coaching
Skill2 starsChanged 3 months agoMITView on GitHub
Use when the user says "coach my CSM", "feedback on this call", "call review", "my CSM keeps making the same mistake", "how do I give feedback on", or pastes a call transcript or a few sentences on what they saw. Produces a one page prep sheet for the conversation: diagnosis (skill, knowledge, will, environment), the single behavior, the opening self-assessment question, the quoted moment, two rehearsal prompts and the next-observation date. Not for calibrating account reads across a team (use portfolio-review) or writing the customer recap (use call-recap).
1 other project uses a version of this.
Adopted by
Most recently taken up by
- mycelium-hq/ai-brain-startertheir own version, first seen Apr 10, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- mycelium-hq/ai-brain-starter★ 50same 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 repository54 other files it gives its agents.
- account-contextSkill
- account-planSkill
- account-reviewSkill
- adoption-planSkill
- advocacy-askSkill
- book-reviewSkill
- book-triageSkill
- business-reviewSkill
- call-prepSkill
- call-recapSkill
- champion-lossSkill
- churn-postmortemSkill
- commitmentsSkill
- coverage-modelSkill
- csm-hiringSkill
- csm-rampSkill
- csql-motionSkill
- cs-scorecardSkill
- cs-startSkill
- customer-updateSkill
- day-planSkill
- email-criticSkill
- escalationSkill
- exec-conversationSkill
- expansion-caseSkill
- expansion-scanSkill
- handoffSkill
- hard-conversationSkill
- health-scoreSkill
- internal-askSkill
- invoice-chaseSkill
- mutual-action-planSkill
- nrr-narrativeSkill
- offboardingSkill
- onboarding-planSkill
- one-pagerSkill
- playbook-builderSkill
- portfolio-reviewSkill
- price-increaseSkill
- renewal-forecastSkill
- renewal-negotiationSkill
- renewal-riskSkill
- renewal-runwaySkill
- sales-handoffSkill
- save-planSkill
- stakeholder-mapSkill
- status-updateSkill
- survey-follow-upSkill
- team-rollupSkill
- usage-emailSkill
- value-ledgerSkill
- voice-of-customerSkill
- what-do-i-oweSkill
- skill-nameSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 13
If the user pasted a transcript, or gave about three sentences on what they saw (who, what happened, what the customer did), go straight to …
- Distinctive: line 21
Never coach on rumor: if the user only has a secondhand report, say so under "What I could not check" and build the sheet from what exists.
- Distinctive: line 34
Use this skeleton. It must fit one page.
- Distinctive: line 71
No next observation means it did not happen: If nobody looks again, the team learns these conversations are ceremony.
≈ “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
Coaching
A one page prep sheet for the manager, so the conversation changes one behavior instead of describing a call.
Start here
If the user pasted a transcript, or gave about three sentences on what they saw (who, what happened, what the customer did), go straight to "Do this".
Otherwise ask for these in ONE message, then proceed with whatever comes back:
- What you saw: the call or artifact, and the moment that bothered you
- Whether the person has done this well before, here or elsewhere
- Their book size and what they are measured on
Never coach on rumor: if the user only has a secondhand report, say so under "What I could not check" and build the sheet from what exists. If an "Account context" block exists in the conversation, use it.
Do this
- Diagnose before choosing an approach. Skill (does not know how): coach it. Knowledge (does not know the product or segment): teach it, faster. Will (knows how, not doing it): that is an expectations or fit conversation, not coaching. Environment (book too big, wrong incentive, missing tooling): that is the manager's problem. Give the evidence for the call and the one question that tests it: "have you done this before, somewhere it worked?"
- Pick one behavior. Observable and repeatable, such as "ask what outcome they need before showing anything". Choose the highest leverage one, which is often upstream of the visible miss. Cut the rest on purpose.
- Write the opening self-assessment question in the manager's voice: "How do you think that went, and what would you do differently?" Say what each likely answer tells you.
- Quote the moment. A timestamp or line, what was said, the neutral description and the consequence in outcome terms. Never a trait.
- Write two rehearsal prompts to run in the room, aloud, such as a customer line to answer cold. Tell the manager to let it be awkward.
- Set the next observation: the named call or document, a date, and the follow-up conversation date. Flag anything that is an environment problem and therefore the manager's to fix.
Output
Use this skeleton. It must fit one page.
COACHING PREP: [Name], [role] | observed [call or artifact, date]
Call: COACH / TEACH / PERFORMANCE CONVERSATION / FIX THE ENVIRONMENT
Diagnosis: skill / knowledge / will / environment - [evidence, said / seen / inferred]
The one behavior: [observable, one sentence]. Why this one: [leverage]
Open with: "[self-assessment question]"
If they name it: [what to do]. If they do not: [the gap is the finding]
The moment: [timestamp] "[quote]"
What happened: [neutral]. Consequence: [outcome]
Rehearse
1. "[prompt]"
2. "[prompt]"
Next observation: [call or document] on [date]. Follow-up conversation: [date]
Mine to fix: [environment items, or none]
What I could not check
- [gap]A filled example is in examples/sample.md. Match its length.
Rules
- One behavior, never six. A list of six improvements is accurate, fair and impossible to act on, so nothing changes.
- Diagnose first. Coaching a knowledge gap wastes weeks, coaching a will problem insults the person, and coaching an environment problem tells someone a structural failure is their fault.
- Self-assessment before feedback. A thing they name themselves is one they act on, and where they do not, the gap between their read and yours is the real finding.
- Describe the moment, never the person. "You did not ask what outcome they wanted" can be acted on tomorrow. "You are not curious enough" cannot be argued with or acted on.
- Rehearse, do not advise. Advice is understood and forgotten, and two minutes of practice out loud also shows whether it is really a skill problem.
- Coach the cause upstream. A weak recap email is usually a listening problem in the call, so fixing the email fixes nothing.
- No next observation means it did not happen. If nobody looks again, the team learns these conversations are ceremony.
- Keep it out of forecast and portfolio meetings and away from pay talk. Mixing "is this number right" with "are you good" corrupts both, and nothing said after money is heard as development.
Related (only if installed)
portfolio-review for calibrating reads across a team. call-recap for the artifact most call coaching is about. coverage-model when the performance problem is a book that cannot be covered.
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.

