agentleFS
Sign inStart free
baberarjumandbaberarjumand/agentic_markdown_memory_agent-skill/.agents/skills/memory-reflect/SKILL.md

memory-reflect

Skill0 starsChanged 35 days agoMITView on GitHub

Turns a finished work session into durable markdown memory. Answers three questions (friction, missing repo fact, lesson to keep), filters out secrets and unconfirmed external content, routes each item to the right file, avoids duplicates, handles corrections, updates index lines, and clears the scratchpad. Use at the end of a non-trivial task or when asked to save what was learned.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. basicmachines-co/basic-memory★ 4.5ksame name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read references/practices.md and references/layout.md (generated copies of the init skill references).

    line 12
  2. Very specific:

    Search existing memory for the topic.

    line 20
  3. Very specific:

    If memory-audit is installed, run node <memory-audit>/scripts/audit.mjs --check and report the result.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Memory reflect

Requires a local filesystem. Otherwise stop and say so.

Read references/practices.md and references/layout.md (generated copies of the init skill references).

Procedure

  1. Gather candidates from SCRATCHPAD.md, HANDOFF.md, and the conversation.
  2. Answer the three reflection questions from block reflection in practices.md. Do not rewrite them.
  3. Filter using block write-rules and the trust rules: drop secrets, activity logs, derivable facts, and any item whose only origin is external content (or flag it for confirmation; never silently save).
  4. Route each survivor: friction or roadblock → memory/gotchas.md; topic detail → memory/<topic>.md; a choice → docs/decisions/; current belief → knowledge/.
  5. Search existing memory for the topic. Update in place, or supersede (set old file status: superseded and superseded_by, write the new file). Never leave two contradictory active entries.
  6. Show a table: target file, create / update / supersede, one-line content, origin. Wait for confirmation. Never write silently.
  7. Apply. Add or refresh frontmatter (updated = today). In the same change, update the matching index line, and add the decision record or a knowledge/log.md entry when the item is a decision.
  8. Clear SCRATCHPAD.md when the task is done. Fold into memory or delete HANDOFF.md if the next session no longer needs it.
  9. If memory-audit is installed, run node <memory-audit>/scripts/audit.mjs --check and report the result.

Running reflect twice on the same input must not create duplicate entries.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free