dank/command-center
1
0
Fork 0
Code Issues 5 Pull Requests Actions Packages Projects Releases Wiki Activity

fix(grilling): strip history and box-specific prose per review (Refs #20)

Browse Source 
- drop provenance blockquote and the absorbed-law attribution: the skill
  is instructions, not a history
- 'concurrency is capped' replaces the 3-scout figure of one machine
- completion distillate: project's knowledge base or a log markdown file,
  not a command-center-specific path (skill travels outside this repo)
This commit is contained in:
Frank
2026-10-18 19:09:04 -07:00
parent cedef97c99
commit fe039a0b73
1 changed files with 3 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
agent/skills/grilling/SKILL.md
+3 -7
View File
@@ -3,17 +3,13 @@ name: grilling
description: Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
---
> **Authored override.** Extracted 2026-10-18 from `mattpocock/skills` (identical to upstream at extraction) into the command-center repo so Frank can customize it. Removed from the `skills` CLI global store (`~/.agents/.skill-lock.json` pruned) so `skills update -g` never resurrects a duplicate. omp-aware redesign same day; absorbed the `one-decision-per-ask-question` managed skill. Edits to this file are repo prose: branch → PR → Frank OK.
Interview the user relentlessly until you reach a shared understanding. Map this as a **design tree**: every decision branches into the decisions that hang off it.
Work the tree in **rounds**. The **frontier** is every decision whose prerequisites are already settled. A question whose answer depends on an unsettled fact or another open question belongs to a _later_ round, not this one. Ask the whole frontier in one round, then wait.
## The round: `ask` is the default vehicle
Every frontier decision that fits 2–5 options goes through the `ask` tool - one question per decision, `recommended: 0` (the recommended answer is always option 0; the user's single Enter is the bare "yes" that accepts it). Prose in chat is the exception, reserved for genuinely open narrative ("walk me through the deploy flow") - never as buttons.
Per-question discipline (absorbed law, was the `one-decision-per-ask-question` managed skill):
Per-question discipline:
- One question decides exactly **one artefact**. Name it before sending; two names → split. A round may carry many single-artefact questions; a question may not.
- Shared plumbing is not grounds for merging: two products sharing an endpoint, service, or build step are still two questions.
@@ -32,11 +28,11 @@ Dialog mechanics you must respect: `ask` is exclusive - spawn scouts **before**
## Facts are yours; decisions are the user's
- Environment facts (filesystem, repo, live config): `task` + `scout`, one batch, one scout per fact-cluster; on this box at most 3 run at once, so cluster rather than spray.
- Environment facts (filesystem, repo, live config): `task` + `scout`, one batch, one scout per fact-cluster; concurrency is capped, so cluster rather than spray.
- Outside-world facts: call `web_search` directly - no spawn hop.
- Cheap lookups: `read`/`grep` inline.
- Only the main session may ask; every spawn carries the exact facts to return.
## Completion
Frontier empty and nothing blocked → write the settled-decisions summary from the ledger, then **one closing `ask`**: "Shared understanding reached - proceed?" Nothing executes before that yes. After it: distill the settled decisions into an `omp-docs/log.md` work-log entry through the normal branch → PR path, and refresh the ledger file to final form.
Frontier empty and nothing blocked → write the settled-decisions summary from the ledger, then **one closing `ask`**: "Shared understanding reached - proceed?" Nothing executes before that yes. After it: distill the settled decisions into the project's knowledge base, or a log markdown file, and refresh the ledger file to final form.