agentleFS
Sign inStart free
alabenkhlifaalabenkhlifa/dayjob/skills/brag-doc/SKILL.md

brag-doc

Skill1 starsChanged 31 days agoMITView on GitHub

Use when the user wants to log a win, accomplishment, or piece of impact to their brag doc, or to draft a self-review, promotion case, or performance review from their brag doc.

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. mqmalagris/agent-skills★ 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 repository12 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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. Distinctive:

    Write wins down when they happen, so review season is copy-paste, not archaeology.

    line 8
  2. Very specific:

    Write the entry as - <what you did> — <impact>, in the user's words, tightened.

    line 25
  3. Very specific:

    No file yet and the user wants to backfill?

    line 28
  4. Distinctive:

    Read the entries for the period (the user's, or the last 6 months).

    line 32
  5. Distinctive:

    Never invent achievements, numbers, titles, or scope.

    line 40
  6. Very specific:

    Only the user's own work; always pass --author when reading git history.

    line 41

≈ “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

Brag doc

Write wins down when they happen, so review season is copy-paste, not archaeology.

The file

Path: the one the user names; otherwise ~/brag-doc.md.

# Brag doc

## <YYYY-MM-DD>
- <what you did> — <impact or result>

Log a win

  1. Take the win from the user's words. If the impact is missing, ask one question: "What changed because of it?" (a number if there is one).
  2. Append under today's date heading (date +%F); add the heading if it isn't there. If the file doesn't exist, create it with # Brag doc first.
  3. Write the entry as - <what you did> — <impact>, in the user's words, tightened.
  4. Confirm in one line with the path. Logging is what the user asked for, so no extra confirmation is needed.

No file yet and the user wants to backfill? Draft entries from their own commits (git log --author="<email>" --since=<date> --format='%ad %s' --date=short), show them, and write only after a yes. If user.email and user.name are both empty, ask the user which author to use; never run git log with an empty --author.

Draft a self-review

  1. Read the entries for the period (the user's, or the last 6 months).
  2. Group them into themes: Impact, Technical work, Collaboration and leadership, Growth. Skip empty themes.
  3. For each theme, 2–4 sentences in first person, leading with results and numbers from the entries. Restate only what the entries say: no new numbers or ratios ("3× faster"), causes, timing ("on time"), or scope.
  4. End with "Next period" — 2 goals marked "(suggestion — confirm)", each a direct continuation of an entry.
  5. Show the draft in chat. Don't write it to a file unless asked.

Rules

  • Never invent achievements, numbers, titles, or scope. Every claim traces to an entry or the user's words.
  • Only the user's own work; always pass --author when reading git history.
  • The self-review is a draft in chat; save it only after an explicit yes.

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.

Check your setup, free