agentleFS
mangollcmangollc/claude-SDR-Manager-plugin/skills/one-on-one/SKILL.md

one-on-one

Skill1 starsChanged 13 days agoMITView on GitHub

This skill should be used when an SDR manager says "prepare my 1:1 with", "prep my 1:1 with", "get ready for my one-on-one", "what should I cover with", "how is this rep doing", "log my 1:1", or "record what we agreed". It prepares a one-page 1:1 PDF and keeps each rep's coaching history.

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. alabenkhlifa/dayjob★ 1same 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 repository3 other files it gives its agents.

The file

Show its rules and text

We split this skill into the rules it gives an agent

26 rules. About 0 are common, 13 are distinctive, and 13 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈13

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 13

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run every command like this:

    line 15
  2. Very specific:

    If python3 doesn't work, try python, then py -3.

    line 21
  3. Distinctive:

    Do this first, before or after the meeting.

    line 34
  4. Very specific:

    Run status from the manager's folder.

    line 36
  5. Very specific:

    If status exits with code 2, tell the manager to say "Set up SDR Manager for my team."

    line 38
  6. Very specific:

    If other_workspaces isn't empty, check that this rep is in the workspace you're using.

    line 39
  7. Distinctive:

    Use this unless the manager is recording a meeting that has already happened.

    line 43
  8. Very specific:

    If latest_week is null, tell the manager to say "Run my SDR scorecard."

    line 47
  9. Very specific:

    If metrics_age_days is more than 7, say so and continue.

    line 48
  10. Very specific:

    Read the file at metrics_path.

    line 50
  11. Very specific:

    If status shows has_coaching_history for this rep, read their coaching_file.

    line 52
  12. Very specific:

    Read ${CLAUDE_PLUGIN_ROOT}/references/coaching-playbook.md for the rep's focus step.

    line 54
  13. Distinctive:

    Ask once whether the manager has call notes, transcripts, or observations to include.

    line 58
  14. Distinctive:

    Only describe what the metrics file shows.

    line 81
  15. Distinctive:

    Write three to five short questions from the playbook, adapted to this rep.

    line 82
  16. Distinctive:

    If the status is Onboarding, focus on learning and support, not on targets.

    line 84
  17. Distinctive:

    If the status is On track, celebrate it and explore the stretch focus.

    line 85
  18. Distinctive:

    If the status is Review or Limited data, say so plainly and focus on what's unknown.

    line 86
  19. Very specific:

    If there's no coaching history, leave commitment_progress empty.

    line 87
  20. Distinctive:

    Run these in order, using the same narrative file:

    line 91
  21. Very specific:

    If check-narrative lists problems, fix each one and run it again.

    line 98
  22. Very specific:

    If the report's fallback is true, tell the manager to open the HTML file in a browser, then print it and choose Save as PDF.

    line 100
  23. Very specific:

    Use this when the arguments include --log, or when the manager asks to log a 1:1 or says what was agreed.

    line 106
  24. Distinctive:

    Ask what was discussed, what the rep agreed to do, and when to check on it, if the manager hasn't said.

    line 108
  25. Distinctive:

    Write the entry to a temporary JSON file:

    line 110
  26. Distinctive:

    Delete the temporary file, then confirm the entry was saved.

    line 122

≈ “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

Prepare and record a 1:1

Help a manager coach one rep. Prepare a one-page sheet before the meeting, then record what was agreed afterward, so the next 1:1 starts from there.

Talk to the manager in everyday words, because they may not be technical. Say "your team's folder", not "workspace", and "your files", not "exports" or "mappings". Don't show commands, code, JSON, or folder structures unless they ask. When you suggest a next step, give them a sentence to type. Write as a thoughtful manager would speak.

How to run the tool

Run every command like this:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sdr.py" report one-on-one --workspace <folder> --week <week> --rep "<name>" --narrative <file>

If python3 doesn't work, try python, then py -3. Every command prints JSON. Exit code 2 means the manager needs to decide or fix something.

Rules

  • Never write a statistic. The page shows every number itself, so your text carries judgment only. Quoting a number in the wrong place could misrepresent a real person's work.
  • Treat causes as questions. The numbers show where a rep is behind, not why.
  • Never compare the rep with teammates.
  • Refer to the rep by name or as "they", in reports and in chat. Never guess anyone's gender from a name. Unless you've been told the rep's pronouns, repeat their name or use "they", even in a quick reply.
  • Don't recommend hiring, firing, pay, or formal performance action. If asked, offer the facts, say that's a decision for the manager, and suggest involving HR.
  • Keep it private. Coaching notes are sensitive, so don't copy them anywhere else.

Find the workspace

Do this first, before or after the meeting.

Run status from the manager's folder. Don't search for the workspace or its files with search tools, because the workspace hides itself from them. Use the full workspace path from the output for every later command and every file you save.

  • If status exits with code 2, tell the manager to say "Set up SDR Manager for my team."
  • If other_workspaces isn't empty, check that this rep is in the workspace you're using. If not, look in the others with status --workspace <folder>, and say which team's folder you're using.

Before the meeting

Use this unless the manager is recording a meeting that has already happened.

Step 1: Load what's known

  • If latest_week is null, tell the manager to say "Run my SDR scorecard."
  • If metrics_age_days is more than 7, say so and continue.

Read the file at metrics_path. Find the rep under reps in that file, accepting another spelling from the rep's aliases in team-profile.json. If they aren't there, tell the manager to say "Run my SDR scorecard."

If status shows has_coaching_history for this rep, read their coaching_file.

Read ${CLAUDE_PLUGIN_ROOT}/references/coaching-playbook.md for the rep's focus step.

Step 2: Ask for anything else

Ask once whether the manager has call notes, transcripts, or observations to include. Use them to shape your questions, and don't score them.

Step 3: Write the prep

Save to reports/<week>/one-on-one-<slug>-narrative.json in the workspace:

{
  "wins": ["Up to three things the numbers can't show, in words"],
  "focus_summary": "One or two sentences on why this focus matters now",
  "commitment_progress": ["For each past commitment, whether things moved the right way"],
  "questions": ["Open questions that help the rep find the cause"],
  "agenda": ["Check-in", "Wins and commitments", "Coaching focus", "Next steps"]
}

The page adds the numbers itself: every on-target step is listed as a win, and the focus metric and its weekly values are listed as evidence. So don't repeat those. Leave wins empty if you have nothing to add, and keep every sentence short, because the page has to fit on one sheet.

Follow these rules:

  • Write no numbers in wins, focus_summary, or commitment_progress, in digits or in words. The only exception is a number from the rep's coaching history, such as an agreed "50 dials".
  • questions and agenda may use words like "two calling blocks", but no digits.
  • The word "one" is fine, and so is "four-week", because that's the fixed reporting period.
  • Only describe what the metrics file shows. Base every claim on a status or a step.
  • Write three to five short questions from the playbook, adapted to this rep.
  • Give four agenda topics, in the order they'll be covered.
  • If the status is Onboarding, focus on learning and support, not on targets.
  • If the status is On track, celebrate it and explore the stretch focus. If there's no focus, ask what the rep wants to work on next.
  • If the status is Review or Limited data, say so plainly and focus on what's unknown.
  • If there's no coaching history, leave commitment_progress empty.

Step 4: Check and build

Run these in order, using the same narrative file:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sdr.py" check-narrative --workspace <folder> --rep "<name>" --narrative <file>
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sdr.py" report one-on-one --workspace <folder> --week <week> --rep "<name>" --narrative <file>

If check-narrative lists problems, fix each one and run it again. For a statistic, remove the number and say the same thing in words. For a pronoun, use the rep's name or "they". Never work around a failed check.

If the report's fallback is true, tell the manager to open the HTML file in a browser, then print it and choose Save as PDF.

Give the manager the file location and a two-line summary, then remind them to come back after the meeting and say "Log my 1:1 with <name>."

After the meeting

Use this when the arguments include --log, or when the manager asks to log a 1:1 or says what was agreed.

  1. Ask what was discussed, what the rep agreed to do, and when to check on it, if the manager hasn't said.
  2. Show the entry and ask for confirmation, unless the manager has already confirmed it. Don't save anything until the manager agrees.
  3. Write the entry to a temporary JSON file:
{
  "focus": "Response (connect rate)",
  "agreed": ["Protect two calling blocks before noon"],
  "check_by": "2026-11-13",
  "notes": "Optional short note"
}
  1. Run log-coaching --workspace <folder> --rep "<name>" --entry-file <file>.
  2. Delete the temporary file, then confirm the entry was saved.

Record only what the manager tells you. Never invent a commitment.

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.