agentleFS
roronoazoroshao369roronoazoroshao369/vibe-coding-os/skills/memory/project-memory/SKILL.md

project-memory

Skill1 starsChanged 5 months agoMITView on GitHub

Maintain durable project context that future sessions can trust. Use when decisions, conventions, commands, or architecture facts should persist. Decision, context, source, date, confidence, sensitivity level. A concise memory entry with source, confidence, and safety status. Related skills: skills/core/architecture-decision-records/SKILL.md, skills/core/grill-user-before-building/SKILL.md (Phase 2 docs-aware), CONTEXT.md Applied from Supermemory-inspired design: durable memory should be scoped, searchable, source-aware, privacy-filtered, and useful for later retrieval. Not applied: hosted Supermemory service requirement, SDK client, cloud auth, dashboard, connector stack, database infrastructure, or storing full transcripts…

26 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when decisions, conventions, commands, or architecture facts should persist.

    line 20

“Common” is measured: kept by at least 6 in 10 of the 21 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

Skill: Project Memory

Purpose

Maintain durable project context that future sessions can trust.

When to use

Use when decisions, conventions, commands, or architecture facts should persist.

Inputs

Decision, context, source, date, confidence, sensitivity level.

Workflow

  1. Capture only durable information.
  2. Separate facts from assumptions.
  3. Record why the decision matters.
  4. Redact sensitive details.
  5. Mark stale items for later review.

Outputs

A concise memory entry with source, confidence, and safety status.

Failure modes

  • Saving secrets.
  • Saving noisy transcripts.
  • Failing to update obsolete memory.

Verification checklist

  • Entry is durable.
  • No sensitive data is included.
  • Source and confidence are clear.
  • Staleness risk is noted.

Related skills: skills/core/architecture-decision-records/SKILL.md, skills/core/grill-user-before-building/SKILL.md (Phase 2 docs-aware), CONTEXT.md

Applied / Not Applied

Applied from Supermemory-inspired design: durable memory should be scoped, searchable, source-aware, privacy-filtered, and useful for later retrieval. Not applied: hosted Supermemory service requirement, SDK client, cloud auth, dashboard, connector stack, database infrastructure, or storing full transcripts by default.

Ghi chú tiếng Việt

Dùng kỹ năng này để lưu hoặc truy xuất ngữ cảnh bền vững một cách an toàn. Không lưu bí mật, token, khóa riêng tư hoặc dữ liệu cá nhân không cần thiết.

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.