agentleFS
mfollmfoll/second-brain-template/.agents/skills/update-project-summary/SKILL.md

update-project-summary

Skill1 starsChanged 18 days agoMITView on GitHub

Refresh project state, scope, blockers and key links in the selected deployed vault; reconcile next actions when needed.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    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:

    Read the vault rules, Project Type, and Procedure completely before acting.

    line 18
  2. Distinctive:

    Start from the Project, its human view when present, and only task-relevant linked notes.

    line 22
  3. Distinctive:

    Keep the front page near 600–1,200 words and preserve its standard resumption sections.

    line 23
  4. Distinctive:

    Before shortening, build a preservation ledger for every removed block and verify its inspected destination.

    line 25
  5. Distinctive:

    Never treat Git as the sole home for decisions, exact parameters, provenance, caveats, rejected options, approvals, identifiers, handoffs, …

    line 26
  6. Distinctive:

    If durable detail has no verified destination, create or propose one, or leave a justified compactness exception.

    line 27
  7. Distinctive:

    Keep Current State concise, actions and links prioritized, and Maintenance Log to meaningful milestones.

    line 28

≈ “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

Update Project Summary

Refresh a Project’s current synthesis after significant work: state, scope, blockers and useful links. Reconcile next actions when the changed state affects them.

For a focused change to what should happen next, use update-project-next-actions. Both workflows update related project sections when needed.

Source of truth

  • Vault rules: AGENTS.md
  • Project contract: project.md
  • Complete workflow: procedures/update-project-summary.md

Read the vault rules, Project Type, and Procedure completely before acting.

Guardrails

  • Start from the Project, its human view when present, and only task-relevant linked notes.
  • Keep the front page near 600–1,200 words and preserve its standard resumption sections.
  • Replace stale synthesis instead of appending chronology; keep details in canonical linked notes.
  • Before shortening, build a preservation ledger for every removed block and verify its inspected destination. Thresholds never authorize lossy deletion.
  • Never treat Git as the sole home for decisions, exact parameters, provenance, caveats, rejected options, approvals, identifiers, handoffs, or revisit triggers.
  • If durable detail has no verified destination, create or propose one, or leave a justified compactness exception.
  • Keep Current State concise, actions and links prioritized, and Maintenance Log to meaningful milestones.
  • Preserve uncertainty and provenance. Update directly affected notes only when high-confidence; defer broad cascades.
  • Reconcile any existing human view when the notes a person should open next changed.
  • Review the diff against the preservation ledger before checkpointing; push only with current explicit authorization.

Select this package by the requested vault role, not its name alone. Reuse rules and the complete Procedure already read in this session while they remain current; reread after a relevant change.

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.