brief
Skill8 starsChanged 41 days agoMITView on GitHub
Brief the user before a meeting, call, or piece of engagement work, from their imi knowledge base: open items, recent decisions, who is in the room, and threads still unresolved. Use when the user says "brief me before my call with X", "prep me for the Y meeting", "what do I need to know before I talk to Z", "I have a session with [client or person] in an hour", or names an upcoming meeting together with a client, project or person. Works with any imi domain.
78 other projects use a version of this.
Adopted by
Most recently taken up by
- serhiileniv/skillstheir own version, first seen Nov 8, 2026
- serhiileniv/ccstheir own version, first seen Nov 8, 2026
- fjwood69/moritheir own version, first seen Nov 8, 2026
- cathyzhang0905/agent-cockpittheir own version, first seen Nov 8, 2026
- nisarth/claude-skills-storetheir own version, first seen Nov 8, 2026
- grainulation/grainulatortheir own version, first seen Nov 3, 2026
Used with
Projects with it also use capture, strategy and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
toneron2Skillcapture
Capture thoughts to inbox with automatic classification
Also in 6 projects that use this
EpistatesSkillstrategy
Plan weekly or monthly X content strategy. Use when the user wants to plan their content calendar, set growth goals, build a content pipeline, or think strategically about their X presence.
Also in 4 projects that use this
aleksander-dytkoSkilldecision
Make a product decision with full context from the vault and available sources
Also in 3 projects that use this
dirienSkilldecide
Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.
Also in 5 projects that use this
JaimeGBASkillingest
Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base
Also in 7 projects that use this
howellsSkillreconcile
Audit a project against current plugin conventions and offer to update structure.
Also in 3 projects that use this
Other versions78 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 78
- anthropics/knowledge-work-plugins★ 35ksame name
- suboss87/FDEOps★ 940same name
- with-pebbly/aseprite-ai-artist★ 473same name
- educlopez/ui-craft★ 441same name
- github/lever★ 279same name
- dylanroscover/Embody★ 213same name
- yofine/skills★ 154same name
- grainulation/grainulator★ 86same name
- g2i-ai/agents★ 52same name
- gregmos/memoforge★ 38same name
68 more not listed
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 repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- domain-config-advisorSkill
- imi-onboardingSkill
- constitution-reviewSkill
- memory-wrapSkill
- what-changedSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 71 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 17
All tools below are on the imi MCP server.
- Distinctive: line 29
If something is ambiguous, make a reasonable guess, proceed, and state the assumption in one line at the top of the brief.
- Very specific: line 35
Use the shortest unambiguous name ("Acme", not "Acme Industrial Holdings Inc.").
- Distinctive: line 40
If nothing resolves, say the knowledge base has nothing on that subject yet and stop.
- Distinctive: line 67
Key points: only those that illuminate something specific and still unresolved.
- Very specific: line 99
Call record_memory_usage with the request_id from step 3.6, listing the record ids that made it into the brief as used_memory_ids and any …
“Common” is measured: kept by at least 6 in 10 of the 71 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Brief
Walk the user into a meeting with full context and nothing important hiding in a meeting they missed. Surface what is relevant and unresolved; do not tell them what to do.
All tools below are on the imi MCP server. Depending on the client they may appear with a
prefix (for example mcp__imi__search_signals); use whichever form is present. If no imi
tools are available, say so and stop — do not brief from memory.
1. Pull the subject out of the request
From the user's message, take:
- the organization, engagement or project the meeting is about;
- the people attending, if named;
- the meeting type or topic, if given (kickoff, check-in, renewal, a named decision).
If something is ambiguous, make a reasonable guess, proceed, and state the assumption in one line at the top of the brief. Do not ask clarifying questions before looking things up.
2. Resolve entities
For each organization, engagement and person, call get_entity_by_name to get its entity id.
Use the shortest unambiguous name ("Acme", not "Acme Industrial Holdings Inc."). If a
lookup fails, try search_knowledge_graph with the name and pick the best match of the right
type. Entity types come from the instance's domain schema — do not assume names like
client or account; use what the lookup returns.
If nothing resolves, say the knowledge base has nothing on that subject yet and stop.
3. Gather, in parallel
- Subject signals —
search_signalswith the organization's or engagement'sentity_id,max_results30, no type filter. You want open action items, recent decisions, and insights (risks, scope flags, blockers). - Attendee signals — for each named attendee,
search_signalswith theirentity_id,max_results20. This shows commitments and moments they were part of. - Connections —
find_related_entitieson the subject (mode"neighbors") for the people, engagements and systems around it;list_entity_profilesfor attendee roles. - Recent meetings —
list_meetingsand keep the ones whose title or participants match the subject; note the latest date. - What changed lately —
find_changeson the subject withdate_fromset to the date of the last meeting you found (or 30 days ago). Its dates are when things happened. - Anything said in passing —
memory_recallwith a query naming the subject and meeting topic. Keep the default record lane. Note therequest_id.
For a fuzzy subject ("the migration project"), ask_kb with the question in plain words is a
good first step to find the right entities; then continue with the steps above.
4. Filter before writing
- Flags (insights about risk, scope, blockers, drift): always surface, whatever their age.
- Open items: action items whose status is open or empty. Skip done ones.
- Decisions: the 3–5 most recent relevant ones. If a decision was superseded (a later signal changed it), report only the current one and say what it replaced.
- Key points: only those that illuminate something specific and still unresolved.
A brief that takes three minutes to read has failed. Be selective.
5. Write the brief
## Brief: <subject> — <meeting type if known>
<attendees if known> · <today's date> · last met <date of latest meeting, if any>
### Flags
Risks, scope questions, blockers, conflicts. Omit the section if there are none.
### Open items
**Owner** — what they owe *(source meeting or document, date)*
### Recent decisions
One line each, current version only. *(source, date)*
### Who's in the room
Per attendee: role, what they are connected to, and anything notable from their history
(recurring asks, past commitments). Two lines each at most.
### Still open
Threads raised earlier and never resolved, stated neutrally. Omit if none.Dates are when things happened (meeting date, sent date), not when imi recorded them. Omit empty sections; never write "none".
6. Close the loop
Call record_memory_usage with the request_id from step 3.6, listing the record ids that
made it into the brief as used_memory_ids and any you deliberately left out in ignored.
This improves future recall ranking.
Tone
A compass, not a camera. Facts and open threads, no editorializing, no advice unless asked. Readable in under 90 seconds.
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.

