asermax/claude-plugins

build

Build something already designed, together with the user, then verify it and offer to commit. Use when a design is agreed and the work is ready to write, or when another skill needs the shared build discipline.

原文语言：英语

codex

Load first when working with any zenku skill. Carries the vocabulary, the two rules, how to find the project's vault and conventions, and the habits for writing into it.

原文语言：英语

design

Lay out the current shape so the user can settle a new one — which modules exist, where the seams are, how data flows, and what earlier quests already decided. Use when the user wants to design a feature or a module, work out an interface, decide where a…

原文语言：英语

parley

Talk something through with the user relentlessly, round by round, until you reach a shared understanding. Use when the user wants their thinking stress-tested, says to grill or press or challenge them, or when another skill needs a decision settled by the…

原文语言：英语

sync-upstream

Sync this plugin marketplace's skills, commands, and context from their upstream source repositories (superpowers, quint-code/haft, agentic-evolve, agent-browser, dmmulroy-skills, plannotator). Use this skill whenever the user asks to "sync upstream", "pull…

原文语言：英语

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include…

原文语言：英语

systematic-debugging

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

原文语言：英语

init

Seed an Obsidian vault the project then owns, and re-run it later to add a folder, a template or a base.

原文语言：英语

commit

Analyze uncommitted changes and create grouped conventional commits.

原文语言：英语

log

Write something into the project's quest log in a few seconds — a bug, a chunk of work, a half-formed idea — without deciding anything about it. Use when the user says to note this down, add it to the backlog, capture this, or remember this for later, or when…

原文语言：英语

loot

Get everything worth keeping out of a session before it ends — decided work into the quest log, findings about how something works into a note, and anything learned about how we work into the project's own conventions. Use at the end of any zenku session, or…

原文语言：英语

lore

Write or update a durable note in the project's vault explaining how one part of the system works, following the project's own writing charter and templates. Use when the user wants something documented, a mechanism written up, a note brought back in line…

原文语言：英语

raid

Build the thing — turn cleared ground into a shape and a set of slices, then land them one per session.

原文语言：英语

solve

Close a quest out once its answer exists — write the answer on it, set its status, gist it into the adventure's solved index, and clear it from every blocked_by list that named it. Use when a question has just been answered or a slice has just been built, or…

原文语言：英语

spike

Build throwaway code to answer a design question — does this state model hold up, does this API behave, is this fast enough, what should this look like. Use when the user wants to sanity-check an approach before committing to it, or when another skill needs a…

原文语言：英语

strike

End an effort and clear it away — close out whatever is still open, carry out anything worth keeping, remove the spike worktree, and delete the effort's records. Use when an adventure has shipped or stopped being worth continuing, when a loose quest has just…

原文语言：英语

take

Take one quest and see it through in a single session — claim it, get onto the right branch, solve it by its kind, and close it out. Use when the user wants to work the next thing on an adventure, or when a dispatcher needs one session's work done against one…

原文语言：英语

travel

Travel a journey — work on something whose shape is not clear yet, mapping what stands in the way and clearing it one question per session, without building.

原文语言：英语

research

Investigate a question against high-trust primary sources and capture the findings in the project's vault. Use when the user wants a topic researched, docs or API facts gathered, reading legwork delegated, or when another skill needs a fact settled before a…

原文语言：英语

framework-core

Load when working with any katachi framework command. Provides workflow principles, status tracking conventions, and decision guidance. This skill establishes the collaborative context for all framework operations.

原文语言：英语

implement-delta

Implement a delta following its plan

原文语言：英语

commit

Create conventional commits with automatic semantic version bumps for this plugin marketplace and the affected plugin(s). Use this skill whenever the user asks to "commit", "commit my changes", "make a commit", "bump versions and commit", "ship these…

原文语言：英语

agent-communication

Use when user explicitly requests to coordinate with other Claude Code agents, join an agent chat, or communicate across multiple repositories/projects

原文语言：英语

financial-summary

Parse and analyze personal financial transaction CSV exports to calculate account totals and generate detailed breakdowns. Use when the user asks to analyze transaction data, generate financial summaries, calculate account balances, or review spending from…

原文语言：英语

hunk-review

Interacts with live Hunk diff review sessions via CLI. Inspects review focus, navigates files and hunks, reloads session contents, and adds inline review comments. Use when the user has a Hunk session running or wants to review diffs interactively.

原文语言：英语

self-maintaining-claude-md

Use when starting any task in a project - keeps CLAUDE.md instruction file current with high-level project state, prompts for init if missing, adds reflection todo before work to ensure documentation stays updated

原文语言：英语

h-abduct

INTERNAL SUBROUTINE — used by h-diagnose for parallel rival-hypothesis generation. Manual invocation possible but the right user-facing entry point is almost always h-diagnose (which uses h-abduct internally with parallel testing). Generates ≥3 typed rival…

原文语言：英语

h-boundary-unpack

INTERNAL SUBROUTINE — decomposes a boundary statement (API contract, service definition, policy text, SLA prose) into Laws / Admissibility / Deontics / Evidence quadrants per FPF A.6.B. Use only on specific boundary statements that mix statement types and…

原文语言：英语

h-commission

Creates a WorkCommission — bounded execution authority — from an active DecisionRecord. MANUAL ONLY: operator must explicitly type /h-commission. Never auto-invoked: commissions are execution-authority grants under Transformer Mandate. Runs freshness check,…

原文语言：英语

h-compare

Compares 2+ candidate variants under parity discipline and returns a Pareto front (not a scalar winner) — declares the selection policy and parity plan BEFORE scoring, then scores each dimension across all variants in parallel to prevent anchoring bias. Make…

原文语言：英语

h-decide

Records a binding DecisionRecord with full FPF DRR discipline — problem frame, decision/contract, rationale, consequences. MANUAL ONLY — the operator must explicitly type /h-decide. Never auto-invoked: per Transformer Mandate, the human principal records…

原文语言：英语

h-diagnose

Diagnoses a failure with parallel rival-hypothesis testing — multiple read-only subagents test distinct explanations in parallel, then rank by evidence weight while keeping losing rivals visible so the root cause is found honestly, not just plausibly. Make…

原文语言：英语

h-explore

Generates 3–5 genuinely distinct candidate solution variants for a framed problem — each variant differs in KIND (not just degree), carries an explicit weakest-link so weak options surface before implementation, and optionally marks stepping-stones that open…

原文语言：英语

h-frame

Frames an engineering problem before any solution is explored — stabilizes the signal, names what is actually broken, declares acceptance criteria, and records a ProblemCard. Make sure to use this skill whenever the user proposes a refactor, rewrite,…

原文语言：英语

h-note

Records a micro-decision with rationale into the haft artifact graph — lighter than a full DecisionRecord but persisted so future sessions and conflict detection can surface it. Make sure to use this skill whenever the user says "remember that", "FYI for…

原文语言：英语

h-onboard

First-setup ceremony for a project that does not yet use haft — the agent reads the repository, drafts the minimum FPF carriers (target system, enabling system, term map) from observed code/docs, and presents them to the operator for review. The operator is…

原文语言：英语

h-reason

Umbrella for FPF-style structured reasoning in a haft project. Carries the full reasoning palette in one place: framing, exploration, comparison, verification, notes, plus slideument patterns (NQD, Goldilocks, BLP, Scaling-Law Lens). Make sure to use this…

原文语言：英语

h-semio-review

INTERNAL SUBROUTINE — semiotic / fanout audit on a concept rename, deprecation sweep, or doc-vs-code consistency check. Walks all carriers (filenames, manifests, stale refs, review surfaces, dashboards, prompts) until fixed-point clean, because one-shot text…

原文语言：英语

h-spec-cover

Surfaces uncovered files in modules that already have recorded decisions — highlights drift before it accumulates and suggests where new decisions are needed. Make sure to use this skill whenever the user asks "is X documented", "what's covered", "spec…

原文语言：英语

h-status

Project state dashboard for haft — read-only consolidation of active problems, pending decisions, refresh-due artifacts, open work commissions, recent notes, and module coverage. Make sure to use this skill whenever the user asks "where are we", "what's…

原文语言：英语