Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion skills/do-refactor/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
name: do-refactor
description: Execute a refactoring epic on a single branch, implementing all issues sequentially with CI verification after each. Use when user types /do-refactor or asks to execute a refactoring plan.
model: claude-opus-4-6
model: opus
argument-hint: "BT-XXX (epic ID)"
allowed-tools: Bash, Read, Write, Edit, Grep, Glob, Agent
---
Expand Down
2 changes: 1 addition & 1 deletion skills/draft-adr/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
name: draft-adr
description: Research a problem and draft an Architecture Decision Record. Use when user asks to design/draft/write an ADR or make an architectural decision.
model: claude-opus-4-6
model: opus
argument-hint: "[problem or decision topic]"
allowed-tools: Bash, Read, Write, Edit, Grep, Glob, Agent, WebSearch
---
Expand Down
2 changes: 1 addition & 1 deletion skills/linear/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
name: linear
description: Manage Linear issues. Use when asked about tasks, tickets, bugs, or Linear.
model: claude-haiku-4-5-20251001
model: haiku
---

# Linear
Expand Down
2 changes: 1 addition & 1 deletion skills/pick-epic/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
name: pick-epic
description: Execute an epic by running children in dependency-ordered waves using parallel subagents, one isolated worktree and PR per issue, squash-merging as CI and automated reviews (CodeRabbit + Copilot) pass. Use when user types /pick-epic or asks to execute an epic with parallel agents.
model: claude-opus-4-6
model: opus
argument-hint: "BT-XXX (epic ID)"
allowed-tools: Bash, Read, Write, Edit, Grep, Glob, Agent
---
Expand Down
2 changes: 1 addition & 1 deletion skills/plan-refactor/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
name: plan-refactor
description: Analyze the codebase and plan refactoring for code quality and maintainability. Use when user types /plan-refactor or asks to plan refactoring work.
model: claude-opus-4-6
model: opus
argument-hint: "[scope: crate name, layer, or 'all']"
allowed-tools: Bash, Read, Grep, Glob, Agent
---
Expand Down
2 changes: 1 addition & 1 deletion skills/resolve-merge/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
name: resolve-merge
description: Update main branch, merge into current branch, and resolve conflicts. Use when user types /resolve-merge or asks to merge main/resolve conflicts.
model: claude-haiku-4-5-20251001
model: haiku
---

# Merge Resolve Workflow
Expand Down
2 changes: 1 addition & 1 deletion skills/review-adr/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
name: review-adr
description: Review an Architecture Decision Record for completeness, correctness, and quality. Use when user types /review-adr or asks to review an ADR.
model: claude-opus-4-6
model: opus
argument-hint: "[ADR file path or number]"
allowed-tools: Bash, Read, Write, Edit, Grep, Glob, Agent, WebSearch
---
Expand Down
4 changes: 2 additions & 2 deletions skills/review-code/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
name: review-code
description: Review current branch changes vs main. Use when user types /review-code or asks for a code review of their changes.
model: claude-opus-4-6
model: opus
---

# Code Review Workflow
Expand Down Expand Up @@ -166,7 +166,7 @@ Use CodeRabbit AI and a different model family to challenge the design with fres

16. **Launch adversarial model review** using the task tool with a model from a **different family** than your own. If you're Claude, use GPT; if you're GPT, use Claude:

Launch via `task` with `agent_type: "general-purpose"` and `model: "gpt-5.2-codex"` (or `model: "claude-opus-4.6"` if you're a GPT model):
Launch via `task` with `agent_type: "general-purpose"` and `model: "gpt-5.2-codex"` (or `model: "opus"` if you're a GPT model):

```
You are a skeptical senior engineer reviewing a PR. Your job is to find
Expand Down
2 changes: 1 addition & 1 deletion skills/update-issues/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
name: update-issues
description: Find and update Linear issues that need labels, blocking relationships, or metadata. Use when user says '/update-issues' with criteria like 'no labels', 'missing agent-ready', 'needs size', etc.
model: claude-haiku-4-5-20251001
model: haiku
---

# Update Issues Automatically
Expand Down
2 changes: 1 addition & 1 deletion skills/whats-next/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
name: whats-next
description: Find the next logical piece of work. Use when user types /whats-next or asks what they should work on next, or wants recommendations for the next task.
model: claude-haiku-4-5-20251001
model: haiku
allowed-tools: Bash, Read, Grep, Glob
---

Expand Down
Loading