A preserved method from https://github.com/mattpocock/skills at 3cca18b368ae, path skills/productivity/grilling, MIT. 11 of 31 source lines differ (35%), every difference claimed by an entry of the ledger with its reason. Entries: baseline-copies-2026-09-11, pull-2026-09-11, fold-2026-09-11, vocabulary-owner-2026-09-12.
greenline renders its own frontmatter: quoted name and description, the description from the manifest override where one existed, no upstream activation flag
name: grilling
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.
description: "Grill the user relentlessly about a plan, decision, or idea, and fire on your own judgment the moment scope, intent, or a term is unclear mid-work. Use for any 'grill' trigger phrase, for stress-testing thinking, and for ambiguity that must not be guessed through."
---
---
scopechangedvocabulary-owner-2026-09-12
The opening paragraph and the closing Durable output line say when grilling fires (a grill trigger phrase, or on the agent's own judgment when scope, intent or a term is unclear mid-work), that settled decisions in the decisions book, an initiative's decisions.md or the ticket are read first and not reopened, that a discussion earns no initiative or ticket, that durable shaping decisions belong to grill-with-docs and a compact task's settled intent to its ticket, and that a read-only discussion and the operator's stopping point are respected; grilling is situational, applied and never offered, with no durable output. (carried from fold-2026-09-11; the word operator became owner where the copy names the workspace's person, and request owner became request holder (the internal refactor's step 1, ruling 10, 2026-09-12))
Fire on any 'grill' trigger phrase, and on your own judgment the moment scope, intent or a term is unclear mid-work: an ambiguity is put to the user, never guessed through. The questions are the consequential ones this request leaves open, so read the settled decisions first, in the decisions book, an initiative's decisions.md or the ticket at hand, and reopen none of them. A discussion earns no initiative and no ticket merely because this skill is available. When the shared understanding is a larger intent that needs durable shaping decisions, grill-with-docs records them; a compact task keeps its settled intent and acceptance in its own ticket. A read-only discussion stays read-only, and the owner's stated stopping point ends the interview where it stands.
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.
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: the questions you can ask _now_ without guessing at answers you haven't heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round.
Work the tree in **rounds**. The **frontier** is every decision whose prerequisites are already settled: the questions you can ask _now_ without guessing at answers you haven't heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round.
17 unchanged lines
Format a round like so:
Format a round like so:
```
```
❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
➡️ <your recommended answer>
➡️ <your recommended answer>
---
---
❓ **Q2** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
❓ **Q2** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
➡️ <your recommended answer>
➡️ <your recommended answer>
```
```
Each round the user answers reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a _later_ round, not this one.
Each round the user answers reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a _later_ round, not this one.
Finding _facts_ is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it; don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report; ask the rest of the frontier now. The _decisions_ are the user's: put each to them and wait.
Finding _facts_ is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it; don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report; ask the rest of the frontier now. The _decisions_ are the user's: put each to them and wait.
The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.
The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.
scopechangedfold-2026-09-11
The opening paragraph and the closing Durable output line say when grilling fires (a grill trigger phrase, or on the agent's own judgment when scope, intent or a term is unclear mid-work), that settled decisions in the decisions book, an initiative's decisions.md or the ticket are read first and not reopened, that a discussion earns no initiative or ticket, that durable shaping decisions belong to grill-with-docs and a compact task's settled intent to its ticket, and that a read-only discussion and the operator's stopping point are respected; grilling is situational, applied and never offered, with no durable output.
Durable output: none. Applied, never offered, when scope, intent or a term is unclear mid-work; a discussion earns no initiative; durable shaping belongs to grill-with-docs.
agents/openai.yaml
harnessremoved filebaseline-copies-2026-09-11
the renderer generates agents/openai.yaml from the manifest; the vendored copy is not projected
interface:
display_name: "Grilling"
short_description: "Stress-test thinking a round of questions at a time"
The timeline
Each entry that touched this method, with the differences it claimed as they stood at its commit, read from the repository's history.
2026-09-11baseline-copies-2026-09-11
the cutover to an edited copy (ADR 0039): the composed output written as the copy, every difference from upstream claimed with the reason of the overlay that produced it
SKILL.md
harnesschangedbaseline-copies-2026-09-11
greenline renders its own frontmatter: quoted name and description, the description from the manifest override where one existed, no upstream activation flag
name: grilling
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.
description: "Grill the user relentlessly about a plan, decision, or idea, and fire on your own judgment the moment scope, intent, or a term is unclear mid-work. Use for any 'grill' trigger phrase, for stress-testing thinking, and for ambiguity that must not be guessed through."
lifecyclechangedbaseline-copies-2026-09-11
greenline prelude, to fold: resolve the open questions of this request; no initiative is required to use the skill; durable shaping belongs to grill-with-docs
**greenline prelude: clarify the current intent.** Use the method below to resolve the consequential questions this request leaves open. Read existing decisions before reopening them. A discussion does not require an initiative merely because this skill is available. When a larger intent needs durable shaping decisions, grill-with-docs owns that recording; a compact task keeps its settled intent and acceptance in its own ticket. Respect a read-only discussion and the operator's stated stopping point.
agents/openai.yaml
harnessremoved filebaseline-copies-2026-09-11
the renderer generates agents/openai.yaml from the manifest; the vendored copy is not projected
interface:
display_name: "Grilling"
short_description: "Stress-test thinking a round of questions at a time"
2026-09-11pull-2026-09-11
pin advance to 3cca18b: upstream moved with no change under the vendored paths
2026-09-11fold-2026-09-11
The prelude is folded into an opening scope paragraph and a situational closing line; the design-tree method is untouched.
SKILL.md
scopechangedfold-2026-09-11
The opening paragraph and the closing Durable output line say when grilling fires (a grill trigger phrase, or on the agent's own judgment when scope, intent or a term is unclear mid-work), that settled decisions in the decisions book, an initiative's decisions.md or the ticket are read first and not reopened, that a discussion earns no initiative or ticket, that durable shaping decisions belong to grill-with-docs and a compact task's settled intent to its ticket, and that a read-only discussion and the operator's stopping point are respected; grilling is situational, applied and never offered, with no durable output.
Fire on any 'grill' trigger phrase, and on your own judgment the moment scope, intent or a term is unclear mid-work: an ambiguity is put to the user, never guessed through. The questions are the consequential ones this request leaves open, so read the settled decisions first, in the decisions book, an initiative's decisions.md or the ticket at hand, and reopen none of them. A discussion earns no initiative and no ticket merely because this skill is available. When the shared understanding is a larger intent that needs durable shaping decisions, grill-with-docs records them; a compact task keeps its settled intent and acceptance in its own ticket. A read-only discussion stays read-only, and the operator's stated stopping point ends the interview where it stands.
scopechangedfold-2026-09-11
The opening paragraph and the closing Durable output line say when grilling fires (a grill trigger phrase, or on the agent's own judgment when scope, intent or a term is unclear mid-work), that settled decisions in the decisions book, an initiative's decisions.md or the ticket are read first and not reopened, that a discussion earns no initiative or ticket, that durable shaping decisions belong to grill-with-docs and a compact task's settled intent to its ticket, and that a read-only discussion and the operator's stopping point are respected; grilling is situational, applied and never offered, with no durable output.
Durable output: none. Applied, never offered, when scope, intent or a term is unclear mid-work; a discussion earns no initiative; durable shaping belongs to grill-with-docs.
2026-09-12vocabulary-owner-2026-09-12
The workspace's person is the owner: the word operator became owner where the copy names the workspace's person, and request owner became request holder (the internal refactor's step 1, ruling 10, 2026-09-12); every earlier claim on a re-measured hunk is carried forward under its own kind, with its authority where it had one.
SKILL.md
scopechangedvocabulary-owner-2026-09-12
The opening paragraph and the closing Durable output line say when grilling fires (a grill trigger phrase, or on the agent's own judgment when scope, intent or a term is unclear mid-work), that settled decisions in the decisions book, an initiative's decisions.md or the ticket are read first and not reopened, that a discussion earns no initiative or ticket, that durable shaping decisions belong to grill-with-docs and a compact task's settled intent to its ticket, and that a read-only discussion and the operator's stopping point are respected; grilling is situational, applied and never offered, with no durable output. (carried from fold-2026-09-11; the word operator became owner where the copy names the workspace's person, and request owner became request holder (the internal refactor's step 1, ruling 10, 2026-09-12))
Fire on any 'grill' trigger phrase, and on your own judgment the moment scope, intent or a term is unclear mid-work: an ambiguity is put to the user, never guessed through. The questions are the consequential ones this request leaves open, so read the settled decisions first, in the decisions book, an initiative's decisions.md or the ticket at hand, and reopen none of them. A discussion earns no initiative and no ticket merely because this skill is available. When the shared understanding is a larger intent that needs durable shaping decisions, grill-with-docs records them; a compact task keeps its settled intent and acceptance in its own ticket. A read-only discussion stays read-only, and the owner's stated stopping point ends the interview where it stands.