agentleFS
kaushikhegde11kaushikhegde11/obsidian-project-memory/update-project-memory/SKILL.md

update-project-memory

Skill0 starsChanged 2 months agoMITView on GitHub

Update an existing project's memory files in Obsidian from a new instruction or status update — refresh STATUS.md, prepend a dated progress.md entry, append any new decision to Decision.md, and update README.md only if the project direction changed. Companion to project-memory. The storage folder is configurable — no fixed vault structure. Use when the user says "update project memory", "log progress on <project>", "update the status", "record a decision", "the project changed direction", or pastes a project update. Assumes vault read/edit access and that the project's memory already exists.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. DeltaCorvi/Claude-Skills-for-Smart-Crows★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Update the memory of a project that already has a project-memory folder.

    line 8
  2. Very specific:

    Read project-memory-config.yaml (shared with project-memory).

    line 17
  3. Very specific:

    If the target project is not clear, ask which one.

    line 27
  4. Distinctive:

    Read the four files first.

    line 30
  5. Distinctive:

    If the update is ambiguous or context is missing, ask.

    line 40

≈ “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 Memory

Update the memory of a project that already has a project-memory folder. This skill is the update half of the pair. It does not create new project memory — for that, use project-memory.

Tool-neutral: it works in any coding agent that can read and write files — Claude Code (as a skill), OpenAI Codex (as an /update-project-memory prompt), or any other assistant with vault access. Below, "you" means whichever assistant is running these instructions.

Prerequisite: vault access + existing memory

  • Assumes you already have read, create, and edit access to the vault — through the Obsidian MCP server, plain filesystem tools, or your own sandbox mount. This skill does not set up access. If you cannot read or write the vault, stop and ask the user to grant it. In a sandboxed agent (Codex's default is workspace-write on the current directory only), ask the user to add the vault path as a writable root.
  • Assumes the project's memory folder and its four files already exist. If they do not, tell the user to run project-memory first.

Configuration (no fixed folders)

Read project-memory-config.yaml (shared with project-memory). Resolve its path in this order and use the first that exists:

  1. $PROJECT_MEMORY_CONFIG
  2. ~/.config/project-memory/config.yaml
  3. ~/.claude/skills/project-memory/project-memory-config.yaml
  4. ~/.codex/project-memory-config.yaml

Get vault_root, projects_folder, and date_format. Never hardcode a folder. If no config is found, ask for those values and save them to ~/.config/project-memory/config.yaml (same steps as project-memory).

Which project

If the target project is not clear, ask which one. Resolve its folder: <vault_root>/<projects_folder>/<Project Name>/.

What to update

Read the four files first. Then apply only the parts the update calls for.

  1. STATUS.md — refresh the snapshot: where it stands, next action, blockers, needs review. Replace the old snapshot and update the Last updated date.
  2. progress.md — prepend one new dated entry: what happened, what changed, next.
  3. Decision.md — if the update contains a decision, append it: what was decided, why, when to revisit.
  4. README.md — update only if the project direction or overview changed (what it is / why / who / how AI should help / links). Leave it untouched otherwise.

Rules

  • Make targeted edits. Do not overwrite a whole file when a small edit is enough. Prepend to progress, append to decisions, refresh status in place.
  • One project per folder. Do not touch other projects.
  • Date every new progress and decision entry in the configured format.
  • If the update is ambiguous or context is missing, ask. Do not fabricate status, decisions, or history.

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.