asermax
- 151 skills
- 0 followers
- 3 repo stars
- 6 days ago last updated
- ▌
- ▌ Prototype · asermax bundleLoaded by other skills to show the user a screen element, or the options for a piece of the visual direction (palette, icons, logo, fonts), as a working HTML prototype and iterate it with them, round by round, until it matches what they want. Carries how the file is built and opened, and one reference per variant for how its rounds run. The loading skill says what the prototype is of and which decisions it stands for.
- ▌ Explore · asermaxUser-guided investigation mode. The user provides context to use as the basis and then steers the investigation one question at a time. The agent reads only that context up front and, for each question, dispatches a scout at exactly what the question needs. Use when the user wants to build their own understanding of a problem before defining a change. Not for producing a report, a plan or a scope.
- ▌ Commit 2 · asermaxCreate 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 changes", or otherwise wants to create one or more commits in this marketplace repo. Prefer this skill over a plain `git commit` because it groups related files, derives scopes, proposes semver bumps for both the marketplace and any affected plugin's `plugin.json`, and uses conventional commit format with reasoning the user can validate.
- ▌ Spike · asermax bundleAnswer a design question by building the smallest working version of the real thing and running it against reality. Throwaway code that never merges. Use when a question cannot be settled by reading or asking, like "will this work?" or "what shape should this be?", and only running code can answer it. For a UI element a human reacts to, use prototype instead.
- ▌ Basics · asermaxFoundation for every mahou skill. Carries the philosophy and rules the agent follows when running any mahou skill. Load before running any other mahou skill.
- ▌ Design · asermax bundleTurns a settled problem definition into a system design. Works a design tree one area at a time, from data model to flows to rules, with the user settling every leaf. Hands the tree to mahou:write-documentation so the project's docs record it. Stays above endpoints, functions and files. Use after shape, before mahou:program-design.
- ▌ Learn · asermax bundleThe author's tool for growing the plugin from real sessions. When the user asks what the session has to teach, it collects the points where the session generated friction or changed the behavior of the flow that was running, gives a take on each, and drafts what the user picks. When the user names what to build, it works that ask directly from the current context. A mixed ask gets both. Produces new or iterated skills, agents, wiki entries and local .mahou files.
- ▌ Shape · asermaxFinds the holes in a problem and solution definition and fills them with questions, working a design tree in rounds until nothing is left assumed. Stays at the level of behavior and decisions, never implementation. Use after the user has explored a problem and settled its first decisions, and before any design or plan is written.
- ▌ Init · asermax bundleLoad mahou:basics first, then mahou:docs. Then read `.mahou/init.md` if present.
- ▌ Guide · asermaxEntrypoint to the mahou plugin when unsure which skill fits. Give it your goal in plain words and it identifies the matching skill and activates it with your request as context.
- ▌ Docs · asermaxLoaded by skills and agents that read or write the project's own documentation. Carries how to find the docs folder, what its structure is made of, and the rule that the project's charter wins over anything a skill assumes.
- ▌ Systematic Debugging · asermax bundleUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes
- ▌ Agent Communication · asermax bundleUse when user explicitly requests to coordinate with other Claude Code agents, join an agent chat, or communicate across multiple repositories/projects
- ▌ Write Documentation · asermaxWrite or update a note in the project's docs folder explaining how one part of the system works, following the project's own charter and templates. Use when the user wants something documented, a mechanism written up, a note brought back in line with the code, or when mahou:design hands over a settled tree to record.
- ▌ Show Markdown · asermax bundleUse when you need to display a considerable amount of markdown content, or the user asks to display markdown in a browser, preview markdown files, or render markdown with styling. Trigger on requests like "show this markdown", "preview markdown", "display markdown in browser", "open markdown in browser", or any task requiring visual markdown rendering.
- ▌ Commit Changes · asermaxCommits the changes in the repository as conventional commits, grouping related files and confirming the grouping with the user before anything is committed. Use when the user asks to commit, or when another mahou skill reaches its commit step.
- ▌ Sync Upstream · asermaxSync this plugin marketplace's skills, commands, and context from their upstream source repositories (superpowers, quint-code/haft, agentic-evolve, agent-browser, dmmulroy-skills, cursor-plugins). Use this skill whenever the user asks to "sync upstream", "pull upstream", "refresh skills from upstream", "update plugins from their source repos", or mentions wanting to pick up changes from `~/workspace/random/superpowers`, `~/workspace/random/quint-code`, `~/workspace/random/agentic-evolve`, `~/workspace/random/agent-browser`, `~/workspace/random/dmmulroy-skills`, or `~/workspace/random/cursor-plugins`. Trigger even when the user uses paraphrases like "let's see what's new upstream" or "pull the latest into the marketplace".
- ▌ Code Blast Radius · asermaxTraces what an already-written change reaches. Fans out a tracer per changed element, proves the one fact the change is safe because of by running the real code, and reports only the places where behavior changes for someone, each with how far its proof got. Use after code is written, before it is reviewed or merged.
- ▌ Human Review · asermaxCollects the user's own annotations on a change, verifies each against the code, and settles every finding with them before anything is edited.
- ▌ Unslop · asermaxCut AI tells from prose meant to be read as a document. Use when writing or editing documentation, READMEs, design notes, wiki entries, specs, PR descriptions or similar long-form text, and when another skill asks for a writing pass. Do not apply to code, chat replies or short answers.
- ▌ Agentic Review · asermaxRefines the code in a change before a human reads it. Runs four facet reviewers, a test reviewer when the change touches tests, and one conventions reviewer per wiki entry and per project rule file on each repository, fixes what they find without changing how the change looks or behaves, and repeats for up to three rounds. Typed by the user, or invoked by mahou:implement once a repository's code lands.
- ▌
- ▌ Canvas · asermax bundleDraws on a tldraw canvas run from a local app, which the user edits too, with low-fidelity screen mockups, storage cylinders, arrows and free text, and exports it as an SVG. Use when the user asks for a mockup, a sketch or a diagram laid out in space, or when another skill loads it to draw. Mermaid stays the choice for diagrams that live as text in a document, such as sequence, state, ER and flowcharts.
- ▌ Lookup · asermaxLoaded by other skills that need a fact from the project's code, its docs or the outside world while working with the user. Carries the routing between the scouts and the researcher, the rule for facts outside the project, and how a verified fact is told apart from an asserted one.
- ▌ Rebase · asermaxBrings a branch up to date with its base by fetching, rebasing, resolving, and verifying, then reports what moved. Never pushes.
- ▌
- ▌ Validate · asermax bundleRuns a change's manual validation rows against the running system and leaves an evidence report. Takes the manual rows from mahou:test-design, or the scenarios the user names when there is no test design, drives each one through a browser, over HTTP, or on an Android device, records what it observed with before and after state, fixes a failing row when the fix only makes the code do what previous decisions settled, and reports every other failure and every bug outside the rows without fixing it. Use after the tests are green, before human-review, or whenever the user asks to see a change working.
- ▌ Implement · asermaxLoad mahou:basics first. Then read `.mahou/implement.md` if present: it is where a project names its task tracker, the tool that reaches it and the states a task moves through. Follow the wiki indexes only far enough to know which entries exist; the subagents read the entries for the code they touch.
- ▌ Telepathy · asermax bundleMoves the conversation with the user out of the chat and into markdown files in the change's scratch folder, served as a web page the user reads and edits in the browser. Every edit the user makes reaches the agent as a message, and the agent answers by writing in the files. Use when the user asks for telepathy, asks to talk through files or the browser instead of the chat, or asks to continue a session there.
- ▌ Fast Track · asermaxRuns a canvas stage skill (shape-with-canvas, design-with-canvas, program-design-with-canvas, test-design-with-canvas) in fast-track mode. Every branch and part is laid out at once, decisions that earlier artifacts already show become settled leaves without a confirmation round, and only the open decisions are asked. Use when the user asks for a fast track, or asks for a canvas stage with no confirmations and every branch at once. Once on, it holds for every canvas stage run in the same session.
- ▌ Land · asermax bundleTakes a change from its branches to merged pull requests across one or more repositories, in the order that keeps production safe. Runs release-check first, opens every pull request, babysits them in parallel through review and rebase until they are merged, then walks the confirmed order, watching each merge's CI run and waiting for the user's production confirmation before the next; the release follows each project's own process. Use when the code is written, reviewed locally and ready to ship.
- ▌
- ▌ Design With Canvas · asermax bundleRuns the design skill on a canvas instead of in the chat. The canvas is the design tree, one section per branch with its leaves, its representation and its prose; questions, findings and readings are written on it, and the user answers with sticky notes. The recording at the end stays in the chat. Use when the user wants to design a system on a canvas.
- ▌ Implement With Tdd · asermaxImplements a change whose design and test design are settled the way mahou:implement does, but writes each repository's code test first. Per repository, a tester subagent writes the failing tests and validates each round, an implementer subagent writes the code, and this session relays every exchange between them. Use after test-design, before human-review, when the code should be written test first.
- ▌ Create Pull Request · asermaxLoad mahou:basics first. Then read `.mahou/create-pull-request.md` if present.
- ▌ Explore With Canvas · asermax bundleRuns the explore skill on a canvas instead of in the chat. The user asks with sticky notes, the skill lays out the answers freely on the canvas with their facts and diagrams, and a decision log grows in one place. Use when the user wants to build their understanding of a problem on a canvas.
- ▌ Test Design With Canvas · asermaxRuns the test-design skill on a canvas instead of in the chat. The candidate roots are drawn on a map of the system for the user to pick, and each branch is drawn as a classification tree with its combination matrix under it; the user corrects with sticky notes or by voice. Use when the user wants to design the test cases and manual validations of a settled change on a canvas.
- ▌ Architecture Exploration · asermax bundleDraws a system's architecture on a canvas and explores ways to change it with the user. It lays the options out side by side, draws a part they share step by step, and redraws the whole chosen option after each decision the user makes, until one architecture remains. The user edits the same canvas. Use when the user wants to see which parts a system has and how they connect, or to compare options for changing them before a design is settled. For a settled design drawn as one page, use mahou:one-page-design.
- ▌ Program Design With Canvas · asermax bundleRuns the program-design skill on a canvas. Each part of a branch (screen layout, component tree, state) is drawn on the canvas for the user to correct, while the record file keeps the text representation. Use when the user wants to work a program design on a canvas.
- ▌ Implementation Status Report · asermaxReports where an implement run stands, from the change's implementation-status.md. Gives, per repository, a short update against the previous report in the conversation, the highlights since then, and every open item with the context to settle it. Use in the middle of an implement or implement-with-tdd run, and at its end, where implement loads it for the final report.
- ▌ Test Design · asermaxLoad mahou:basics first, then mahou:design-tree, taking from it the tree format and its marks only; the mechanics here are different and stated below. Then read `.mahou/test-design.md` if present. Follow the wiki indexes to the testing entries for the runners the repositories use, and read each repository's own testing conventions where the project keeps them, usually its `AGENTS.md`: they decide the test level and the naming rule the rows follow.
- ▌ Release Check · asermaxFinds what breaks when the repositories of a change are released in a given order, and gives the order that breaks nothing. Compares each branch with the deployed version on both sides of every service boundary, including services the change does not touch, and runs code-blast-radius alongside. Use before opening the pull requests of a change that touches more than one repository, or one that other services or a distributed client depend on.
- ▌ Mermaid · asermax bundleLoaded to choose, write, style and validate mermaid diagrams (flowcharts, sequence, state, ER and class diagrams). Diagrams are drawn with pele (pele.run), which reads mermaid syntax. Carries a chart-selection table, one reference per chart type with a default shape and colour palette, the common syntax rules, a bundled pele validator and renderer, and the rendering rules the validator cannot catch. Use whenever you generate, write or edit a mermaid code block, and validate every diagram before showing it, even one that looks correct.
- ▌ Program Design · asermax bundleTurns a settled system design, or a change proposed in the conversation, into a program design, the level between the design and the code. Works a design tree one repository at a time, proposing each branch's layout, components, state, call path, interfaces and files from the code and the conventions, and settling them with the user one part at a time. Every part is a representation, never code. Use after design, before implementation.
- ▌ Validate Setup · asermaxWrites and keeps up `.mahou/validate.md`, the file mahou:validate reads to bring a project's system up, drive it, capture evidence and clean up, with one file per feature under `.mahou/validate/features/`. Learns each part from the repository, asks only what the repository does not show, and proves the file by driving one feature end to end. Re-run on an existing file to check it against the repository and a live pass. Use when a project has no `.mahou/validate.md`, or when validation keeps stumbling on how the system runs.
- ▌ One Page Design · asermax bundleDraws a settled design as one page on a canvas, as a journey (what the user sees step by step, what gets stored on the way and how it is read back) or as an anatomy (what one thing is made of and where each of its parts comes from). The user edits the same canvas. Exports it as an SVG. Use when the user asks for a one-page design.
- ▌ Address Pr Review · asermaxWorks the review left on an open pull request. Fetches the live threads, verifies each finding against the code, settles them with the user, applies what they approve, then commits, pushes and resolves the threads. Use when a reviewer, a person or a bot, has commented on a PR. Typed by the user, or run by mahou:land when a review arrives.
- ▌ Shape With Canvas · asermax bundleRuns the shape skill on a canvas instead of in the chat. The canvas is the shape tree, one section per branch with its leaves and its prose; questions, findings and readings are written on it, and the user answers with sticky notes. Once every branch is settled, the skill draws a breadboard of the places a person moves through to check the connections between the leaves. Use when the user wants to settle the open decisions of a problem and solution definition on a canvas.
- ▌ Sync With Filadd · asermaxSync the mahou plugin with the Filadd marketplace's experimental-dev plugin in both directions, plus the few dev and docs skills that pair with mahou or superpowers ones. The two plugins share a base but diverge on purpose, so the skill lists what can move each way, waits for the user to pick, and ports each item generalized for the side it lands on. Use when the user asks to "sync with filadd", "sync to filadd", "sync with experimental-dev", "sync mahou with filadd", "bring the filadd changes over" or "port this back to filadd".
- ▌ Commit 4 · asermaxBump the plugin version, decide whether the change warrants README/CLAUDE.md updates, commit the change (feature files + bump together) as a single conventional-commits commit, then push. Use when the user asks to "commit", "ship", "bump and push", or "land" the current working-tree changes.
- ▌ H Note 2 · asermaxPersist a fact, observation, caveat, or small non-binding rationale in Haft project memory when the operator explicitly asks or current Work supplies a concrete operator-named or agent-inferred receiving use that needs a lightweight addressable fact. Use for "remember this", "запиши", or "note for later". Do not auto-persist ordinary reasoning. A note is not a choice, ProblemCard, evidence verdict, approval, or WorkPlan.
- ▌ H Spec 2 · asermaxManage Haft's typed specification lifecycle and source-currentness repair: inspect current SpecSections, draft or clarify carriers, classify FPF semantic fanout, record operator-requested spec changes, and cross explicit approve/rebaseline/reopen gates only with human authorization. Use for "spec status", "update specs", "запиши в спеки", stale spec sections, newer FPF source revisions, or semantic changes that must be repaired across several spec carriers. Treat markdown as a carrier and the kernel projection as the lifecycle contract. Use h-status for read-only module/file coverage and h-onboard for first bootstrap.
- ▌ H Frame 2 · asermaxShape an engineering problem without assuming a solution or forcing a project phase. Use when a redesign, refactor, or proposal arrives before the affected object, observed signal, constraints, unresolved relation, and acceptance basis are clear. Default to a conversational frame; record a ProblemCard only on explicit save intent or when current Work supplies a concrete operator-named or agent-inferred receiving use that needs a durable accepted problem statement. Prefer h-diagnose for a concrete failure with unclear cause.
- ▌ H Decide 2 · asermaxRoutes one direct, unambiguous operator request to bind a bounded choice as a DecisionRecord. Use when the operator asks to decide, bind, or supersede a choice; h-frame, h-explore, and h-compare are independent capabilities, not mandatory phases.
- ▌ H Reason 2 · asermaxSource-first umbrella for FPF-aware reasoning in a Haft project. Use when the operator asks to think through an ambiguous engineering, management, architecture, specification, or project question without naming a narrower Haft capability. Recover the current object and question, query the bundled FPF source, inspect the governing pattern body, and choose only the capability that is current. Ordinary reasoning stays conversational; proactively persist the minimum needed memory when current Work supplies a concrete durable receiving use. h-decide may route a direct operator request; h-commission remains manual-only.
- ▌ H Status 2 · asermaxRead-only Haft project cockpit for active problems, decisions, notes, evidence freshness, drift, commissions, spec lifecycle, module decision coverage, and bounded exact file-link gaps from a current code index. Use for project status, session resumption, "what is decision-linked", "what is uncovered", or "what needs attention". This skill reports current graph state and drill-downs; it does not mutate artifacts, infer a project phase, or prescribe a universal next step.
- ▌ H Verify 2 · asermaxVerifies that a recorded DecisionRecord still holds — baseline-vs-measure evidence loop with drift detection per FPF Evidence Decay. Make sure to use this skill whenever the user asks "did dec-X work", "is decision Y still valid", "did the prediction come true", "check if the migration held", "is X stale", "measure that decision against reality", "did we actually fix Z", "is our caching decision still right" — or whenever a shipped decision needs a post-implementation reality-check before further work relies on it. Also use when /h-status surfaces a refresh-due decision. NOT for ad-hoc sanity checks (just run the tests directly). NOT for re-framing the underlying problem (use h-frame).
- ▌ H Compare 2 · asermaxCompare two or more existing candidates under an explicit characteristic space, parity basis, and predeclared selection policy. Return constraints, trade-offs, and a non-dominated set rather than hiding the choice in one score. This skill is independent of h-frame and h-explore. Default to a conversational comparison; persist comparison artifacts only on explicit save intent or when current Work supplies a concrete operator-named or agent-inferred receiving use that needs replay. A binding choice requires a direct unambiguous operator request routed through h-decide.
- ▌ H Explore 2 · asermaxGenerate 3-5 genuinely distinct candidate approaches for a current question, with the weakest link of each kept visible. Use when alternatives are needed or one favored approach is prematurely closing the search. This skill is independent: it may work from an inline question, cue, accepted problem, or other current basis. Default to conversational candidates; persist a SolutionPortfolio only on explicit save intent or when current Work supplies a concrete operator-named or agent-inferred receiving use that needs replay.
- ▌ H Onboard 2 · asermaxBootstrap Haft through one readable onboarding surface, prepare an initial profile review or one bounded existing-scope relation change, and orient applicable specification carriers. Use for first-time setup, incomplete setup, or profile-underdetermined spec recovery. Project memory is ready immediately after haft init. Status and repository detection are read-only; all reviewed profile effects and specification lifecycle gates remain explicit human acts.
- ▌ H Diagnose 2 · asermaxDiagnose a concrete failure with parallel rival-hypothesis testing. Use when symptoms are observable but cause is unclear. Stabilize the signal, generate distinct explanations, test them read-only in parallel, and rank by evidence while keeping losing rivals visible. This skill is independent and ordinarily non-persistent; save a diagnosis frame or hypothesis portfolio only on explicit request or when current Work supplies a concrete operator-named or agent-inferred receiving use that needs replay.
- ▌ H Commission 2 · asermaxCreates 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, scope check, derives an ImplementationPlan, snapshots the autonomy envelope, then STOPS before execution. NOT for the decision itself (use /h-decide first). NOT for running tests or one-off tasks (the operator's coding agent handles those directly).
- ▌ Plannotator Last 2 · asermaxOpen Plannotator on the latest rendered assistant message and use the returned annotations to revise that message or continue.
- ▌ Plannotator Review 2 · asermaxOpen Plannotator's browser-based code review UI for the current worktree or a pull request URL, then act on the feedback that comes back.
- ▌ Plannotator Annotate 2 · asermaxOpen Plannotator's annotation UI for a markdown file, HTML file, URL, or folder and then respond to the returned annotations.
- ▌ H Note · asermaxPersist a fact, observation, caveat, or small non-binding rationale in Haft project memory when the operator explicitly asks or current Work supplies a concrete operator-named or agent-inferred receiving use that needs a lightweight addressable fact. Use for "remember this", "запиши", or "note for later". Do not auto-persist ordinary reasoning. A note is not a choice, ProblemCard, evidence verdict, approval, or WorkPlan.
- ▌ H Spec · asermaxManage Haft's typed specification lifecycle and source-currentness repair: inspect current SpecSections, draft or clarify carriers, classify FPF semantic fanout, record operator-requested spec changes, and cross explicit approve/rebaseline/reopen gates only with human authorization. Use for "spec status", "update specs", "запиши в спеки", stale spec sections, newer FPF source revisions, or semantic changes that must be repaired across several spec carriers. Treat markdown as a carrier and the kernel projection as the lifecycle contract. Use h-status for read-only module/file coverage and h-onboard for first bootstrap.
- ▌ H Frame · asermaxShape an engineering problem without assuming a solution or forcing a project phase. Use when a redesign, refactor, or proposal arrives before the affected object, observed signal, constraints, unresolved relation, and acceptance basis are clear. Default to a conversational frame; record a ProblemCard only on explicit save intent or when current Work supplies a concrete operator-named or agent-inferred receiving use that needs a durable accepted problem statement. Prefer h-diagnose for a concrete failure with unclear cause.
- ▌ H Decide · asermaxRoutes one direct, unambiguous operator request to bind a bounded choice as a DecisionRecord. Use when the operator asks to decide, bind, or supersede a choice; h-frame, h-explore, and h-compare are independent capabilities, not mandatory phases.
- ▌ H Reason · asermaxSource-first umbrella for FPF-aware reasoning in a Haft project. Use when the operator asks to think through an ambiguous engineering, management, architecture, specification, or project question without naming a narrower Haft capability. Recover the current object and question, query the bundled FPF source, inspect the governing pattern body, and choose only the capability that is current. Ordinary reasoning stays conversational; proactively persist the minimum needed memory when current Work supplies a concrete durable receiving use. h-decide may route a direct operator request; h-commission remains manual-only.
- ▌ H Status · asermaxRead-only Haft project cockpit for active problems, decisions, notes, evidence freshness, drift, commissions, spec lifecycle, module decision coverage, and bounded exact file-link gaps from a current code index. Use for project status, session resumption, "what is decision-linked", "what is uncovered", or "what needs attention". This skill reports current graph state and drill-downs; it does not mutate artifacts, infer a project phase, or prescribe a universal next step.
- ▌ H Verify · asermaxVerifies that a recorded DecisionRecord still holds — baseline-vs-measure evidence loop with drift detection per FPF Evidence Decay. Make sure to use this skill whenever the user asks "did dec-X work", "is decision Y still valid", "did the prediction come true", "check if the migration held", "is X stale", "measure that decision against reality", "did we actually fix Z", "is our caching decision still right" — or whenever a shipped decision needs a post-implementation reality-check before further work relies on it. Also use when /h-status surfaces a refresh-due decision. NOT for ad-hoc sanity checks (just run the tests directly). NOT for re-framing the underlying problem (use h-frame).
- ▌ H Compare · asermaxCompare two or more existing candidates under an explicit characteristic space, parity basis, and predeclared selection policy. Return constraints, trade-offs, and a non-dominated set rather than hiding the choice in one score. This skill is independent of h-frame and h-explore. Default to a conversational comparison; persist comparison artifacts only on explicit save intent or when current Work supplies a concrete operator-named or agent-inferred receiving use that needs replay. A binding choice requires a direct unambiguous operator request routed through h-decide.
- ▌ H Explore · asermaxGenerate 3-5 genuinely distinct candidate approaches for a current question, with the weakest link of each kept visible. Use when alternatives are needed or one favored approach is prematurely closing the search. This skill is independent: it may work from an inline question, cue, accepted problem, or other current basis. Default to conversational candidates; persist a SolutionPortfolio only on explicit save intent or when current Work supplies a concrete operator-named or agent-inferred receiving use that needs replay.
- ▌ H Onboard · asermaxBootstrap Haft through one readable onboarding surface, prepare an initial profile review or one bounded existing-scope relation change, and orient applicable specification carriers. Use for first-time setup, incomplete setup, or profile-underdetermined spec recovery. Project memory is ready immediately after haft init. Status and repository detection are read-only; all reviewed profile effects and specification lifecycle gates remain explicit human acts.
- ▌ H Diagnose · asermaxDiagnose a concrete failure with parallel rival-hypothesis testing. Use when symptoms are observable but cause is unclear. Stabilize the signal, generate distinct explanations, test them read-only in parallel, and rank by evidence while keeping losing rivals visible. This skill is independent and ordinarily non-persistent; save a diagnosis frame or hypothesis portfolio only on explicit request or when current Work supplies a concrete operator-named or agent-inferred receiving use that needs replay.
- ▌ H Commission · asermaxCreates 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, scope check, derives an ImplementationPlan, snapshots the autonomy envelope, then STOPS before execution. NOT for the decision itself (use /h-decide first). NOT for running tests or one-off tasks (the operator's coding agent handles those directly).
- ▌ Plannotator Last · asermaxOpen Plannotator on the latest rendered assistant message and use the returned annotations to revise that message or continue.
- ▌ Plannotator Review · asermaxOpen Plannotator's browser-based code review UI for the current worktree or a pull request URL, then act on the feedback that comes back.
- ▌ Plannotator Annotate · asermaxOpen Plannotator's annotation UI for a markdown file, HTML file, URL, or folder and then respond to the returned annotations.
- ▌ Init 2 · asermax bundleSeed an Obsidian vault the project then owns, and re-run it later to add a folder, a template or a base.
- ▌ Spike 2 · asermaxBuild 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 question answered by trying it rather than by reasoning about it.
- ▌ Design 2 · asermaxLay 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 boundary belongs, or when another skill needs a shape agreed before code.
- ▌
- ▌ Skill Authoring · asermaxActivates when the user wants to create, define, set up, build, or scaffold a new skill; encode expertise or save a process for reuse; define automation for the assistant. Also triggers on requests to author a skill, write a skill, help me make a skill, guide me through skill authoring, how to create a skill, make a skill, build a skill, new skill.
- ▌ Workflow Authoring · asermaxActivates when the user wants to create, define, set up, build, or scaffold a new workflow; encode a multi-step process or save a procedure for reuse; define automation for workflows. Also triggers on requests to author a workflow, write a workflow, help me make a workflow, guide me through workflow authoring, how to create a workflow, make a workflow, build a workflow, new workflow.
- ▌ Review · asermax bundleNEVER INVOKE THIS SKILL DIRECTLY; USE `/annai:review-pr` to review a GitHub pull request, or `/annai:review-local` to review code an agent just produced locally. This file is the shared base that the two leaf skills load — it owns the surface-authoring rules, launch + watch + react loop, schema-validation contract, and cleanup. It is not a standalone entry point.
- ▌
- ▌
- ▌ Zai Glm · asermaxUse the z.ai GLM API client for LLM-powered AI. Use when implementing the LLM brain, serializing game state, parsing responses, or debugging API calls.
- ▌ Wasm Export · asermaxBuild and serve the WebAssembly export. Use when the user asks to export, build, test in browser, or deploy the web version.
- ▌ Godot MCP Pro · asermaxReference for all 169 Godot MCP Pro tools. Use when creating scenes, adding nodes, writing scripts, simulating input, inspecting running games, or any editor interaction through MCP.
- ▌ Isometric Grid · asermaxReference for the isometric grid system. Use when working with grid coordinates, height maps, tile rendering, click detection, pathfinding, or movement range.
- ▌ Gdscript Patterns · asermaxArchitecture patterns for the GDScript codebase. Use when implementing battle systems, state machines, event buses, resources, actions, or turn queues.
- ▌ Log · asermaxWrite 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 another skill turns something up that must not live only in the conversation.
- ▌ Wiki · asermax bundleConsult distilled knowledge about technologies, tools, and their gotchas before designing, choosing, or debugging with them. Reads the indexes first and loads only matching entries.
- ▌ Loot · asermaxGet 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 when another skill is about to close or delete something and needs whatever it learned carried out first.
- ▌ Lore · asermaxWrite 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 with the code, or when another skill has changed how something works and the explanation has to follow.
- ▌ Raid · asermaxBuild the thing — turn cleared ground into a shape and a set of slices, then land them one per session.