agentleFS
alabenkhlifaalabenkhlifa/dayjob/skills/standup/SKILL.md

standup

Skill1 starsChanged 29 days agoMITView on GitHub

Use when the user wants to prepare a daily standup, scrum update, or "what did I do yesterday" summary, or asks what they worked on recently.

55 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-day, meeting-prep and 8 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.
  • vantageos-agencySkill

    close-day

    End-of-day routine: close tasks with their time, leave the repository and the disk clean, write the diary, harvest friction, and hand over to tomorrow. Use this skill whenever the user says "close day", "end of day", "fin de journée", "bonne nuit", "wrap up", "call it a day", "close session", "daily close", or mentions ending their work session -- even if they don't say "close-day" explicitly.

    Also in 3 projects that use this

  • OpenAISkill

    meeting-prep

    Use when creating Public Equity Investing meeting prep briefs. Do not use for private diligence, IB, FP&A, legal, or scheduling-only tasks.

    Also in 5 projects that use this

  • jasonmichaelbell78-creatorSkill

    todo

    Cross-session todo management with interactive menu, JSONL-backed persistence, and AI-powered context capture. Manages ideas, tasks, and insights that emerge during sessions so they survive across sessions. Independent of GSD.

    Also in 3 projects that use this

  • takleb3rrySkill

    kickoff

    Initialize a new project by analyzing source documents and generating requirements.md and design.md

    Also in 3 projects that use this

  • asterkinSkill

    adr

    Create Architecture Decision Records (ADRs) following project standards. Guides template usage, process, and best practices for documenting architecturally significant decisions.

    Also in 4 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 7 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 51 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run these; skip any command that fails and keep going.

    line 12
  2. Very specific:

    If that is empty, retry with --author="<name>".

    line 18
  3. Distinctive:

    If a board tool is available (Jira, Linear, ClickUp, Trello, Asana, GitHub or GitLab issues, as MCP tools): my in-progress tickets with …

    line 27
  4. Distinctive:

    Keep a hit only if it names something still missing (access, a role, an approval, capacity, another team's work) and no later commit says …

    line 38
  5. Distinctive:

    Use it only for blockers and unfinished next steps, and only what the user said or agreed to.

    line 52
  6. Very specific:

    Start a bullet with its ticket refs as the board shows them (PROJ-279:, PROJ-74, PROJ-111:, #45:).

    line 59
  7. Distinctive:

    Every bullet is backed by a commit, PR, ticket, or the user's own words (in this chat or the last session).

    line 81
  8. Distinctive:

    Every ticket ref is copied from a commit, branch name, PR, or board tool.

    line 82
  9. Very specific:

    Never include commits by other authors.

    line 83
  10. Very specific:

    Never show tool errors (like gh not being logged in) in the standup.

    line 85
  11. Distinctive:

    Never post anywhere without an explicit yes.

    line 86

“Common” is measured: kept by at least 6 in 10 of the 51 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

Standup

Draft a paste-ready standup from real activity: Yesterday / Today / Blockers.

Gather context

Run these; skip any command that fails and keep going. If git itself will not run, say so and ask the user what they worked on.

  1. Who am I: git config user.name and git config user.email.
  2. Window: since the last working day. If date +%u prints 1 (Monday), use --since="last friday 00:00"; otherwise --since="yesterday 00:00". A range the user gives wins. For gh dates use d=$(date -v-1d +%F 2>/dev/null || date -d yesterday +%F) (Monday: -v-3d / "3 days ago").
  3. My commits on all branches, with the branch each came from (%S): git log --all --source --no-merges --author="<email>" --since="<window start>" --format='%h %S %ad %s' --date=short If that is empty, retry with --author="<name>". If user.email and user.name are both empty, ask the user which author to use; never run git log with an empty --author.
  4. GitHub, only if git remote -v shows a GitHub remote. The user may have several gh accounts, and the active one may not see this repo. List each account's access:
    for u in $(gh auth status 2>&1 | sed -n 's/.*account \([^ ]*\).*/\1/p'); do echo "$u $(GH_TOKEN=$(gh auth token --user "$u") gh repo view --json viewerPermission -q .viewerPermission 2>/dev/null)"; done; true
    Pick the first account with ADMIN, MAINTAIN or WRITE, else one with READ or TRIAGE. If none shows a permission, skip every gh call. Run every gh call as that account, GH_TOKEN=$(gh auth token --user <account>) gh ..., with 2>/dev/null. Never run gh auth switch.
    • My PRs: gh pr list --author @me --state all --search "updated:>=<YYYY-MM-DD>" --limit 20
    • My CI runs: gh run list --user <account> --limit 5
  5. Work in progress: git status --short --branch.
  6. If a board tool is available (Jira, Linear, ClickUp, Trello, Asana, GitHub or GitLab issues, as MCP tools): my in-progress tickets with their titles. Otherwise skip.
  7. Ticket refs: for each commit, take its ref from the subject; if the subject has none, from its branch name (%S); then from its PR title. One commit can carry several. Learn the format from the repo's own branches and commits:
    • a key like PROJ-279 (Jira, Linear, ClickUp custom IDs), often lowercase in branch names: fix/proj-279-midnight → PROJ-279
    • CU-86c0abc (ClickUp), #45 (GitHub or GitLab issue), AB#123 (Azure Boards), a Trello card link
    • A trailing (#15) from a squash merge is the PR number, not a ticket.
  8. Blockers written down: subjects rarely carry them. Scan my commit bodies, then the lines my commits added to notes, plans and task lists:
    p='block|wait(s|ing)? (for|on)|until .*(grant|approv|access)|must .* before|needs? .*(access|role|approval|permission)'
    git log --all --no-merges --author="<email>" --since="<window start>" --format='%h %b' | grep -iE "$p"
    git log --all --no-merges --author="<email>" --since="<window start>" -p -U0 --format='%h %s' -- '*.md' '*.txt' | grep -E '^\+[^+]' | grep -iE "$p"
    Keep a hit only if it names something still missing (access, a role, an approval, capacity, another team's work) and no later commit says it is done or no longer needed. A "Blocked: None" heading does not cancel a blocker written further down.
  9. Blockers said in chat: if the agent keeps chat logs, read the end of the last session for this repo. For Claude Code:
    d="${CLAUDE_CONFIG_DIR:-$HOME/.claude}/projects/$(pwd | sed 's/[^A-Za-z0-9]/-/g')"; f=$(ls -t "$d"/*.jsonl 2>/dev/null | grep -v "${CLAUDE_CODE_SESSION_ID:-none}" | head -1)
    [ -n "$f" ] && python3 -I -c 'import json,sys
    m=[]
    for l in open(sys.argv[1]):
      try: d=json.loads(l)
      except Exception: continue
      c=d.get("message",{}).get("content") if d.get("type") in ("user","assistant") else None
      t=c if isinstance(c,str) else " ".join(x.get("text","") for x in c or [] if isinstance(x,dict))
      if t.strip(): m.append(d["type"]+": "+t.strip()[:1500])
    print("\n\n".join(m[-10:]))' "$f"
    Use it only for blockers and unfinished next steps, and only what the user said or agreed to. It never counts as Yesterday activity.

If steps 3, 4 and 6 (commits, PRs, tickets) find nothing for this identity, reply: "No activity found for <email> since <date>." Then ask what to include. Uncommitted work from step 5 may inform Today but does not count as Yesterday activity. Never fill the gap with other people's work, and never name or describe their commits, even to say you left them out. You may offer to check another identity.

Write

  • Group commits by ticket, then by theme; one bullet can cover several commits. Drop noise (typos, merges, wip) unless it is all there is.
  • Start a bullet with its ticket refs as the board shows them (PROJ-279:, PROJ-74, PROJ-111:, #45:). Work with no ref in git, PRs or the board gets a bullet with no ref.
  • Plain language a teammate outside the code understands. No feat:/fix: prefixes, no commit hashes.
  • Today: name the specific unfinished file or branch when you found one. Infer from the current branch (name it), uncommitted work, what your latest commits leave unfinished (e.g. a test added but no fix yet), open PRs, in-progress tickets. Do not run tests or other project code. Mark guesses with "(confirm)".
  • Blockers: only real ones: failing CI, a PR waiting on review for more than a day, an open blocker from step 8 or 9, something the user said. Name who or what it waits on. Otherwise "None". If a blocker stops a Today step, that step says "once <blocker> is cleared".

Output template

**Yesterday**
- <ticket refs, if any>: <what changed and why it matters>

**Today**
- <ticket refs, if any>: <next step> (confirm)

**Blockers**
- None

Max 3 bullets per section. In the normal case, add nothing before or after the template except the closing line (a one-line caveat is fine when it changes how to read the standup). If a Slack, Teams or ticket tool is available, end with one line: "Want me to post it?" and post only after an explicit yes. Otherwise end after the template.

Rules

  • Every bullet is backed by a commit, PR, ticket, or the user's own words (in this chat or the last session).
  • Every ticket ref is copied from a commit, branch name, PR, or board tool. Never guess one.
  • Never include commits by other authors. Never run git log without --author, so other people's commits never appear in your own tool output either.
  • Normal case: the reply is the standup and the closing line. No notes about sources, skipped commits, other authors, or how you gathered data. The no-activity reply is the exception: it follows the no-activity rule above instead.
  • Never show tool errors (like gh not being logged in) in the standup; just leave that source out.
  • Never post anywhere without 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.