lwlee2608/agent-skills

1

ascii-diagram Use after generating or editing ASCII art, box diagrams, tables, or any monospace text art to ensure all lines, corne…

lwlee2608/agent-skills

116

2

gh-create-pr Use when creating/raising/opening/submitting a GitHub PR. Produces short, feature-focused descriptions without a test…

lwlee2608/agent-skills

94

3

prefer-make Use before running any Go toolchain command (`go build`, `go test`, `go run`, `go vet`, `go fmt`, `golangci-lint`). S…

lwlee2608/agent-skills

94

4

gh-update-pr Use when updating GitHub PR title or body. Works around the gh pr edit GraphQL bug caused by GitHub's Projects Classi…

lwlee2608/agent-skills

91

5

create-skill Use when creating a new agent skill. Ensures the skill follows quality guidelines for SKILL.md files.

lwlee2608/agent-skills

89

6

writing-system-prompts Use when writing or editing a system prompt for any LLM API or SDK (any code passing a `system=` / `system` role para…

lwlee2608/agent-skills

89

7

whiteboard-explain Use when the user asks to explain or teach a technical concept. Replies in ASD-STE100 Simplified Technical English wi…

lwlee2608/agent-skills

71

8

trim-comments Use when asked to trim, clean up, shorten, or remove code comments. Two levels — "normal" (default) shortens verbose …

lwlee2608/agent-skills

62

9

handoff Use when the user wants to condense the current conversation into a handoff document for another agent to pick up.

lwlee2608/agent-skills

58

10

review-code Use when asked to review a local diff, a GitHub PR, or a whole codebase. Reports rated findings; never edits code.

lwlee2608/agent-skills

55

11

linear Use when the user wants to interact with Linear.app — reading or searching issues/tickets.

lwlee2608/agent-skills

40

12

linear-issues Use when reading, searching, creating, updating, or commenting on Linear issues. Routes every Linear operation throug…

lwlee2608/agent-skills

40

13

plan-feature Use when planning a feature too big to hold in one session. Settles every open decision by asking the user, locks the…

lwlee2608/agent-skills

40

14

opencode-review Use when the user asks to review code/a PR with opencode or with a non-Claude model (e.g., "review with opencode", "r…

lwlee2608/agent-skills

38

15

generate-media Use when generating or editing an image or video with an AI model — ads, mockups, style variations, image-to-video. C…

lwlee2608/agent-skills

37

16

codebase-design Loads shared vocabulary and principles for designing deep modules. Invoke explicitly when designing or restructuring …

lwlee2608/agent-skills

34

17

build-feature Use when implementing a feature plan file split into phases with task checkboxes.

lwlee2608/agent-skills

29