coaching-note
Skill0 starsChanged 19 days agoMITView on GitHub
Turn QA results, metrics or a ticket into a coaching note and a feedback message in SBI form, plus a coaching log entry. Use when the user asks to write feedback for an agent, prepare a 1:1, draft a coaching email, or log a coaching conversation.
In this repository3 other files it gives its agents.
- calibrationSkill
- nesting-reviewSkill
- qa-reviewSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 17
Never speculate about why the person behaved that way.
≈ “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 note
Template: ${CLAUDE_PLUGIN_ROOT}/templates/coaching-log.md.
Rules
- Facts first. Every observation points at a ticket id, a metric with a period, or a QA criterion. If the user has none, ask for one example before writing.
- One behavior to change per note. If there are three problems, pick the one with the biggest customer impact and park the rest for next time; say which you parked.
- The behavior is observable: "open with the customer's goal in one sentence" not "be more customer focused".
- Measurable follow up: criterion or metric, target, date.
- Tone: direct and warm, no corporate padding, no praise sandwich. Strengths are real and specific or they are left out.
- Never speculate about why the person behaved that way. Ask them; log their answer.
- Nothing personal in the log: no health, family, mood, personality labels.
Outputs
- The feedback message (email or chat, user chooses; default email under 180 words).
- The filled coaching log table.
- A one line calendar reminder text for the follow up date.
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.