agentleFS
mpaaratingmpaarating/ai-workflow-kit/skills/standup/SKILL.md

standup

Skill2 starsChanged 8 months agoMITView on GitHub

Draft and post async standup updates from your current work context

55 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-day, kickoff 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

  • 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

  • GitHubSkill

    refactor

    Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

    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

  • Hugging FaceSkill

    implement

    Make tests pass. Invoke after /write-tests produces failing tests.

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 51 edited versions we read keep these.

  • 11

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If {{tasks}} is not configured, check today's daily page in {{notes}} for context instead.

    line 26
  2. Distinctive:

    Quick mode: If the user provides all context inline (e.g., "standup: finished auth migration, working on PR review, blocked on deploy …

    line 38
  3. Distinctive:

    Keep each bullet to one line.

    line 59
  4. Distinctive:

    Always include task IDs when available — they make updates searchable.

    line 60
  5. Distinctive:

    If nothing is blocked, omit the Blocked section entirely.

    line 61
  6. Distinctive:

    If the user mentions availability changes (OOO, half-day, meetings), add a brief note at the end.

    line 62
  7. Distinctive:

    Don't post until they say it's good.

    line 69
  8. Distinctive:

    If {{chat}} is not configured, copy the formatted message to the clipboard and tell the user it's ready to paste.

    line 75
  9. Distinctive:

    If the team has a specific standup channel or thread convention, ask the user on first run and remember the preference.

    line 76
  10. Distinctive:

    Don't over-format. Standup updates should be scannable, not essays.

    line 86
  11. Distinctive:

    If the user says "standup" and there's nothing in-progress in {{tasks}}, ask them directly rather than posting an empty update.

    line 87

“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

Async Standup

Trigger Phrases

  • "standup"
  • "post update"
  • "async update"
  • "progress update"
  • "team update"

Workflow

Step 1: Gather Work Context

Query {{tasks}} for the user's in-progress and recently completed items.

  • In Progress: Tasks with "In Progress" or equivalent status, assigned to the user.
  • Recently Completed: Tasks completed since the last standup (or in the last 2 days if no prior standup is found).
  • Include: task ID, title, status.

If {{tasks}} is not configured, check today's daily page in {{notes}} for context instead. If neither is available, ask the user what they're working on.

Step 2: Collect Updates Per Item

For each in-progress item, ask the user:

  1. Progress: What did you do on this? (one line)
  2. Next: What's the next step? (one line)
  3. Blocked?: Anything blocking progress? (yes/no, and on whom if yes)

For recently completed items, just note them as done.

Quick mode: If the user provides all context inline (e.g., "standup: finished auth migration, working on PR review, blocked on deploy access"), parse it directly and skip the interactive questions.

Step 3: Format the Update

Draft the standup message using this structure:

**Done:**
- [task title] ([task ID])
- [task title] ([task ID])

**In Progress:**
- [task title] ([task ID]) — [progress note]. Next: [next step].

**Blocked:**
- [task title] ([task ID]) — blocked on [who/what]

[optional: one-line note about priorities or availability]

Rules:

  • Keep each bullet to one line.
  • Always include task IDs when available — they make updates searchable.
  • If nothing is blocked, omit the Blocked section entirely.
  • If the user mentions availability changes (OOO, half-day, meetings), add a brief note at the end.

Step 4: Preview and Confirm

Show the formatted message to the user and ask for confirmation before posting.

  • Let them edit, add, or remove items.
  • Don't post until they say it's good.

Step 5: Post to Team Channel

Post the confirmed message to the team channel in {{chat}}.

  • If {{chat}} is not configured, copy the formatted message to the clipboard and tell the user it's ready to paste.
  • If the team has a specific standup channel or thread convention, ask the user on first run and remember the preference.

Step 6: Confirm

Tell the user the update was posted (or copied to clipboard) and where.

Notes

  • This skill works best when morning-kickoff or daily page context exists, but it also works standalone.
  • Quick mode is the fast path: the user gives a one-liner and gets a formatted post in seconds.
  • Don't over-format. Standup updates should be scannable, not essays.
  • If the user says "standup" and there's nothing in-progress in {{tasks}}, ask them directly rather than posting an empty update.

Examples

Standard flow:

User: "standup"

Assistant: I see 3 items in your task tracker:

  • ENG-312: Auth migration (In Progress)
  • ENG-318: Login timeout fix (In Progress)
  • ENG-301: Dashboard redesign (To Do)

Quick progress update on each?

User: "312 is done, 318 has an open PR needs review, not starting 301 yet"

Assistant: Here's your standup:

Done:

  • Auth migration (ENG-312)

In Progress:

  • Login timeout fix (ENG-318) — PR open, needs review

Post to #team-standup?


Quick mode:

User: "standup: shipped auth migration, login timeout PR up for review, blocked on deploy access from infra"

Assistant: Here's your standup:

Done:

  • Auth migration

In Progress:

  • Login timeout fix — PR up for review

Blocked:

  • Deploy access — waiting on infra team

Post to your team channel?

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.