agentleFS
GitHubKnown publishergithub/squad/.squad/skills/team-memory-maintenance/SKILL.md

team-memory-maintenance

Skill3.4k starsChanged 2 months agoMITView on GitHub

Merge accepted Squad decisions through the active state backend with exact verification

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    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:

    Use this skill only for accepted durable decisions.

    line 11
  2. Very specific:

    Use the active state backend for mutable Squad state.

    line 17
  3. Distinctive:

    Use archival-integrity procedures whenever accepted records are moved or compacted.

    line 19
  4. Distinctive:

    Stop on any mismatch and report the incomplete operation.

    line 30
  5. Distinctive:

    Stop if the team root, active backend, acceptance evidence, or required read-back capability is unavailable.

    line 34
  6. Distinctive:

    Stop if merged content or deletion cannot be verified exactly.

    line 36
  7. Distinctive:

    Do not manufacture a durable record for a tentative request, onboarding observation, or unaccepted recommendation.

    line 37

≈ “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

Team Memory Maintenance

Use this skill only for accepted durable decisions. The current Scribe role does not maintain session logs, orchestration logs, specialist histories, onboarding records, or general team memory.

Scope

  • Allowed targets: .squad/decisions/inbox/ and .squad/decisions.md.
  • Use the active state backend for mutable Squad state.
  • Preserve decision authorship, rationale, and accepted scope.
  • Use archival-integrity procedures whenever accepted records are moved or compacted.

Procedure

  1. Resolve the supplied team root and configured state backend.
  2. List and read every candidate inbox entry before acting.
  3. Merge only decisions that have explicit acceptance evidence.
  4. Deduplicate exact decision headings without rewriting unrelated decisions.
  5. Normalize nested headings while preserving relative hierarchy and fenced code blocks.
  6. Re-read .squad/decisions.md and verify the merged content before deleting an inbox entry.
  7. Refetch after deletion and verify the exact inbox entry is absent.
  8. Stop on any mismatch and report the incomplete operation.

Stop Conditions

  • Stop if the team root, active backend, acceptance evidence, or required read-back capability is unavailable.
  • Stop if merged content or deletion cannot be verified exactly.
  • Do not manufacture a durable record for a tentative request, onboarding observation, or unaccepted recommendation.

Anti-Patterns

  • Writing session logs or specialist histories.
  • Bypassing the state backend with branch switching, note-ref pushes, resets, or manual persistence.
  • Deleting inbox content before verifying the canonical merge.
  • Expanding a decision-only maintenance request into product or repository cleanup.

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.