all publishers

jerseycheese

@jerseycheese source repo

53 published skills

  1. ▌
    Review · jerseycheese
    Use when reviewing Narraitor code or PR changes for bugs, regressions, missing tests, and merge readiness.
    32 repo stars
  2. ▌
    Cyoa · jerseycheese
    Choose Your Own Adventure mode. Use when the user invokes /cyoa, asks for "cyoa mode", "choose your own adventure", or asks to make a development task feel like a game. Frames a real software task as a branching adventure where the user picks design decisions at every meaningful step. Produces real, working code — the adventure framing is purely a stylistic and decision-elicitation layer on top of normal development.
    32 repo stars
  3. ▌
    Kiss · jerseycheese
    Apply KISS principles to a diff or set of changes. Trims the change to the minimum surface required to achieve the stated goal — removes refactors, cleanup, style fixes, and "while I'm here" additions that aren't strictly necessary. Use when a diff has crept beyond its original scope or when you want to commit the smallest possible change.
    32 repo stars
  4. ▌
    Doc Rot · jerseycheese
    Sniffs out stale and deprecated documentation — markdown files, code comments, docstrings, and commented-out code — then updates or removes it. Grounds every staleness call against the actual code before acting: auto-fixes the high-confidence rot, surfaces judgment calls for review. Trigger on: "find stale docs", "outdated documentation", "doc rot", "doc sniffer", "clean up docs", "are the docs current", "deprecated docs", "fix the README", "stale comments", "remove commented-out code". For a broader sweep of dead variables, functions, files, or tests (not just docs/comments), use dead-code-cleanup instead.
    32 repo stars
  5. ▌
    Ds Guard · jerseycheese
    Automatically run after any edit to a .css, .tsx, .ts, .jsx, or .js file that contains styling. Triggers on: new CSS rules, className changes, style props, token usages, or any visual/layout change. Checks the diff against the project's design system token inventory and living style guide (canon, if one exists). Flags hardcoded values, off-system tokens, Tailwind utility classes, and patterns not established in the living style guide. Run this before every commit that touches styles or components.
    32 repo stars
  6. ▌
    Test Fix · jerseycheese
    Automatically invoke when any test run produces failures. Triggers on: test output showing FAIL, test errors, or assertion failures in unit or E2E suites. Applies a strict 3-attempt limit per failure to avoid debugging spirals — stops and escalates if not resolved. Do NOT wait for user to ask; invoke immediately when tests fail. Not for build errors, type errors, or lint failures — those aren't test failures.
    32 repo stars
  7. ▌
    Post Merge · jerseycheese
    Runs the post-merge workflow after a PR is merged. Phase 0 syncs the correct base branch and deletes the merged branch and its worktree so later work never starts from stale state. Phase 1 automatically closes the loop on linked GitHub issues (posts a completion comment, marks acceptance criteria done, closes the issue if fully addressed, ticks any parent epic) without asking permission — including for PRs merged into a non-default base like develop, where GitHub won't auto-close. Phase 2 recommends the single best next issue to work on, scoring all open issues by value, effort, and age. Invoke whenever the user says a PR was merged — "merged PR
    32 repo stars
  8. ▌
    Ship Issue · jerseycheese
    End-to-end conductor that drives a single GitHub issue all the way to a merged PR. Chains the issue-workflow skills — sync the base branch, analyze the issue, implement a minimal fix with a test, open a PR, drive CI to green, confirm the merge, run post-merge cleanup, and wrap up. Use to take one issue from a cold start to merged in a single command. Trigger on "ship issue
    32 repo stars
  9. ▌
    Wrap It Up · jerseycheese
    Close out the current chat with a tight summary and a sweep of the current project's durable context files — memory entries, status and task docs, plan files, and any project-specific reminders — so nothing important dies in the transcript. Trigger on /wrap-it-up, "wrap it up", "wrap up this chat", "close out this conversation", "end of chat", "summarize and clean up", or any end-of-session housekeeping request. Pairs with /handoff (which preps a new chat) — wrap-it-up is the backward-looking bookend.
    32 repo stars
  10. ▌
    Test Reaper · jerseycheese
    Finds and removes dead or trivial tests - duplicates, tests that only assert a mock was called, render checks that prove nothing, and suites whose name promises behavior they never observe. Distinguishes a test that tests nothing from one that tests the wrong thing, because those need opposite fixes. Trigger on: "test reaper", "reap tests", "remove trivial tests", "dead tests", "useless tests", "our tests don't test anything", "prune the test suite", "test audit", "which tests are worthless", "tests that always pass". For tests that are FAILING, use test-fix. For removing tests because their source is dead, use dead-code-cleanup.
    32 repo stars
  11. ▌
    Skill Parity · jerseycheese
    Keeps skills in sync across Claude Code, Codex, Gemini CLI, and shared .agents/skills paths. Handles copying, updating, pruning, and verifying parity across all provider locations. Trigger on: "sync my skills", "hydrate codex with skills", "copy skill to gemini", "add this skill to codex", "update skills across providers", "skill parity check", "push skills to all providers", "are my skills in sync", "propagate skill changes".
    32 repo stars
  12. ▌
    Visual Crawl · jerseycheese
    Crawls the running app at randomized breakpoints, screenshots visual issues, checks design token consistency, and tests interactive elements. Each run covers different ground by design. Trigger on: "visual QA", "audit the app visually", "screenshot all the pages", "check for visual regressions", "crawl the site for issues", "visual design system audit", "responsive check", "screenshot the routes", "look for visual bugs", "check the UI".
    32 repo stars
  13. ▌
    Analyze Issue · jerseycheese
    Analyzes a single GitHub issue and produces a detailed technical specification ready for implementation. Fetches the issue, discovers existing patterns in the codebase, defines scope boundaries, and produces an implementation plan with MVP tests. Use before starting work on an issue to understand it fully. Trigger on "analyze issue
    32 repo stars
  14. ▌
    Tdd Implement · jerseycheese
    Implements a feature or fix using Test-Driven Development — write failing tests first, then implement just enough to make them pass, then refactor. Keeps tests focused on acceptance criteria rather than implementation details. Use when building something new with TDD, or when the user wants to start from tests rather than code. Trigger on "implement with TDD", "use TDD for this", "write the tests first", "TDD workflow", "red-green-refactor".
    32 repo stars
  15. ▌
    Test Workflow · jerseycheese
    Automatically run after editing source files to select and run the appropriate test suite. Triggers on: any src/ file edit before a commit, or when the user says "run tests", "check tests", or "make sure tests pass". Selects unit, E2E, visual regression, or CSS lint based on what changed. Protects running dev servers. Do NOT wait for user to ask after a code change — run proactively before committing. Not for documentation-only or config-only edits, or when the user says to skip tests.
    32 repo stars
  16. ▌
    Comment Reaper · jerseycheese
    Finds and removes unnecessary code comments - the ones that restate the code, cite an issue number, narrate refactor history, or wrap a one-line function in six lines of JSDoc. Sorts every find into auto-fix, propose, or never-touch, so the WHY comments survive the sweep. Trigger on: "comment reaper", "reap comments", "remove unnecessary comments", "too many comments", "verbose comments", "clean up the comments", "strip redundant JSDoc", "comment audit", "comment hygiene", "our comments are noise". For comments that are WRONG rather than merely unnecessary, use doc-rot. For comments that are hard to READ rather than unnecessary, use plain-language-audit.
    32 repo stars
  17. ▌
    Evidence Check · jerseycheese
    An honesty gate that makes an AI back up its claims with real evidence instead of presenting guesses as fact. Use as an always-on background behavior, and invoke explicitly when the user says show your work, prove it, how do you know that, evidence check, what's your source, back that up, or when the AI is recommending a course of action. Apply as a cross-cutting self-check before presenting technical claims, recommendations, or architectural guidance.
    32 repo stars
  18. ▌
    Band Aid Finder · jerseycheese
    Scans a change or codebase area for band-aid fixes that suppress a symptom instead of resolving the underlying cause, traces each to its actual root cause, and proposes the fix that addresses it. Distinguishes a band-aid from a deliberate, documented mitigation (incident hotfix, third-party defect, cost-outweighs-benefit) so it doesn't dogmatically demand a root-cause fix. The counterweight to KISS: it argues against a fix so simple it only hides the symptom. Trigger on: "is this a real fix or a band-aid", "am I treating the symptom", "why does this keep happening", "this feels hacky", "find the root cause", "search and destroy quick fixes", "is this a workaround".
    32 repo stars
  19. ▌
    Code Health Audit · jerseycheese
    Kicks off a recurring code-health audit — the "embarrassing code" / overengineering sweep that turns vague tech-debt anxiety into a short list of measurable, validated simplifications to ship. Bakes in the pre-flight discipline (sync the correct base branch, confirm the active worktree and its dev server, list files in scope) so the audit never runs against stale or wrong-worktree code. Trigger on: "embarrassing code audit", "overengineering audit", "code health audit", "find simplification candidates", "what can we simplify", "tech debt sweep", "audit the codebase", "find overengineered code", "what's embarrassing in this repo".
    32 repo stars
  20. ▌
    Dead Code Cleanup · jerseycheese
    Identifies and removes dead/orphaned code, tests, and Storybook stories — including trivial tests that check only obvious behavior or rare edge cases with no real value. Always validates that code is truly unused before deleting anything. Trigger on: "remove dead code", "clean up unused files", "delete orphaned components", "find unused exports", "remove trivial tests", "clean up the codebase", "what code can we delete", "prune the repo", "remove stale stories".
    32 repo stars
  21. ▌
    Github Screenshot · jerseycheese
    Generates GitHub-compatible markdown for screenshots using raw.githubusercontent.com URLs via the generate-github-image-markdown.sh script. Trigger on: "add a screenshot to this PR", "embed image in issue", "attach screenshot", "paste image into GitHub", "add screenshot to docs", "insert image in markdown", "show a screenshot in the PR", "add image to issue".
    32 repo stars
  22. ▌
    Issue Maintenance · jerseycheese
    Periodic and on-demand maintenance pass over a repo's open GitHub issue backlog. Re-labels miscategorized or unlabeled issues (bug/enhancement/question/invalid/duplicate) and bug lifecycle labels (needs-repro/needs-info) following the same decision logic as Anthropic's own dogfooded triage-issue command; re-scores every open issue with prioritize-issues' value/effort/ age rubric and writes the resulting priority:high/medium/low/post-mvp label; fills in missing sizing labels (complexity/model-power or the repo's equivalent) where the repo documents a convention for them; applies mechanical plain-language fixes (AI-tell swaps, filler removal) to issue title/body via the plain-language-audit skill and surfaces jargon/verbosity/tone judgment calls for review. Auto-applies high-confidence changes, flags ambiguous ones in a single tracking issue. Unlike prioritize-issues (read-only ranked report) or analyze-issue (single-issue technical spec), this skill WRITES to issues. Needs no repo clone — GitHub issue metadata
    32 repo stars
  23. ▌
    Prioritize Issues · jerseycheese
    Analyzes all open GitHub issues to identify the highest-priority candidates for implementation. Scores by value, effort, age, and roadmap alignment. Produces a ranked top-5 with detailed technical specs for the top 3. Use when planning what to work on next, triaging a backlog, or preparing for a sprint. Trigger on phrases like "what should I work on", "prioritize my issues", "what's the highest value issue", "triage my backlog", "help me pick the next issue", "what's worth doing next".
    32 repo stars
  24. ▌
    Project Bootstrap · jerseycheese
    Bootstrap a project under ~/Projects with the standard agent scaffolding, stamped from the starter kit at shared/Development/templates/starter-kit - a CLAUDE.md from the house template, the stack-agnostic core (.editorconfig, .gitignore, .claude settings/launch, worktree-port script), an optional stack layer, and a row in the ~/Projects/CLAUDE.md root map. Use when creating a new project or repo, or when an existing repo is missing its CLAUDE.md. Trigger on "bootstrap this project", "new project setup", "stamp a CLAUDE.md", "set up agent scaffolding", "give this repo a CLAUDE.md".
    32 repo stars
  25. ▌
    Worktree Enhanced · jerseycheese
    Sets up a git worktree for isolated feature work — creates the branch, configures the worktree, detects whether a dev server is already running, and handles project-specific setup. Trigger on: "create a worktree", "set up a new branch", "start work on issue #X", "work on this in isolation", "new worktree for", "start a feature branch", "create an isolated environment for", "set up worktree".
    32 repo stars
  26. ▌
    Abstraction Finder · jerseycheese
    Scans a codebase or a named area for recurring patterns that could be extracted into shared, general-purpose code, and proposes the smallest form for each — helper, service, base class, template, or util — with the exact call sites it would replace. The inverse of a conformance check: it discovers duplication worth unifying rather than checking one change against existing patterns. Enforces the rule of three and refuses to abstract single-use or surface-similar code. Trigger on: "where are we repeating ourselves", "what could be abstracted", "find duplication", "is there a shared helper for this", "could this be DRY'd up", "extract a common pattern", "find abstraction candidates".
    32 repo stars
  27. ▌
    CI Fix With Memory · jerseycheese
    Automatically invoke when CI checks fail on a PR. Triggers on: any mention of CI failure, red checks, failed GitHub Actions, or "CI is broken/failing". Reads session handoffs and a known-issues log to avoid repeating failed fix attempts. Do NOT wait for user to ask — invoke as soon as a CI failure is confirmed. Not for local-only test failures (use test-fix instead) or lint-only failures with an obvious single-line fix.
    32 repo stars
  28. ▌
    Visual QA Pipeline · jerseycheese
    Turns a visual QA crawl into shipped work: crawl the running app, triage findings by severity, file Major+ findings as GitHub issues with screenshots, batch the small stuff into one roll-up issue, and optionally open fix PRs for mechanical design-system violations. Runnable on a schedule. Trigger on: "visual QA pipeline", "crawl and file issues", "autonomous visual QA", "visual QA to PR", "screenshot the app and open issues", "nightly visual QA", "ship visual fixes".
    32 repo stars
  29. ▌
    Drupal Mental Model · jerseycheese
    Use when explaining code, debugging, or discussing architecture with Jack — map programming concepts to Drupal equivalents he already knows from years of Drupal/theming work. Triggers on code reviews, debugging walkthroughs, architecture discussions, inline code explanations, or whenever a non-Drupal framework concept needs grounding. Skip for non-programming topics.
    32 repo stars
  30. ▌
    Browser Debugger CLI · jerseycheese
    Inspect and debug live web pages using the Chrome DevTools Protocol via the `bdg` CLI. Use for targeted DOM queries, computed style checks, layout debugging, and CDP method calls without loading a full page snapshot. Prefer over chrome-devtools-mcp for token efficiency. Trigger on: "inspect element", "check computed styles", "query the DOM", "what does the DOM look like", "debug layout", "check the CSS on", "run a DevTools query", "what's the rendered style of", "inspect the page".
    32 repo stars
  31. ▌
    Plain Language Audit · jerseycheese
    Sweeps a codebase's text — comments, docstrings, markdown docs, and user-facing UI copy — for jargon that could be plainer, AI writing tells/tropes, and verbose text that could be tightened. Auto-fixes unambiguous swaps, surfaces judgment calls for review. Trigger on: "jargon audit", "plain language audit", "find jargon", "sounds too technical", "AI tells", "AI slop in the docs", "sounds like AI wrote this", "too wordy", "make this more concise", "simplify this copy", "plain-language sweep". For code correctness/structure issues (fake fallbacks, dead logic), use dead-code-cleanup or code-health-audit instead — this skill is prose/tone only.
    32 repo stars
  32. ▌
    Pr Review Fix Pipeline · jerseycheese
    Autonomous PR review that also applies fixes for non-controversial issues — combines review, fix, test, and commit into a single pipeline. Unlike a read-only review, this writes code. Only use on feature branches where you're comfortable with automatic edits. Trigger on: "review and fix PR", "auto-fix the PR", "clean up this PR automatically", "review PR #X and fix issues", "fix whatever's wrong in this PR", "run the review pipeline".
    32 repo stars
  33. ▌
    Narraitor Storybook App Parity · jerseycheese bundle
    Isolation-vs-integration parity reasoning and the component promotion ladder for Narraitor. Use when something "works in Storybook" but not the app (or vice versa), before calling any component done/integrated, when writing stories with withStores or MSW, or when deciding whether Storybook-green is enough evidence. Storybook is the canon DESIGN surface, never proof of app behavior.
    32 repo stars
  34. ▌
    Narraitor AI Quality Discipline · jerseycheese bundle
    The evidence bar for AI narrative quality in Narraitor. Use when judging whether a prompt or generation change "works", when someone says "the output reads better", "the AI handles it", "works on my world", or when evaluating narrative coherence, choices, endings, or any Gemini-generated behavior. Encodes why one good generation is a signal not evidence, and how to turn a hunch into a checked improvement.
    32 repo stars
  35. ▌
    Narraitor Architecture Contract · jerseycheese bundle
    The load-bearing architecture invariants of Narraitor - domain boundaries, Zustand store contracts, the event bus, persistence rules, Next.js 15 server/client boundaries, and what may never be bypassed. Use before changing a store's shape, adding cross-domain imports, touching src/lib/api or src/lib/ai seams, moving logic between server and client, or whenever deps:validate / skott / boundary questions come up.
    32 repo stars
  36. ▌
    Narraitor Diagnostics And Tooling · jerseycheese bundle
    How to MEASURE instead of eyeball in Narraitor - curl smokes for the AI/API routes, inspecting persisted Zustand state in IndexedDB, DOM/computed-style checks for layout and theming, visual tooling, and where reports land. Use when you need proof of runtime behavior - "is the route up", "what's actually in the store", "what computed style applies", "where is the playwright report" - or when a claim needs an artifact.
    32 repo stars
  37. ▌
    Narraitor Pattern Alignment Skill · jerseycheese bundle
    Automatically run after any code change in this repo (components, stores, API routes, CSS, tests, types). Triggers on: new files, refactors, feature additions, or any edit touching src/. Reviews changes for alignment with established project patterns — design tokens, state conventions, error handling, domain boundaries, accessibility. Do NOT wait for user to ask; run as a post-edit check before committing.
    32 repo stars
  38. ▌
    Narraitor Hardest Problem Campaign · jerseycheese bundle
    Executable campaign for Narraitor's hardest live problem - closing the v1.0 release gate, whose un-automatable core is validating the live AI play loop (real Gemini, multi-turn, consequences, endings) that every automated suite deliberately gates off. Use when asked to "get v1.0 out", "close the release gate", "validate the play loop end to end", "is this shippable", or to run/resume the release campaign.
    32 repo stars
  39. ▌
    Narraitor Prompt Template Governance · jerseycheese bundle
    The governed lifecycle for AI prompt templates in Narraitor - registry, input contract, context-leakage gate, evaluation, regression, cost, and integration gates. Use when adding or editing any prompt template, when tempted to inline a prompt string into a generator or route, when reviewing a prompt change, or when asked "where do prompts live" / "can I just tweak the prompt".
    32 repo stars
  40. ▌
    Narraitor Parallel Lane Orchestration · jerseycheese
    Run a batch of Narraitor issues as parallel worktree lanes, with a Fable orchestrator picking the batch and delegating each issue to a subagent whose model matches the issue's model-power label. Use when asked to "work the top N issues in parallel", "fan out the backlog", "kick off a parallel batch", "orchestrate lanes", or when planning a multi-issue push that should run concurrently rather than serially. Covers batch selection, collision avoidance against work already in motion, model tiering, and the lane failure modes that have actually bitten this repo.
    32 repo stars
  41. ▌
    Narraitor Feature Experiment Lifecycle · jerseycheese bundle
    How a hunch becomes a shipped, held, or retired change in Narraitor - issue capture, acceptance criteria, experiment flagging for AI-behavior changes, the gate sequence, and ship/hold memos. Use when starting any feature or improvement idea, when someone says "let's try", "quick experiment", "I have an idea for the narrative", or when deciding whether in-flight work ships, holds, or gets retired.
    32 repo stars
  42. ▌
    Style Port · jerseycheese
    Port inline styles from a reference/demo component to production CSS in the Narraitor design system. Rigid 6-phase process that diffs inline styles against production stylesheets, ports gaps using design tokens, and removes inline styles from production components. Use when porting design system styles from any reference source to the app.
    32 repo stars
  43. ▌
    Narraitor Architecture · jerseycheese bundle
    Automatically invoke when creating new components, stores, API routes, or planning a feature in Narraitor. Triggers on: new file creation under src/, architecture questions, feature design discussions, or any structural decision. Applies domain boundaries, naming conventions, state management patterns, and AI integration conventions. Do NOT wait for user to ask — invoke before writing new structural code.
    32 repo stars
  44. ▌
    Narraitor Playtest Loop · jerseycheese bundle
    Drive real multi-turn game sessions in a browser against live Gemini and score whether the story is actually engaging. Use when asking "is this fun to play", "does the narrative hold up over 30 turns", "why does the story get boring", when planning a release playtest, or when a change to prompts or narrative logic needs a before-and-after read on story quality. This is the taste instrument; narraitor-qa-walkthrough is the release defect gate and narraitor-ai-quality-discipline is the evidence bar both of them answer to.
    32 repo stars
  45. ▌
    Narraitor Build Test Env · jerseycheese bundle
    Recreate, run, and verify the Narraitor environment - install, dev server, Storybook, the full quality gate, and how to classify failures as environment vs data vs AI-provider vs code. Use when setting up from scratch, when "npm test / build / lint fails", when the dev server won't start or the port is taken, when Playwright can't run locally, when jest runs out of memory, or before claiming any gate is green.
    32 repo stars
  46. ▌
    Narraitor Change Control · jerseycheese bundle
    How changes are classified, gated, evidenced, and shipped in Narraitor - and what may never be claimed without proof. Use before declaring anything "done", "fixed", "validated", or "verified", before re-baselining any gate (visual snapshots, dep-cruiser, skott, ds-canon), when correcting an earlier wrong claim, or when deciding what evidence a PR needs. This is the anti-overclaiming gate for every other skill.
    32 repo stars
  47. ▌
    Narraitor Docs And Writing · jerseycheese bundle
    Maintaining Narraitor's docs of record - status language, marking stale claims, append-only corrections, doc templates, and the project voice for all generated prose (PRs, issues, comments, code comments, user-facing copy, docs). Use when WRITING or FIXING any documentation or prose, when marking/correcting a doc that contradicts the code, when recording a correction to an earlier wrong claim, or when drafting PR/issue text. (Deciding whether the claim is true -> narraitor-change-control; which docs to trust -> narraitor-repo-orientation.)
    32 repo stars
  48. ▌
    Narraitor Domain Reference · jerseycheese bundle
    Applied domain knowledge a mid-level engineer lacks for Narraitor - the world/character/narrative/session data model, Zustand store and persistence conventions, Next.js 15 App Router pitfalls, streaming/latency realities of Gemini, and the single-design-system (ds3) theming model. Use when reasoning about how domains relate, what a store field means, why hydration/persistence behaves oddly, or how AI-provider quirks shape the code.
    32 repo stars
  49. ▌
    Narraitor Product Frontier · jerseycheese bundle
    Narraitor's open frontier problems and how to attack them in THIS repo - long-arc story memory and coherence, consequence tracking, progressive streaming, replayability, and automated prompt evaluation. Use when asked "what's next", "what would make this state of the art", when scoping ambitious AI-narrative work, or to check whether a big idea already has an epic, an asset, or a failed attempt.
    32 repo stars
  50. ▌
    Narraitor Repo Orientation · jerseycheese bundle
    Fast orientation map for a zero-context session in the Narraitor repo. Use FIRST when starting work here, when asked "where does X live", "how is this repo organized", "what's the stack", "where do I look for the stores / AI code / themes / tests", or to check WHICH docs are trustworthy before acting on one. (Asking WHY something is built this way -> narraitor-failure-archaeology; fixing or correcting a stale doc -> narraitor-docs-and-writing; "where do prompts live" -> narraitor-prompt-template-governance.)
    32 repo stars
  51. ▌
    Narraitor Validation And QA · jerseycheese bundle
    What counts as evidence in Narraitor - the test tiers (unit, Storybook, visual regression, e2e, manual QA walkthrough), what each can and cannot prove, acceptance thresholds, how to add tests, and how to read failures. Use when deciding which tests a change needs, interpreting a red or suspiciously green run, planning QA before a release, or when someone cites "tests pass" as proof.
    32 repo stars
  52. ▌
    Narraitor Debugging Playbook · jerseycheese bundle
    Symptom-to-triage runbook for Narraitor failures - blank narrative, AI route 500/timeouts, hydration mismatch, state not persisting after reload, works-in-Storybook-but-broken-in-app, theming drift, flaky visual specs, mystery tsc errors. Use whenever something is broken and the cause isn't already proven, or when you're about to try a second fix for the same symptom.
    32 repo stars
  53. ▌
    Narraitor Failure Archaeology · jerseycheese bundle
    Narraitor's memory of painful failures, reverts, dead ends, and deliberately settled decisions. Use BEFORE proposing to remove/replace something that looks wrong or overengineered (the event bus, the react-joyride pin, split store files), before re-attempting an idea that may have been tried, when a doc or memory claims HISTORY the tree contradicts ("was X removed?", "did we already try Y?"), or when asked "why is it built this way". Do not re-fight settled battles. (Which docs to trust at all -> narraitor-repo-orientation; writing the correction -> narraitor-docs-and-writing.)
    32 repo stars