zprolab/WhaleKit

Superpowers customized for DeepSeek Harness

2Stars on the repository
22Mods indexed here, across every type
20d agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

adversarial-review

01

zprolab/WhaleKit

Skill Claude CodeCodex

Use when a decision affects a final implementation conclusion, may shift technical direction, or fixes an architecture-level bug.

not rated 2 20d ago A 26 tokens

zprolab/WhaleKit

Skill Claude CodeCodex

Use when a design or build task begins and user requirements must be clarified into verified conclusions before any design or implementation work.

not rated 2 20d ago A 28 tokens

commit

03

zprolab/WhaleKit

Skill Claude CodeCodex

Use when starting implementation work on a task, or when the user asks you to commit changes to the repository.

not rated 2 20d ago A 23 tokens

decision-approval

04

zprolab/WhaleKit

Skill Claude CodeCodex

Use when the user waives a decision (you decide / whatever / don't ask me) and open decisions must be resolved through a draft sheet the user approves or edits before they take effect.

not rated 2 20d ago A 41 tokens

dispatching-agents

05

zprolab/WhaleKit

Skill Claude CodeCodex

Use when delegating work to one or more subagents - any task whose recipient needs a self-contained brief instead of your session's context or history.

not rated 2 20d ago A 34 tokens

dual-records

06

zprolab/WhaleKit

Skill Claude CodeCodex

Use when a directory under development is routed to tier L5 Full.

not rated 2 20d ago A 17 tokens

executing-plans

07

zprolab/WhaleKit

Skill Claude CodeCodex

Use when you have a written implementation plan to execute in a separate session with review checkpoints.

not rated 2 20d ago A 22 tokens

zprolab/WhaleKit

Skill Claude CodeCodex

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.

not rated 2 20d ago A 38 tokens

zprolab/WhaleKit

Skill Claude CodeCodex

Use when completing tasks, implementing major features, or before merging to verify work meets requirements.

not rated 2 20d ago A 22 tokens

routing

11

zprolab/WhaleKit

Skill Claude CodeCodex

Use when selecting process depth for a task.

not rated 2 20d ago A 10 tokens

zprolab/WhaleKit

Skill Claude CodeCodex

Use when starting creative work - creating features, building components, adding functionality, or modifying behavior.

not rated 2 20d ago A 25 tokens

zprolab/WhaleKit

Skill Claude CodeCodex

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

not rated 2 20d ago A 21 tokens

zprolab/WhaleKit

Skill Claude CodeCodex

Use when a non-trivial task needs understanding of a fixed target (module, file, question, or whole project) before process selection.

not rated 2 20d ago A 33 tokens

zprolab/WhaleKit

Skill Claude CodeCodex

Use when implementing any feature or bugfix, before writing implementation code.

not rated 2 20d ago A 17 tokens

using-git-worktrees

17

zprolab/WhaleKit

Skill Claude CodeCodex

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback.

not rated 2 20d ago A 36 tokens

using-whalekit

18

zprolab/WhaleKit

Skill Claude CodeCodex

Use when starting any conversation - establishes how to find and use WhaleKit skills, requiring skill invocation before ANY response including clarifying questions.

not rated 2 20d ago A 31 tokens

zprolab/WhaleKit

Skill Claude CodeCodex

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.

not rated 2 20d ago A 43 tokens

zprolab/WhaleKit

Skill Claude CodeCodex

Use when starting a conversation after using-whalekit - the canonical global conventions binding all agents: plain language, user gold standard, commit consent, doc chain, parking, iron-law gates.

not rated 2 20d ago A 43 tokens

writing-plans

21

zprolab/WhaleKit

Skill Claude CodeCodex

Use when you have a spec or requirements for a multi-step task, before touching code.

not rated 2 20d ago A 21 tokens

writing-skills

22

zprolab/WhaleKit

Skill Claude CodeCodex

Use when creating new skills, editing existing skills, or verifying skills work before deployment - skill TDD: pressure scenarios, unaware subagents, fail-then-fix-then-pass loops.

not rated 2 20d ago A 41 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: