ohyeh/agent-scripts

1

delegation-templates Fill-in-the-blank prompt templates for delegating work to subagents or tmux workers - SEARCH/LOCATE, IMPLEMENT, REFAC…

ohyeh/agent-scripts

165

2

using-design-skills Which design skill, in what order. Invoke BEFORE any visual output: web page, landing page, dashboard, product UI, mo…

ohyeh/agent-scripts

160

3

using-workflows Which workflow recipe runs this. Invoke BEFORE any of: audit (docs vs code, design vs code, root cause, project direc…

ohyeh/agent-scripts

158

4

unknowns-discovery Find the map/territory gap BEFORE it gets expensive. Invoke when starting a non-trivial task in unfamiliar territory …

ohyeh/agent-scripts

150

5

using-skills Which skill owns this task. Invoke BEFORE doing by hand any of: merge or rebase conflict, .pdf read or fill, Renovate…

ohyeh/agent-scripts

150

6

shared-memory-intake Curate shared Codex memory when Claude submits findings or Codex reviews, promotes, or maintains task memory.

ohyeh/agent-scripts

135

7

ask-nova Interview-driven flow picker. Use when the user is unsure which skill/flow/pipeline fits — new project kickoff, cross…

ohyeh/agent-scripts

124

8

writing-artifacts Turn a fuzzy subject — a problem description, an incident, a decision, a long-form idea — into a polished deliverable…

ohyeh/agent-scripts

108

9

defect-first-review Perform a read-only, defect-first review of a specified code change and return every actionable finding, reading the …

ohyeh/agent-scripts

53

10

session-handoff Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests ha…

ohyeh/agent-scripts

37

11

using-grok-bot-app Read and drive the "Grok Bot" macOS desktop app (an Electron app) over CDP with agent-browser — list its bots and fol…

ohyeh/agent-scripts

22

12

second-model-consensus Run a bounded cross-model consensus loop — a fresh second-model reviewer (Codex Sol, agy Gemini, or another Claude) a…

ohyeh/agent-scripts

12

13

batch-grill-me A relentless interview that asks every frontier question at once, round by round.

ohyeh/agent-scripts

5

14

design-an-interface Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants t…

ohyeh/agent-scripts

5

15

edit-article Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to …

ohyeh/agent-scripts

5

16

migrate-to-shoehorn Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to…

ohyeh/agent-scripts

5

17

obsidian-vault Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, c…

ohyeh/agent-scripts

5

18

qa Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explore…

ohyeh/agent-scripts

5

19

request-refactor-plan Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user w…

ohyeh/agent-scripts

5

20

wizard Generate an interactive bash wizard that walks a human through a manual procedure — third-party setup, a one-off migr…

ohyeh/agent-scripts

5

21

writing-beats Writing, exploit — assemble raw material into a journey of beats, grounding each term before a beat leans on it.

ohyeh/agent-scripts

5

22

writing-fragments Writing, explore — mine raw fragments, no structure yet.

ohyeh/agent-scripts

5

23

writing-shape Writing, exploit — shape raw material into an article, paragraph by paragraph.

ohyeh/agent-scripts

5

24

canary-source-proof Internal canary skill used only to prove that the `npx skills` add/list/update/remove lifecycle works correctly again…

ohyeh/agent-scripts

1