csark0812/toolbox

1

second-opinion Adversarial critique of a written artifact through task-specific lenses and claim anchoring. Single-agent by default;…

csark0812/toolbox

58

2

handoff Agent-to-agent cross-session transfer — pointers not bodies. Channel prompt (user /handoff) or artifact (model-invoke…

csark0812/toolbox

57

3

code-review Review code through a user-named surface and lens. Use for focused risk checks, ordinary code review, prior-finding c…

csark0812/toolbox

56

4

grill Clarify fuzzy intent and pressure-test design choices through focused dialogue before implementation. Use when the us…

csark0812/toolbox

56

5

crystallize Shape a fuzzy or half-formed idea through Socratic dialogue — crystallized intent, not solutions or a plan yet. Use w…

csark0812/toolbox

38

6

multi Parallel subagent orchestration kernel — spawn invariants, model routing, generic prompts and synthesis. Entry skills…

csark0812/toolbox

38

7

investigate Narrow a specific hunch — settle it with primary-source evidence and a plain-language verdict. Find and verdict only.…

csark0812/toolbox

37

8

domain-model Persist glossary entries and ADRs after a term or decision is ready. Process skill. Not open design dialogue.

csark0812/toolbox

24

9

prototype Create a throwaway logic, state, or UI artifact that answers one design question. Not production test-first implement…

csark0812/toolbox

24

10

tdd Test-first build at agreed public seams, one red-green slice at a time. Process skill. Not repro-first hard-bug work …

csark0812/toolbox

24

11

probe Narrow a hunch or hard bug through evidence and a pragmatic-STE verdict. Fix only with explicit authority and an on-d…

csark0812/toolbox

19

12

review-walkthrough Bind a code change and explain it through the smallest useful causal story. Use when a user wants to understand stage…

csark0812/toolbox

14

13

council Multi-agent orchestrator that creates task-specific personas, selects a useful interaction pattern, runs real indepen…

csark0812/toolbox

12

14

subagents Agent-to-agent spawn — subagent_type, extremely token-efficient splits (≤100k total context), context-pack envelopes,…

csark0812/toolbox

10

15

refactor-companion Preserve a developer's target design through evidence-led, proven refactor slices. Use for existing-code replacement,…

csark0812/toolbox

9

16

writing-great-skills Skill-authoring vocabulary and predictability principles — progressive disclosure, leading words, failure modes.

csark0812/toolbox

9

17

diagnose Hard-bug diagnosis loop — repro → tighten feedback loop → fix → regression lock. Use when something is broken, throwi…

csark0812/toolbox

8

18

iterate Agent-to-agent pass loop — iterative blind review subagent passes until a bounded code or plan section holds together…

csark0812/toolbox

8

19

branch-cleanup Inventory and clean merged or stale git branches (local + remote) and unused worktrees; flag branches with unique com…

csark0812/toolbox

2

20

debug Bug localization and Cursor debug-mode instrumentation across PostPrint. Use when the owning layer is unknown, NDJSON…

csark0812/toolbox

2

21

domain-modeling Sharpen overloaded business/domain terms against docs/domain/glossary.md, challenge conflicting user language, and up…

csark0812/toolbox

2

22

product-principles PostPrint product philosophy router and decision framework. Use when deciding whether to build a feature, evaluating …

csark0812/toolbox

2

23

pull-request PR description generation from diff. Use when user asks for PR description, document changes, or write the PR body. F…

csark0812/toolbox

2

24

refine-agent-work Judge agent-created work against the developer's preferences, record ownership decisions, and refine accepted changes…

csark0812/toolbox

2

25

testing Write, fix, and run tests across all layers — E2E (Playwright), integration (Vitest), unit (Vitest/pytest). Use when …

csark0812/toolbox

2