agentleFS
ZAidBinAsifZAidBinAsif/flutter-ai-starter/.cursor/skills/save-context/SKILL.md

save-context

Skill0 starsChanged 5 months agoMITView on GitHub

Persist research and decisions to context/ across sessions

2 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

8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read context/ — files relevant to the current task

    line 12
  2. Very specific:

    Read context/project.md if it exists (project identity)

    line 13
  3. Very specific:

    Read docs/DECISIONS.md for stack/architecture ADRs

    line 14
  4. Very specific:

    Read docs/ARCHITECTURE.md when touching app structure

    line 15
  5. Distinctive:

    Do ask permission: before new skills or rules

    line 33
  6. Distinctive:

    Keep files scannable; date entries that accumulate

    line 52
  7. Distinctive:

    Don't save trivial re-derivable facts

    line 53
  8. Distinctive:

    Check existing files before creating duplicates

    line 54

≈ “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

Saving Workspace Context

Build institutional memory in this repo's paths only.

At session start

  1. Read context/ — files relevant to the current task
  2. Read context/project.md if it exists (project identity)
  3. Read docs/DECISIONS.md for stack/architecture ADRs
  4. Read docs/ARCHITECTURE.md when touching app structure

Where to save

SignalLocation
Stack / architecture decisiondocs/DECISIONS.md (dated ADR)
Research, spikes, domain notescontext/{topic-slug}.md (dated entries)
Project identity (what/who/constraints)context/project.md
New component catalog entrydocs/DESIGN.md
Repeatable workflowNew skill in .cursor/skills/ (ask first)
Persistent code constraintNew rule in .cursor/rules/ (ask first)

Link from context/ to ADRs — do not duplicate.

How to save

  • Don't ask permission for small context/ appends — mention what you saved
  • Do ask permission before new skills or rules
  • Append with dated entries (newest first); don't overwrite history

Context file format

# {Topic}

## {Date} — {Brief title}

{What was learned or decided}

End of session

Save anything painful to redo: research, discovered patterns, deferred decisions.

Rules

  • Keep files scannable; date entries that accumulate
  • Don't save trivial re-derivable facts
  • Check existing files before creating duplicates

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.