templates/agent/skills/flow-memory-keeper/SKILL.md
Use at task, phase, flow, sync, archive, finish, revise, or failure checkpoints to keep Flow specs clean, capture learnings and failures, elevate durable patterns, and refine this skill with project-specific nuances
npx skillsauth add cofin/flow flow-memory-keeperInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This project-local skill prevents Flow work from drifting into stale specs, missing learnings, or half-archived folders.
Use it whenever work is completed, paused, blocked, revised, synced, or archived.
<workflow>Before claiming a task, phase, or flow is complete:
spec.md is readable and current through the normal Flow sync process.learnings.md..agents/patterns.md..agents/knowledge/ chapters when the current-state knowledge base changed..agents/workflow.md when they were discovered or corrected during the work..agents/specs/<flow_id>/learnings.md:
.agents/patterns.md..agents/knowledge/*.md chapter and .agents/workflow.md.spec.md reflects the latest state.Capture failure notes whenever one of these happened:
Failure notes belong in learnings.md, but keep them short and reusable. Focus on what future agents should avoid or check earlier.
When a flow is finished:
learnings.md is not missing critical discoveries..agents/archive/ according to the Flow archive workflow.This skill should improve over time.
When you discover a repeated project nuance, add or revise a short rule below instead of keeping the lesson only in session memory.
Only keep:
Do not keep:
Before claiming a task, phase, or flow is complete, verify:
spec.md was synced through the normal Flow processlearnings.md captures the durable lessons, failures, and recoveries.agents/patterns.md when appropriate.agents/knowledge/ reflects current-state knowledge when it changeddevelopment
Use when tracing execution paths, mapping dependencies, understanding unfamiliar code, following data flow, investigating end-to-end behavior, debugging call chains, or deciding which files to read next.
development
Use when reviewing authentication, authorization, user input, secrets, API keys, database queries, file uploads, session management, external API calls, OWASP risks, or data handling attack surface.
testing
Use when analyzing tradeoffs, comparing approaches, weighing options, assessing risks, stress-testing conclusions, identifying blind spots, or applying multiple viewpoints to a decision.
development
Use when reviewing hot paths, slow code, database queries, N+1 risks, memory usage, loops, I/O, caching strategy, concurrency, latency-sensitive paths, or resource efficiency.