agentleFS
SurfrrosaSurfrrosa/claude-skills/session/SKILL.md

session

Skill1 starsChanged 5 months agoMITView on GitHub

Generate an end-of-session log for any project

17 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use debug, release and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    debug

    Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.

    Also in 3 projects that use this

  • MicrosoftSkill

    release

    Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).

    Also in 4 projects that use this

  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

17 rules. 0 are common, 9 are distinctive, and 8 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 9

    Distinctive

    This author's own choices. Worth a look.

  • 8

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No args: auto-detect the project from the current working directory

    line 13
  2. Distinctive:

    If the user provides a path directly, use that.

    line 26
  3. Distinctive:

    Check whether the project already has session logs:

    line 32
  4. Very specific:

    Look for docs/sessions/ directory (the established convention)

    line 34
  5. Very specific:

    If it exists, read docs/sessions/README.md to understand the index format

    line 35
  6. Very specific:

    If it doesn't exist, create docs/sessions/ and a README.md index (see Bootstrap below)

    line 36
  7. Distinctive:

    Check if a session log already exists for today's date

    line 41
  8. Very specific:

    If it does, append a counter: YYYY-MM-DD_session_2.md, YYYY-MM-DD_session_3.md

    line 42
  9. Distinctive:

    Read the previous session log (if any) to check whether planned "next tasks" were addressed

    line 62
  10. Distinctive:

    Check for any new TODO/FIXME comments added during this session

    line 63
  11. Very specific:

    Create docs/sessions/YYYY-MM-DD_session.md with this format:

    line 67
  12. Very specific:

    Add a one-line summary to the sessions table in docs/sessions/README.md.

    line 106
  13. Very specific:

    When a project has no docs/sessions/ directory:

    line 122
  14. Distinctive:

    Keep the one-line README summary under 200 characters.

    line 143
  15. Distinctive:

    Check the previous session's "Next tasks" list.

    line 144
  16. Distinctive:

    Don't fabricate accomplishments.

    line 145
  17. Very specific:

    After completing this skill, append a log entry to ~/.claude/skill-log.md under the Run Log table.

    line 150

“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “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

Session Log Generator

Generate a session log summarizing what was accomplished in the current session. Works for any project.

Arguments

The user may specify:

  • No args: auto-detect the project from the current working directory
  • A project name or path (e.g., myapp, ~/code/marketing-site)

Parse the argument string. Examples:

  • /session -- log for current project
  • /session myapp -- log for myapp

Project Aliases

AliasPath
myapp(add your projects here)

If the user provides a path directly, use that. If a name isn't in the alias table, search for it.

Process

Step 1: Detect session log location

Check whether the project already has session logs:

  1. Look for docs/sessions/ directory (the established convention)
  2. If it exists, read docs/sessions/README.md to understand the index format
  3. If it doesn't exist, create docs/sessions/ and a README.md index (see Bootstrap below)

Step 2: Determine the filename

  • Base format: YYYY-MM-DD_session.md
  • Check if a session log already exists for today's date
  • If it does, append a counter: YYYY-MM-DD_session_2.md, YYYY-MM-DD_session_3.md

Step 3: Gather context

Collect information from multiple sources to build the log:

From the conversation:

  • Review the conversation history to identify what was accomplished
  • Note any decisions made, approaches tried and abandoned, trade-offs weighed

From git:

cd [project-root]
# What changed this session (files modified since last commit before session, or today's commits)
git log --since="$(date +%Y-%m-%d) 00:00" --oneline
git diff --stat HEAD
git diff --cached --stat

From the project:

  • Read the previous session log (if any) to check whether planned "next tasks" were addressed
  • Check for any new TODO/FIXME comments added during this session

Step 4: Write the session log

Create docs/sessions/YYYY-MM-DD_session.md with this format:

# Session: YYYY-MM-DD

## Status: Complete

## What was accomplished

### [Category 1]
- Bullet points of what was done
- Include file names and specific changes

### [Category 2]
- More bullets

## Files created
- List any new files (or "None")

## Files modified
- List any modified files (or "None")

## Key decisions
- Any decisions made about architecture, approach, brand, etc. (or "None")

## Next tasks (prioritized)
1. Most important next task
2. Second priority
3. etc.

## Known issues
- Any issues discovered (or "None")

## Blockers
- Any blockers (or "None")

Step 5: Update the index

Add a one-line summary to the sessions table in docs/sessions/README.md.

Match the existing index format. If the README uses a table, add a table row. If it uses a bullet list, add a bullet. If you just bootstrapped it, use the table format shown in Bootstrap below.

Step 6: Commit

Stage and commit the session log and README update:

cd [project-root]
git add docs/sessions/YYYY-MM-DD_session.md docs/sessions/README.md
git commit -m "Add session log for [date] ([brief summary])"

Bootstrap (new projects)

When a project has no docs/sessions/ directory:

  1. Create docs/sessions/
  2. Create docs/sessions/README.md:
# Session Logs

| Date | Summary |
|------|---------|
  1. Proceed with writing the session log as normal.

Note: if the project has no docs/ directory at all, create docs/ first. This is a standard convention.

Notes

  • Be specific about files and changes, not vague. "Updated Header component" is bad. "Added mobile nav toggle to src/components/Header.tsx, swaps text via nav-full/nav-short spans at 768px" is good.
  • Prioritize next tasks based on what's time-sensitive or blocks other work.
  • Include key decisions so future sessions don't re-litigate them. "Decided to use Stripe Checkout instead of custom form because..." is valuable context.
  • Keep the one-line README summary under 200 characters.
  • Check the previous session's "Next tasks" list. If any were completed, note that. If any were skipped, note why.
  • Don't fabricate accomplishments. If the session was mostly debugging one issue, say that. A short honest log is more useful than a padded one.

Skill Run Logging

After completing this skill, append a log entry to ~/.claude/skill-log.md under the Run Log table. New entries at the top (most recent first).

Format: | YYYY-MM-DD | /skill-name | target (details) | one-line result |

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.