This preserves problems, decisions, and gotchas to build a lasting knowledge base for future agents.
The best way to preserve architectural decisions is to scan existing task notes to surface related learnings and avoid duplication. Optionally, you can promote critical decisions to an AGENTS.md file for always-loaded context in future runs.
You need to write session notes to a task file after completing a debugging session, making an architectural decision, or finishing any significant problem-solving. This captures what happened, why decisions were made, and any surprises to guide future work.
Yes, AGENTS.md works with task files by providing always-loaded context for future AI agents. Critical learnings can be promoted from task files into AGENTS.md, while related tasks are linked back to ensure continuous knowledge retrieval.
Yes, you can avoid duplicating knowledge when appending future-agent-notes by scanning existing task notes first. The process surfaces related learnings already captured in the task file, ensuring new notes add distinct context without redundancy.
ulpi-ioExtracts session learnings and propagates them to central and agent-specific files.
davekilleenCapture and organize work learnings into categorized Markdown files.
pillipGuide structured problem-space exploration and ideation, saving notes to docs/brainstorm_notes.md.
microsoftAutomate continual learning for AI coding agents with global and local memory.
