agentleFS
thoughtbotthoughtbot/rails-consultant/skills/standup/SKILL.md

standup

Skill26 starsChanged 8 months agoMITView on GitHub

Write a client update — identify what was done, what's next, and surface risks before they become surprises. End of day, start of day, or end of week.

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 49 edited versions we read keep these.

  • 9

    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:

    Start by checking git for context:

    line 14
  2. Distinctive:

    Check for open branches, uncommitted work, open PRs

    line 17
  3. Distinctive:

    Wait for their answer. Git shows commits but misses investigation, debugging, conversations, decisions, and thinking.

    line 23
  4. Distinctive:

    Wait. This forces them to prioritise.

    line 29
  5. Distinctive:

    Wait. This surfaces blockers and risks before they become surprises.

    line 35
  6. Distinctive:

    Before writing the update, push on what they've said:

    line 39
  7. Distinctive:

    Don't ask all of these — pick the 2–3 that are most relevant based on what they've said.

    line 58
  8. Distinctive:

    After producing the update, close with:

    line 102
  9. Distinctive:

    Wait for their answer. If they identify something, help them reword it clearly — then the update is ready to send.

    line 106

“Common” is measured: kept by at least 6 in 10 of the 49 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

Behavior

This is a guided conversation that ends with a polished, ready-to-send update. Start by getting the raw material from the user — then help them sharpen it.

Step 1: Gather

Start by checking git for context:

  • git log --since="yesterday" --author=$(git config user.email) (or last few days if no recent commits)
  • Check for open branches, uncommitted work, open PRs

Then open with:

"Here's what I can see from git. Before I help you write this — what did you actually spend your time on? Git doesn't always tell the full story."

Wait for their answer. Git shows commits but misses investigation, debugging, conversations, decisions, and thinking. Their answer fills the gaps.

Then ask:

"What's the most important thing the client should know from today — if they read one sentence and nothing else?"

Wait. This forces them to prioritise. Most updates bury the lead.

Then:

"Is there anything the client needs to decide, unblock, or be aware of before your next working session?"

Wait. This surfaces blockers and risks before they become surprises.

Step 2: Sharpen — Socratically

Before writing the update, push on what they've said:

On completeness:

  • "You mentioned [X] — is that done-done, or is there a loose end the client should know about?"
  • "Is there anything you learned today that changes the plan or the estimate?"
  • "Are you waiting on anything from the client's side? Now's the time to ask — don't let it sit."

On risks — push hard here:

  • "Is there a risk here you're not mentioning because you think you can handle it? Those are the ones worth flagging early."
  • "If the client asked 'are we on track?' right now — what's your honest answer?"
  • "Are you going to hit the next deadline? If there's any doubt, say it now — not the day before."
  • "Is there anything that took longer than expected today? If so, does that change the timeline for what comes next?"
  • "Are there areas you shipped without full test coverage? What's the QA gap — and does the client know?"
  • "Is there a part of this feature that works but you're not confident in — something that could break under edge cases or real load?"
  • "Are there any assumptions you're making about the client's infrastructure, data, or users that you haven't verified?"
  • "If you got hit by a bus tomorrow, what would fall through the cracks?"

Don't ask all of these — pick the 2–3 that are most relevant based on what they've said. The goal is to catch the thing they'd forget to mention or unconsciously downplay. Consultants instinctively soften risks in updates — push against that.

On team communication — push here before writing:

  • "Is there something here you need to raise with your team before this goes to the client?"
  • "Did anything come up today that a teammate needs to know about — a decision you made, a direction you changed, or a dependency you introduced?"
  • "Is there a conversation you should have with someone on the team before your next working session — not the client, your team?"

This matters because client updates aren't the only communication that gets neglected. Internal alignment breaks quietly when people assume teammates will figure it out from the code.

Step 3: Write the Update

Produce a clean, ready-to-send update. Keep it short — clients don't read long updates. Format:


Update: [Date]

Done:

  • [Completed items — written in terms of outcomes, not tasks. "Users can now reset their password" not "Implemented password reset controller"]

In progress:

  • [What's actively being worked on, with brief status. "Billing integration — Stripe webhooks working, proration logic next"]

Up next:

  • [What's planned for the next working session]

Heads up:

  • [Risks, blockers, decisions needed, or anything the client should be aware of. Omit this section entirely if there's nothing — don't manufacture concern]

Writing Principles

  • Outcomes over tasks — "Users can now do X" beats "Implemented Y controller"
  • Honest over optimistic — a small concern flagged early builds trust; a surprise later erodes it
  • Short over thorough — respect the client's time. If they want more detail, they'll ask
  • No jargon — write for a smart person who doesn't know Rails. "Background processing" not "Sidekiq workers"
  • No filler — "Continued working on..." is not an update. Name what changed

After producing the update, close with:

"Read it back — does it honestly reflect where things stand? Is there anything you softened that should be said more directly?"

Wait for their answer. If they identify something, help them reword it clearly — then the update is ready to send.

Tone

Efficient and honest. This isn't a ceremony — it's a communication tool. Help them say what matters in as few words as possible, without hiding the uncomfortable parts.

Download now (ZIP)

  • Other versions53 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 53

    1. anthropics/knowledge-work-plugins★ 34ksame name
    2. drafthq/draft★ 40same name
    3. shipshitdev/skills★ 38same name
    4. rlajous/claude-code-commands★ 30same name
    5. GTMify/aigtm★ 25same name
    6. kriscard/Skills★ 15same name
    7. carlvellotti/codex-for-pms-skills-bonus★ 8same name
    8. edjchapman/claude-code-config★ 8same name
    9. jcurbelo/agent-seed★ 8same name
    10. zauberzeug/game-of-cards★ 7same name

    43 more not listed

    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.

  • Used alongsideProjects with it also use close-day, meeting-prep and 7 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

    • 0x43e96fSkill

      kickoff

      "Interview Me" 启动协议。需求不清晰时,在开始实施之前先反问用户,收集足够上下文再规划。 触发词: /kickoff、"先问我问题再开始"、"在动手之前了解需求"、"需求还不清楚"

      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

  • In this repository11 other files it gives its agents.

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.