feat(grilling): omp-aware interview redesign, absorb ask-etiquette law #20
@@ -5,7 +5,7 @@ description: Grill the user relentlessly about a plan, decision, or idea. Use wh
|
||||
|
||||
# Grilling
|
||||
|
dank marked this conversation as resolved
Outdated
|
||||
|
||||
Interview the user relentlessly until nothing is silently assumed. The subject is a **design tree**: every decision branches into the decisions that hang off it.
|
||||
Interview the user relentlessly until nothing is silently assumed and you reach a shared understanding. Map this as a **design tree**: every decision branches into the decisions that hang off it.
|
||||
|
dank marked this conversation as resolved
Outdated
dank
commented
"... until nothing is silently assumed and you reach a shared understanding. Map this as a design tree:..." "... until nothing is silently assumed and you reach a shared understanding. Map this as a design tree:..."
|
||||
|
||||
A decision is **frontier** when it can be asked now, without an answer you haven't heard yet. The interview is done when the frontier is empty: every branch of the tree visited.
|
||||
|
||||
@@ -36,11 +36,11 @@ Write `local://grilling-state.md` at the end of every round: the tree, each deci
|
||||
|
||||
## Facts are yours, decisions are theirs
|
||||
|
||||
- Environment facts (filesystem, repo, live config): dispatch a **scout** per fact-cluster, batched into one `task` call, before the round's `ask`. Cluster tightly; spawns are the expensive route.
|
||||
- Outside-world facts: call `web_search` directly.
|
||||
- Environment facts (filesystem, repo, live config): dispatch a **scout** per fact-cluster, batched into one `task` call, before the round's `ask`. Cluster tightly; doing so keeps each scout more aware of possible adjacencies.
|
||||
|
dank marked this conversation as resolved
Outdated
dank
commented
"Cluster tightly; doing so keeps each scout more aware of possible adjacencies." "Cluster tightly; doing so keeps each scout more aware of possible adjacencies."
|
||||
- Outside-world facts: call `web_search` directly, do not delegate to a subagent.
|
||||
|
dank marked this conversation as resolved
Outdated
dank
commented
call web_search directly, do not delegate to a subagent call web_search directly, do not delegate to a subagent
|
||||
- Cheap lookups: `read`/`grep` inline.
|
||||
- The main session is where questions happen: every spawn carries the exact facts to return, and comes back into the next round.
|
||||
|
dank marked this conversation as resolved
Outdated
dank
commented
The skill might not be used in the omp directory. Just say "either the projects knowledge base, or a log markdown file" The skill might not be used in the omp directory. Just say "either the projects knowledge base, or a log markdown file"
|
||||
|
||||
## Done
|
||||
## Definition of Done
|
||||
|
dank marked this conversation as resolved
Outdated
dank
commented
Definition of Done Definition of Done
|
||||
|
||||
The frontier is empty and nothing sits blocked. Distil the ledger into a **brief**: one line per decision, verdict plus rationale, grouped by branch. Put it in chat, then one closing `ask`: "Proceed on this brief?" Nothing executes before that yes. After it, fold the brief into the project's knowledge base, or a log markdown file, wherever the project keeps its decisions.
|
||||
Reference in new issue
Block a user
Drop this line. The skill is not a history.