agentleFS
Sign inStart free
IcodeNetIcodeNet/agent-skills/skills/memory-management/SKILL.md

memory-management

Skill0 starsChanged 4 months agoMITView on GitHub

Resolves project shorthand, acronyms, nicknames, and internal names using durable memory and docs. Use when the goal contains unexplained acronyms, nicknames, or team jargon that must be decoded before planning. Do not use for general research synthesis (use synthesize-research).

23 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use agent-agent, agent-analyze-code-quality and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 22 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Prefer written project sources over model prior knowledge for internal names.

    line 24
  2. Very specific:

    Do not invent expansions for unknown acronyms.

    line 25
  3. Distinctive:

    Keep memory entries short and factual.

    line 26

“Common” is measured: kept by at least 6 in 10 of the 22 edited versions of this file we could read. “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 Management

Decode shorthand so plans use the team's real names and constraints.

Workflow

  1. Extract terms — acronyms, nicknames, ticket IDs, service aliases from the goal.
  2. Resolve — check project memory notes, AGENTS.md / CLAUDE.md, domain glossaries (CONTEXT.md), ADRs, and recent docs. See references/resolution-order.md.
  3. Disambiguate — if a term maps to multiple meanings, state candidates and pick with evidence (or ask only if blocked).
  4. Normalize — rewrite the goal/plan using canonical names.
  5. Capture (optional) — if a stable new alias was confirmed, propose a one-line memory entry for the user to keep — do not invent long-lived memory without confirmation when project rules require it.

Constraints

  • Prefer written project sources over model prior knowledge for internal names.
  • Do not invent expansions for unknown acronyms; mark [UNKNOWN: term] and continue with unblocked work.
  • Keep memory entries short and factual.

Verification

  • All critical shorthand resolved or marked unknown
  • Plan uses canonical names
  • Sources cited for non-obvious expansions

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