agentleFS
mehrad-dmmehrad-dm/mastermind/skills/help/SKILL.md

help

Skill23 starsChanged 2 months agoMITView on GitHub

Use when the user asks what MasterMind can do or how to drive it: \"help\", \"what can you do\", \"how do I use this\", \"what commands are there\", \"list your skills\", \"what are my options\": or when they seem unsure how to get started.

76 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use create-stories, story-done and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • lilangMaxSkill

    create-stories

    Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

    Also in 9 projects that use this

  • lilangMaxSkill

    story-done

    End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.

    Also in 9 projects that use this

  • +10 more from lilangMax

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 57 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before the full menu, name up to three skills that would earn their keep here right now, each with the reason it applies: read from what's …

    line 18
  2. Very specific:

    If MasterMind isn't set up for this project yet (no field pack for your stack), it will offer a one-time setup, say *"init"* or just start …

    line 98

“Common” is measured: kept by at least 6 in 10 of the 57 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Help: what MasterMind can do, and how to use it

Present this as a clear, friendly menu (adapt length to the ask). Open with the brand header, then lead with the one thing that matters most, then the tables. Keep it scannable. Header:

🧠  MasterMind: a genius-builder brain for your AI
    33 skills · 4 agents · Claude Code · Cursor · Codex

Lead with what fits this project

Before the full menu, name up to three skills that would earn their keep here right now, each with the reason it applies: read from what's actually in front of you (the stack, the current task, what the last few turns were about, whether a field pack exists yet):

Most useful here right now
  · init: no field pack yet for this Django project; one-time setup, then I'm sharper on it
  · quarantine: there's client data in this repo; this keeps it out of git
  · handoff: this session is long; a handoff survives the reset

A full menu is a catalogue; three fitting picks are advice. Then give the tables below: the catalogue still matters, because the point is that the user learns what they already own.

The one rule: you don't run commands: you just talk

MasterMind works by recognizing intent. Say what you want in plain language and it applies the right skill or agent itself, then shows a short note that it did (e.g. 🧠 MasterMind ▸ building this, will verify before handoff, with └ build · design → implement → verify beneath it). The /name calls below are an optional shortcut: a way to force a specific skill, not something you need to memorize. Every skill is Auto (the model can invoke it); you can also call any of them by hand.

Skills: the workflows (all Auto-invocable)

SkillWhat it doesFires automatically when…Call it by hand
initset MasterMind up for this project: detect the stack (or ask what you're building), load the field packyour first real task in a project it isn't set up for"init" · "set up MasterMind"
builddesign → implement → verify → review → capture, end to endyou ask to build/add/implement a non-trivial feature"build a search box for the header"
debugstructured, evidence-first root-cause debugginga bug is hard, weird, or keeps coming back"debug why the list doesn't refresh"
performancemeasure → find the real bottleneck → fix the biggest → verifysomething's slow or janky ("why is this slow?")"why is this page so slow?"
qaprove a change works by driving it for real (+ optional tests)you finish something / ask to test it"qa this" · "write tests for it"
reporta shareable write-up of a cycle: changed files, decisions, verification, verdict (MD default, HTML on request)you ask for a report; or end of build/qa if you turned it on (off by default)"give me a report of this" · "reports on"
interviewturn a fuzzy ask into a crisp, buildable spec; resolve a written spec's open questionsthe request is ambiguous, or a spec has open questions"interview me about the checkout flow first"
assessdecide whether an idea deserves building: go, clarify or stop, with evidencean idea nobody has said yes to yet"is this worth building?"
constitutionwrite and version the rules every feature in this project must obeyyou state a non-negotiable, or start spec-first work"these are our non-negotiables"
living-docskeep the product, business and tech documents current, each fact written oncedocs are missing or stale, or a feature just finished"write down how this product works"
specifywrite a feature spec: what and why, prioritized stories, traceable requirementsa feature spans sessions, or touches money, auth or data"write the spec for invitations"
blueprintturn a spec into a technical plan, checked against the constitutiona spec has no plan yet"plan this spec"
breakdowncut the plan into tasks, grouped by user story so each ships alonea plan has no task list yet"break this into tasks"
checklisttest one concern's requirements (security, UX, API) before buildinga sensitive feature heads into planning"security checklist for this spec"
analyzecheck spec, plan and tasks agree before any code, read-onlyyou're about to build from a task list"is this ready to build?"
convergecheck the built code against everything the feature promised; append the gapsevery box is ticked, or you ask "is it really done?""check the code against the spec"
routeload only the files/skills a task actually needsa task is non-trivial or you're unsure where to start"route this"
learnget up to speed fast on an unfamiliar stack/API, verify assumptionsthe tech is new, fast-moving, or you're guessing"learn how the Stripe API handles refunds"
prototypebuild a throwaway prototype to learn, then rebuild properlythe right approach is genuinely unknown"throw together a quick prototype of this"
signaturecapture your team's real conventions as durable rules it followsyou ask it to match your codebase / keep correcting the same thing"make it match our patterns"
personawrite in the documented public style of a named engineer, citedyou ask for someone's style ("write like X")"write this like Kent C. Dodds"
explainwrite AI-friendly usage docs beside an internal packagean internal package has little/no docs (asks first)"explain this package"
promptsharpen a vague prompt into a precise, AI-ready oneyou ask to optimize/fix a prompt for an AI"improve this prompt"
quarantineset up a private, gitignored quarantine for confidential databefore capturing project/client-specific notes"keep this client's data private"
levelupimprove MasterMind's own knowledge (lessons, curriculum, new field)after a correction/review, or to refresh standards"levelup: remember this"
double-checkinterrogate a claim before handing it over: adversarial, reviewer never sees your conclusionyou're about to say "it works", or a review came back suspiciously clean"are you sure? double-check it"
deprecateremove/migrate/retire safely: expand → migrate → contractdeleting a feature, column, flag, or endpoint"can we delete this?"
roadmapa durable decision map for multi-week workwork spanning many sessions; "why did we decide X?""keep a roadmap for this project"
lintcheck MasterMind's own files for bloat, repeated rules, contradictionsbefore a release, or the brain feels bloated"lint the brain"
clarifyre-pitch an answer that did not land, in plain words or as a pictureyou say "I did not follow that", "simpler", "you lost me""say that simply"
deepensurvey an area and rank where the design costs most, you pick one"this is getting messy", "why is this so hard to change?""where is this hurting?"
handoffwrite a concise handoff so work survives a reset/teammatebefore a long-task /clear, pausing, or handing off"write a handoff"
helpshow this menu, what every skill/agent does and when it firesyou ask "what can you do?" / "help" / "how do I use this""what can you do?"

Agents: the deep expert roles (isolated context)

Agents run in their own context for a focused job. MasterMind delegates to them inside a task; you can also summon one directly.

AgentWhat it doesUsed automatically when…Call it by hand
architectdesigns the solution before code (boundaries, data model, APIs)a feature is non-trivial (inside build)"architect this feature"
code-reviewerreviews a diff against the rigor gate; proposes fixes, never appliesafter a change, before "done""review this"
refactorerrestructures working code to a better design, behavior-preservingyou ask to clean up / restructure working code"refactor this component"
tech-scoutdecides adopt-vs-build for a library/tool/pattern, with a verdictchoosing a dependency or approach"should we use Zustand or Redux here?"

Skills vs agents (one line)

Skills are inline workflows that run in the current conversation; agents are separate expert roles with their own fresh context for a heavier, focused job. You rarely pick. MasterMind reaches for the right one and tells you.

Getting set up

If MasterMind isn't set up for this project yet (no field pack for your stack), it will offer a one-time setup, say "init" or just start working and it'll ask. Verify your install anytime with ~/.mastermind/install.sh --check.

Optional preferences (per project, kept in .mastermind/prefs.md; the first two are off by default):

  • cycle report: a written write-up at the end of a build/QA cycle. Turn on: "reports on".
  • plan-first: on bigger tasks, MasterMind shows the plan and waits for your OK before editing. Turn on: "plan first from now on".
  • specs-dir: where spec-driven documents live, specs unless that folder already holds something else.

The first two behave exactly as their implementations define them, skills/build/SKILL.md (plan-first gate) and skills/report/SKILL.md (report formats).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.