alexion/dev
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

refactor(skills): remove drafting and grilling skills

Browse Source
This commit is contained in:
alexion
2026-10-17 19:54:17 -04:00
parent b9a7f32d13
commit 1665a73f6d
5 changed files with 0 additions and 216 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.pi/skills/grill
View File

@@ -1 +0,0 @@
../../src/skills/grill

1
.pi/skills/to-document
View File

@@ -1 +0,0 @@
../../src/skills/to-document

88
src/skills/grill/SKILL.md
View File

@@ -1,88 +0,0 @@
---
name: grill
description: Stress-test a plan, decision, or design through a one-question-at-a-time interview. Use when the user asks to grill, stress-test, pressure-test, challenge, interrogate, or poke holes in a plan.
---
# grill
Interview the user until the session has no open or blocked questions.
Open questions define the ending condition for the grill session.
Blocked questions track known decisions with unsettled prerequisites.
Do not begin implementation during or after grill without an explicit user instruction.
A completed grill summary is not an instruction to build.
## Run the interview
1. Prepare the grill.
Read the conversation, files, and docs that can settle facts or reveal constraints.
Resolve factual questions yourself when tools can answer them.
Do not ask the user for facts you can find.
Build the required-question set from the known plan or idea.
Put ready questions under `Open questions:`.
Put known questions with unsettled prerequisites under `Blocked questions:`.
Finish when both sections contain every known required question.
2. Start the interview.
Show `Open questions:` and `Blocked questions:` in short form.
Include titles only, not full question bodies.
Use Markdown list items in both sections.
Mark each initial item with `- [ ]`.
Ask exactly one numbered question in the same turn.
The question title must match an item under `Open questions:`.
Finish when the interview has started with exactly one numbered question.
3. Process the answer.
Account for the user's answer before asking another question.
Resolve, update, remove, unblock, or add questions as the answer requires.
Use `- [ ]` for unchanged unresolved questions.
Use `- [+]` for questions added by the latest answer.
Use `- [u]` for questions updated by the latest answer.
Use `- [x]` for questions resolved by the latest answer.
Use `- [-]` for questions removed by the latest answer.
Include a cause note for each `- [+]`, `- [u]`, and `- [-]` change.
Indent cause notes by two spaces under the changed question.
Show `- [+]`, `- [u]`, `- [x]`, and `- [-]` for one turn only.
After that turn, keep an updated question visible as `- [ ]`.
After that turn, remove resolved and removed questions from the visible list.
Move unblocked questions from `Blocked questions:` to `Open questions:` with `- [u]`.
Do not use `- [+]` for unblocked questions because they are not new.
Add questions only when the latest answer directly causes them.
When the user extends scope instead of answering, account for the new question before pursuing it.
Do not add optional follow-up questions to either section.
Put optional follow-up questions in the final summary instead.
Resolve newly answerable facts yourself.
Finish when every list change has an explicit marker and required cause note.
4. Ask the next question.
Show `Open questions:` and `Blocked questions:` on every active grill turn.
Keep `- [ ]` items visible every turn.
Preserve agent judgment when the user reframes or invalidates a question.
Show the resulting list change instead of following a rigid reframe algorithm.
If the user catches incorrect accounting, briefly explain the error.
Then show the corrected question sections.
Ask exactly one numbered question when `Open questions:` contains an unresolved item.
The question title must match an item currently shown under `Open questions:`.
Give concrete options with trade-offs.
Label options with `A.`, `B.`, `C.`, and later letters.
Use the same labels in the recommendation.
Give a recommendation and rationale.
Probe vague words, overloaded terms, and hidden assumptions.
Use concrete scenarios to test concept boundaries and edge cases.
When code contradicts the user's claim, quote both the claim and the code behavior.
If the turn includes a correction, file edit, apology, or explanation, still end with the next numbered question.
Finish when the turn ends with the next numbered question.
5. Close or pause.
Close when `Open questions:` and `Blocked questions:` are empty.
Output a concise summary of every decision reached.
Include optional follow-up questions that were not added to either section.
Do not act on the summary unless the user gives a new implementation instruction.
If the user changes tasks, state that grill is paused.
End the turn with the final decision summary or the pause statement.
Finish when the summary is delivered or grill is explicitly paused.

62
src/skills/to-document/DOCUMENT-FORMAT.md
View File

@@ -1,62 +0,0 @@
# Document Format
## Template
```md
## Problem Statement
The problem that the user is facing, from the user's perspective.
## Solution
The solution to the problem, from the user's perspective.
## User Stories
An extensive, numbered list of user stories, covering all aspects of the feature. Each user story should be in the format of:
1. As an <actor>, I want a <feature>, so that <benefit>
<user-story-example>
1. As a mobile bank customer, I want to see balance on my accounts, so that I can make better informed decisions about my spending
</user-story-example>
## Implementation Decisions
A list of implementation decisions that were made. This can include:
- The modules that will be built/modified
- The interfaces of those modules that will be modified
- Technical clarifications from the developer
- Architectural decisions
- Schema changes
- API contracts
- Specific interactions
## Testing Decisions
A list of testing decisions that were made. Include:
- A description of what makes a good test (only test external behavior, not implementation details)
- Which modules will be tested
- Prior art for the tests, that is, similar tests in the codebase
## Out of Scope
A description of the things that are out of scope for this spec.
## Further Notes
Any further notes about the feature.
```
## Rules
- **Do not include specific file paths or code snippets.**
They can become outdated quickly.
Exception: include a prototype snippet when it records a decision more precisely than prose.
Examples include a state machine, reducer, schema, or type shape.
Inline the snippet in the relevant implementation decision.
Note briefly that the snippet came from a prototype.
Trim the snippet to the decision-rich parts.
Do not include a working demo.

64
src/skills/to-document/SKILL.md
View File

@@ -1,64 +0,0 @@
---
name: to-document
description: Draft a requested summary, specification, plan, decision record, or similar document from conversation and repository context.
---
Do not start with an interview when the conversation gives a usable subject.
Ask before drafting only when the conversation lacks a usable subject.
Do not put draft contents in the chat response.
Always persist the draft to a file.
Do not implement the draft contents unless the operator gives a separate instruction.
Treat a completed draft as documentation, not an instruction to build.
## Process
1. Identify the subject.
Use the conversation as the primary source.
If the conversation lacks a usable subject, ask what the document is about.
Do not ask clarifying questions before drafting when a usable subject exists.
Finish when you have a subject or a question that requests the missing subject.
2. Gather repository facts that the draft needs.
Inspect files when repository details matter.
Do not invent modules, paths, commands, flows, contracts, or conventions.
Distinguish confirmed facts from assumptions.
Finish when each repository-specific claim has support or an explicit assumption marker.
3. Choose the document shape.
Infer the document type and title from context.
Load [DOCUMENT-FORMAT.md](DOCUMENT-FORMAT.md) when the operator requests no specific format.
Adapt the structure only when the requested document type needs different sections.
Preserve useful sections for decisions, testing, scope, and notes.
Finish when the draft has a title and section plan that fit the requested document.
4. Write the draft.
Capture known context accurately.
Mark assumptions and gaps explicitly.
Include decisions that the conversation settled.
Include open questions only as gaps, not as an interview.
Keep the document focused on the operator's problem and intended use.
Finish when the draft contains the relevant facts, decisions, assumptions, gaps, and scope.
5. Persist the draft.
Use `docs/00 INBOX/ai` as the default destination.
Use the operator's requested path when one exists.
Derive a kebab-case slug from the inferred title.
Create the destination directory when it does not exist.
If the target file exists, summarize the expected change.
Confirm before overwriting an existing file.
Do not print the draft in chat instead of writing it.
Finish when the draft is written or overwrite confirmation is pending.
6. Finish with the result.
Report the written path.
Do not include the draft contents in the response.
Do not continue into implementation without an explicit instruction.
Finish when the operator can find the written draft.