agentleFS
faizkhairifaizkhairi/claude-code-blueprint/skills/save-diary/SKILL.md

save-diary

Skill73 starsChanged 4 months agoMITView on GitHub

MUST use when user says 'save diary', 'write diary', 'diary entry', 'update diary', or 'document session'. Also auto-trigger at the end of any significant session (feature shipped, major bug fixed, architecture decision, new project started).

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 7 are distinctive, and 3 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.

  • 3

    Very specific

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

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

    Prerequisite check (run first): if ./memory/diary/current/ does not exist OR ~/.claude/.memory-disabled marker file is present, this skill …

    line 7
  2. Distinctive:

    When this skill activates, output: "Dev Diary: documenting today's session."

    line 15
  3. Very specific:

    Create ./memory/diary/archived/YYYY-MM/ folder if not exists

    line 32
  4. Very specific:

    Check if ./memory/diary/current/YYYY-MM-DD.md exists

    line 38
  5. Distinctive:

    If exists: use it (will append new entry)

    line 39
  6. Distinctive:

    If not: create new file with header:

    line 40
  7. Distinctive:

    Write structured entry using our actual diary format:

    line 49
  8. Distinctive:

    Always APPEND: never overwrite existing diary entries

    line 69
  9. Distinctive:

    Archive first: run monthly archive check before every write

    line 72
  10. Distinctive:

    Evidence-based: document actual session content, not generic summaries

    line 73

≈ “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

Prerequisite check (run first): if ./memory/diary/current/ does not exist OR ~/.claude/.memory-disabled marker file is present, this skill is a no-op. Output: "Memory persistence is disabled. Run ./setup.sh and choose to enable memory if you want diary entries to be saved."

Dev Diary: Session Documentation Skill

Today's story takes shape.

Activation

When this skill activates, output: "Dev Diary: documenting today's session."

Context Guard

ContextStatus
User says "save diary" / "write diary" / "diary entry"ACTIVE, full diary write
End of significant sessionACTIVE, auto-document
User says "review diary"ACTIVE, read recent entries
Mid-conversation (no save request)DORMANT, no diary action

Protocol

Step 1: Monthly Archive Check

  • Scan ./memory/diary/current/ for files from previous months
  • For each file where month != current month:
    • Create ./memory/diary/archived/YYYY-MM/ folder if not exists
    • Move the file from current/ to archived/YYYY-MM/
  • Continue with diary write

Step 2: Find or Create Today's File

  • Check if ./memory/diary/current/YYYY-MM-DD.md exists
  • If exists: use it (will append new entry)
  • If not: create new file with header:
# YYYY-MM-DD, Session N: Brief Description

Step 3: Compose and Append Diary Entry

  • Get current date via bash: date +"%B %d, %Y" or PowerShell Get-Date -Format "MMMM dd, yyyy"
  • Analyze current session for key content
  • Write structured entry using our actual diary format:
    • Title: # YYYY-MM-DD, Session N: Brief Description
    • What Happened: Concise summary of the session context and goals
    • Fixes Applied / Key Changes: Specific technical work done (commits, code changes)
    • Key Insight: Lessons learned or important observations
    • Pending / Next Steps: What's left to do
  • Session numbering: Read the existing file first. Find the highest Session N number in today's entries and increment by 1. If this is the first entry of the day, check the previous day's file for the last session number and continue from there. If no previous entries exist, start at Session 1.
  • APPEND to today's file (never overwrite existing content)
  • Multiple entries per day are separated by ---

Step 4: Update Session Memory

  • Update ./memory/core/session.md with:
    • Session recap and key achievements
    • Current working state for continuity
    • Next steps identified
  • Confirm diary entry saved

Mandatory Rules

  1. Always APPEND: never overwrite existing diary entries
  2. One file per day: multiple entries separated by ---
  3. Use real timestamps: get current date via system command
  4. Archive first: run monthly archive check before every write
  5. Evidence-based: document actual session content, not generic summaries
  6. Use our format: concise technical summaries (What Happened, Key Changes, Key Insight, Pending)

Edge Cases

SituationBehavior
First entry of the dayCreate new file with header + first entry
Second+ entry same dayAppend with --- separator
No significant contentCreate brief entry noting session type
"review diary" commandRead and present recent entries from current/

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.