em-context
Skill114 starsChanged 7 months agoMITView on GitHub
Foundation skill for engineering managers. Use when setting up context about your team, org structure, management philosophy, and current priorities. All other EM skills read this first. Also use when creating or updating a direct report profile. Trigger phrases: "set my team context," "update my EM context," "here's my team setup," "my team is," "my org is," "add a report," "update report profile," "create a profile for.
In this repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- 1on1sSkill
- business-literacySkill
- career-developmentSkill
- delegationSkill
- developer-productivitySkill
- difficult-situationsSkill
- em-grid-scorerSkill
- engineer-motivationSkill
- feedbackSkill
- hiringSkill
- influenceSkill
- knowledge-sharingSkill
- management-transitionsSkill
- managing-high-performersSkill
- managing-upSkill
- managing-urgencySkill
- managing-yourselfSkill
- meetingsSkill
- performance-reviewsSkill
- retaining-developersSkill
- roadmap-planningSkill
- shadow-workSkill
- team-compositionSkill
- team-healthSkill
- working-with-architectsSkill
- working-with-pmSkill
- written-communicationSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
25 rules. About 0 are common, 11 are distinctive, and 14 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
Distinctive · estimate
This author's own choices. Worth a look.
14
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Team context: Create .agents/em-context.md with your team and org context.
- Very specific: line 29
Direct report profiles: Create .agents/reports/[firstname].md for each direct report.
- Distinctive: line 31
If files don't exist, ask the user for the relevant context before proceeding.
- Distinctive: line 33
When other skills learn durable new context, they should update these files automatically.
- Very specific: line 39
If there is no .agents/em-context.md yet, do not keep giving generic advice forever.
- Very specific: line 48
If a specific person comes up and there is no .agents/reports/[name].md yet, ask for a minimal profile for that person first, create the …
- Distinctive: line 57
Do not wait for a perfect profile.
- Very specific: line 63
All EM skills should use em-context as shared memory:
- Very specific: line 65
Read .agents/em-context.md first if it exists
- Very specific: line 66
If a specific person is involved, also read .agents/reports/[name].md
- Very specific: line 67
If .agents/em-context.md does not exist, collect the minimum manager profile and create it before giving detailed advice
- Very specific: line 68
If a specific person is involved and .agents/reports/[name].md does not exist, collect the minimum direct report profile and create it …
- Distinctive: line 69
If the conversation reveals durable new context, update the relevant file automatically
- Distinctive: line 70
Prefer additive updates over rewrites
- Distinctive: line 71
Do not overwrite existing context unless the user clearly corrected it
- Distinctive: line 73
Only save information that is likely to remain useful across future conversations.
- Distinctive: line 90
When in doubt, ask: "Will this still be useful and fair three months from now?"
- Very specific: line 141
Create one file per person at .agents/reports/[firstname].md:
- Distinctive: line 188
When another skill says "check em-context first," this means:
- Very specific: line 189
Read .agents/em-context.md if it exists
- Very specific: line 190
If the task involves a specific person, also look for .agents/reports/[name].md
- Very specific: line 191
If .agents/em-context.md does not exist, ask for a minimal manager profile and create it first
- Very specific: line 192
If a specific person is involved and .agents/reports/[name].md does not exist, ask for a minimal profile for that person and create it first
- Distinctive: line 194
Never ask for information already in the context files
- Distinctive: line 195
Never store guesses, temporary frustration, or unresolved interpretations as facts
≈ “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
EM Context
This is the foundation skill. Its purpose is to capture your team, org, and individual direct report context so every other skill can work with your specific situation rather than generic advice.
This skill is not meant to be the main thing you invoke every day. It is the shared memory layer for the other EM skills.
File Structure
.agents/
├── em-context.md # Your team and org context
└── reports/
├── alice.md # One file per direct report
├── bob.md
└── carol.mdHow to Use
Team context: Create .agents/em-context.md with your team and org context. All EM skills read this first.
Direct report profiles: Create .agents/reports/[firstname].md for each direct report. Skills like 1on1s, feedback, and performance-reviews will look for this file when you mention a person by name.
If files don't exist, ask the user for the relevant context before proceeding.
When other skills learn durable new context, they should update these files automatically. Treat them as living memory, not static setup files.
Bootstrapping Missing Context
If there is no .agents/em-context.md yet, do not keep giving generic advice forever. Ask for a minimal manager profile first, create the file, and then continue.
Minimum manager profile to collect:
- role/title
- team size
- team mission or area of ownership
- current challenge or priority
If a specific person comes up and there is no .agents/reports/[name].md yet, ask for a minimal profile for that person first, create the file, and then continue.
Minimum direct report profile to collect:
- title or level
- tenure on the team
- strengths
- current challenge, growth area, or reason they came up
Do not wait for a perfect profile. Save the minimum useful context first, then enrich it over time as new conversations reveal more.
Auto-Update Rules
All EM skills should use em-context as shared memory:
- Read
.agents/em-context.mdfirst if it exists - If a specific person is involved, also read
.agents/reports/[name].md - If
.agents/em-context.mddoes not exist, collect the minimum manager profile and create it before giving detailed advice - If a specific person is involved and
.agents/reports/[name].mddoes not exist, collect the minimum direct report profile and create it before giving detailed advice - If the conversation reveals durable new context, update the relevant file automatically
- Prefer additive updates over rewrites
- Do not overwrite existing context unless the user clearly corrected it
Only save information that is likely to remain useful across future conversations.
Good candidates for auto-save:
- team size, charter, org changes, stakeholder changes
- management preferences and communication norms
- a report's level, goals, working style, motivations, and recurring growth areas
- durable project ownership or recurring responsibilities
- feedback history and stable risk signals worth remembering
Do not save:
- one-off frustration or venting phrased as fact
- speculative diagnoses that have not been validated
- transient emotions that will age badly
- details that are too vague to help later
When in doubt, ask: "Will this still be useful and fair three months from now?"
Team Context Template
# EM Context
## About Me
- Role: (e.g., Engineering Manager, Senior EM, Director of Engineering)
- Years as EM:
- Company/team size:
- Industry:
## My Team
- Team size:
- Team mission/charter:
- Key areas of ownership:
- Current tech stack (brief):
- Team tenure mix: (e.g., mostly senior, mixed, mostly junior)
- Remote/hybrid/in-person:
## Org Structure
- Who I report to:
- Peer teams:
- Key stakeholders:
- How engineering relates to product/design:
## Current Priorities
- Top 3 team goals this quarter:
- Known challenges or risks:
- Recent wins:
## My Management Style
- How I like to run 1:1s:
- Feedback style (direct, coaching-oriented, etc.):
- Decision-making approach:
- Anything I'm actively working on as a manager:
## Norms and Preferences
- How we communicate (Slack, email, etc.):
- Meeting cadences:
- Performance review cycle:
- Anything unusual about this team/org I should know:Direct Report Profile Template
Create one file per person at .agents/reports/[firstname].md:
# [Name]
## Role & Background
- Title:
- Level: (e.g., L4, Senior, Staff)
- Tenure on team:
- Background / how they joined:
## Strengths
- [What they're genuinely good at — specific, not generic]
## Growth Areas
- [What they're actively working on or should be]
## Working Style
- How they prefer to receive feedback:
- Communication style:
- What motivates them:
- What drains them:
- How they handle ambiguity:
## Goals
- Short-term (this quarter):
- Long-term (career):
## Current Projects
- [Project name]: [their role and status]
## 1:1 Notes
- Cadence:
- What works well in our 1:1s:
- Recurring themes or topics:
## Feedback History
- [Date]: [Brief note on feedback given — topic, not full transcript]
## Flags / Things to Watch
- [Anything to be aware of — risk of attrition, stress, interpersonal friction, etc.]Instructions for Other Skills
When another skill says "check em-context first," this means:
- Read
.agents/em-context.mdif it exists - If the task involves a specific person, also look for
.agents/reports/[name].md - If
.agents/em-context.mddoes not exist, ask for a minimal manager profile and create it first - If a specific person is involved and
.agents/reports/[name].mddoes not exist, ask for a minimal profile for that person and create it first - If the conversation reveals durable new context, update the relevant file automatically
- Never ask for information already in the context files
- Never store guesses, temporary frustration, or unresolved interpretations as facts
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.

