one-on-one
Skill1 starsChanged 31 days agoMITView on GitHub
Use when the user wants to prepare for a 1:1 (one-on-one) meeting with their manager, a report, or a peer — wins, blockers, asks, and topics to raise.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- mangollc/claude-SDR-Manager-plugintheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- mangollc/claude-SDR-Manager-plugin★ 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 repository12 other files it gives its agents.
- brag-docSkill
- design-docSkill
- fix-bugSkill
- incidentSkill
- postmortemSkill
- refactorSkill
- review-prSkill
- ship-prSkill
- standupSkill
- start-ticketSkill
- weekly-updateSkill
- whats-nextSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
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
- Distinctive: line 12
Run these; skip any command that fails and keep going.
- Distinctive: line 25
If calendar or ticket MCP tools exist: the meeting's agenda, my tickets.
- Distinctive: line 34
Do not run tests or other project code.
- Distinctive: line 59
Never show tool errors; leave that source out.
- Distinctive: line 60
Never send or post the prep anywhere.
- Distinctive: line 61
Do not name or describe anyone else's commits, even to say you left them out.
≈ “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.
Files
One-on-one
Walk into the 1:1 with your wins, blockers and asks ready, instead of "uh, things are fine".
Gather context
Run these; skip any command that fails and keep going.
- Who it's with: their manager, a report, or a peer. Take it from the user's words or project notes (CLAUDE.md, memory). If the user names a person and neither says the role, ask only "Is
<name>your manager, a report, or a peer?" and wait; gather nothing before the answer. With no person named ("my 1:1"), use manager. - Window: since the last 1:1 if the user says when; otherwise the last 14 days (
--since="14 days ago 00:00"). - Who am I:
git config user.nameandgit config user.email. Ifuser.emailanduser.nameare both empty, ask the user which author to use; never rungit logwith an empty--author. - My commits:
git log --all --no-merges --author="<email>" --since="<window start>" --format='%h %ad %s' --date=short(retry with--author="<name>"if empty). - My PRs, only with a GitHub remote. The user may have several
ghaccounts, and the active one may not see this repo. List each account's access:
Pick the first account with ADMIN, MAINTAIN or WRITE, else one with READ or TRIAGE. If none shows a permission, skip everyfor u in $(gh auth status 2>&1 | sed -n 's/.*account \([^ ]*\).*/\1/p'); do echo "$u $(GH_TOKEN=$(gh auth token --user "$u") gh repo view --json viewerPermission -q .viewerPermission 2>/dev/null)"; done; trueghcall. Run everyghcall as that account,GH_TOKEN=$(gh auth token --user <account>) gh ..., with2>/dev/null. Never rungh auth switch.gh pr list --author @me --state all --search "updated:>=<YYYY-MM-DD>" --limit 20. Note PRs waiting on review. - Brag doc: read the path the user names, else
~/brag-doc.mdif it exists. Use entries in the window. - If calendar or ticket MCP tools exist: the meeting's agenda, my tickets. Otherwise skip.
Write
- Wins: outcomes from the window, in plain language. Group related work.
- Blockers: what slows you down — reviews waiting, unclear requirements, things the user mentioned.
- Asks: what you need from this person (a decision, an intro, feedback, priorities). Mark each "(suggestion — confirm)".
- Topics: 1–3 things worth raising (growth, workload, feedback both ways). Mark each "(suggestion — confirm)".
- For a 1:1 with a report, flip it: their wins to recognize, their blockers to clear, questions to ask them. Their wins and blockers come only from what the user tells you or from tickets assigned to them (when ticket MCP tools exist); if neither gives anything, ask the user. Never pull the report's git history.
- Do not run tests or other project code.
Output template
**1:1 with <who> — <date>**
**Wins**
- <outcome>
**Blockers**
- None
**Asks**
- <ask> (suggestion — confirm)
**Topics**
- <topic> (suggestion — confirm)Max 4 bullets per section. End with one line: "Anything on your mind you want to add?"
Rules
- Your wins come only from the user's own commits, PRs, brag doc entries, or words. Always pass
--authortogit log; never include other people's work. - Never show tool errors; leave that source out.
- Never send or post the prep anywhere.
- Do not name or describe anyone else's commits, even to say you left them out. Nothing after the closing line.
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
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.

