Source profileQuality 93/100

simota/agent-skills/muse/SKILL.md

muse

Defining and managing design tokens, applying token systems to existing codebases, building design system foundations. Use for spacing, color, typography, dark mode, cross-platform output.

Source repository stars
74
Declared platforms
0
Static risk flags
1
Last source update
2026-08-24
Source checked
2026-08-28

Decision brief

What it does: where it fits

Systematize visual language with tokens. Favor stable semantics over one-off styling.

Best for

    Not for

    • Tasks that require unconfirmed production actions or broad system permissions.
    • Environments where the pinned source and install steps cannot be inspected.

    Compatibility matrix

    Platform support, with evidence labels

    PlatformStatusEvidenceWhat to check
    CodexNot declaredNo explicit evidencePortability before use
    Claude CodeNot declaredNo explicit evidencePortability before use
    CursorNot declaredNo explicit evidencePortability before use
    Gemini CLINot declaredNo explicit evidencePortability before use
    Open the compatibility checker

    Installation

    Inspect first. Install second.

    The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

    Source-detected install commandSource
    npx skills add https://github.com/simota/agent-skills --skill "muse"
    Safe inspection promptEditorial

    Inspect the Agent Skill "muse" from https://github.com/simota/agent-skills/blob/0b594f3ff4bf53639f60832a943d90a5109ddf85/muse/SKILL.md at commit 0b594f3ff4bf53639f60832a943d90a5109ddf85. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

    Workflow

    What the source asks the agent to do

    1. 01

      Workflow

      SCAN → POLISH → REFINE → VERIFY → PRESENT

      SCAN → POLISH → REFINE → VERIFY → PRESENT
    2. 02

      Trigger Guidance

      Use Muse when the task requires any of the following:

      Define or revise design tokens for color, spacing, typography, shadows, or radius.Replace hardcoded UI values with semantic tokens.Build or repair a design system foundation.
    3. 03

      Core Contract

      Define tokens before styling components by feel.

      Define tokens before styling components by feel.Prefer semantic tokens over raw primitive references in app code — follow the three-layer model: primitive → semantic → component (per Martin Fowler's token-based UI architecture).Keep design and code aligned through an explicit token lifecycle.
    4. 04

      Boundaries

      Agent role boundaries - common/BOUNDARIES.md

      Define tokens for colors, spacing, typography, shadows, and radius.Create token files for the active stack.Replace hardcoded values with semantic tokens.
    5. 05

      Always

      Define tokens for colors, spacing, typography, shadows, and radius.

      Define tokens for colors, spacing, typography, shadows, and radius.Create token files for the active stack.Replace hardcoded values with semantic tokens.

    Permission review

    Static risk signals and limitations

    Reads files

    low · line 185

    The documentation asks the agent to read local files, directories, or repositories.

    If it matches a Recipe Subcommand above → activate that Recipe; load only the "Read First" column file at the initial step.

    Evidence record

    Why each signal appears

    EvidenceSourceComputedTestedEditorial
    SignalValueEvidence typeMeaning
    Quality score93/100ComputedDocumentation, specificity, maintenance, and trust rules
    Repository stars74SourceRepository attention, not individual Skill quality
    Compatibility0 platformsSourceDeclared in the catalog source record
    Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

    Pinned source

    Provenance and original SKILL.md

    Repository
    simota/agent-skills
    Skill path
    muse/SKILL.md
    Commit
    0b594f3ff4bf53639f60832a943d90a5109ddf85
    License
    MIT
    Collected
    2026-08-28
    Default branch
    main
    View the original SKILL.md

    Muse

    Systematize visual language with tokens. Favor stable semantics over one-off styling.

    Trigger Guidance

    Use Muse when the task requires any of the following:

    • Define or revise design tokens for color, spacing, typography, shadows, or radius.
    • Replace hardcoded UI values with semantic tokens.
    • Build or repair a design system foundation.
    • Add or verify light and dark theme support.
    • Audit token coverage, off-grid spacing, or inconsistent component styling.
    • Validate or convert tokens to W3C DTCG spec v2025.10 format ($value, $type, $description).
    • Configure Style Dictionary v5, Tokens Studio, or Terrazzo token pipelines.
    • Define accessibility-focused tokens (touch targets, focus rings, reduced motion).
    • Process reverse feedback from Palette, Flow, Vitrine, or Judge about accessibility, motion, hardcoded values, or inconsistency.

    Route elsewhere when the task is primarily:

    • Full component implementation → Artisan
    • Animation choreography or keyframe logic → Flow
    • Creative direction or visual identity exploration → Vision
    • Figma plugin API calls or canvas manipulation → Frame
    • i18n/RTL layout logic beyond token definitions → Polyglot
    • End-to-end design→implementation pipeline across multiple artifact types with design-system persistence → Atelier

    Core Contract

    • Define tokens before styling components by feel.
    • Prefer semantic tokens over raw primitive references in app code — follow the three-layer model: primitive → semantic → component (per Martin Fowler's token-based UI architecture).
    • Keep design and code aligned through an explicit token lifecycle.
    • Treat dark mode support as part of the baseline system, not as a later patch.
    • Use system rules, not subjective taste, as the basis for changes.
    • Target W3C DTCG spec v2025.10 format ($value, $type, $description) as the canonical interchange format for new token files. The spec is the first stable release — treat it as production-ready, not experimental.
    • Prefer modern color spaces (Display P3, OKLab, OKLCH) over sRGB hex for wide-gamut token definitions when the target platform supports them; DTCG v2025.10 natively supports these spaces. Ship sRGB fallbacks and layer OKLCH via @supports / color-mix() for progressive enhancement on narrow-gamut displays.
    • Leverage DTCG v2025.10 native theming support via resolver documents (.resolver.json) — manage light/dark modes, accessibility variants, and multi-brand themes without file duplication. When multiple .tokens.json sources are declared, they merge in array order (last wins).
    • Adopt tokens incrementally — attempting a full-system rollout at once stalls teams; start with color primitives, then expand to spacing and typography.
    • Author for the executing engine (P1–P11 bind only on Opus 5; P12 generation-wide). See _common/OPUS_5_AUTHORING.md (P3, P5 critical for Muse; P2, P1 recommended).

    Boundaries

    Agent role boundaries -> _common/BOUNDARIES.md

    Always

    • Define tokens for colors, spacing, typography, shadows, and radius.
    • Create token files for the active stack.
    • Replace hardcoded values with semantic tokens.
    • Verify light and dark mode.
    • Audit changed files for hardcoded values and off-grid spacing.
    • Follow the lifecycle in reference/token-lifecycle.md.
    • Process reverse feedback from Palette, Flow, Vitrine, and Judge.

    Ask First

    • Breaking token value changes.
    • Page layout restructuring.
    • Full design system migration.
    • Overriding component styles instead of fixing tokens.
    • Deprecating or removing STABLE tokens.

    Never

    • Use raw HEX/RGB values in components unless defining tokens — leads to inconsistency cascade where one-off overrides multiply across components, making theme changes require file-by-file hunts.
    • Name tokens by color value (e.g. green-500, blue-dark) — breaks semantic meaning when values change; use purpose-based names (color.surface.primary, color.feedback.success).
    • Expose tokens not defined by designers to production code — creates Figma↔code conflicts at scale when designers update tokens expecting consistent propagation.
    • Make subjective visual changes without a system basis.
    • Trade accessibility for aesthetics — WCAG 2.2 AA violations carry legal risk (ADA Title III lawsuits exceeded 4,000/year in the US).
    • Delete or rename tokens without a migration path.
    • Use Inter, Roboto, or Arial as the primary display font.
    • Manually sync token values between design tools and code — breaks at team scale; use automated pipelines (Style Dictionary v5, Tokens Studio).
    • Rely on $extensions surviving Figma round-trips — Figma's native DTCG import/export (announced Schema 2025) strips $extensions on export; store extension data in the code-side token pipeline, not in Figma as the source of truth.

    Workflow

    SCAN → POLISH → REFINE → VERIFY → PRESENT

    PhaseFocusRequired checksRead
    SCANFind inconsistencies, hardcoded values, off-grid spacing, dark mode gaps, stale docs, and reverse feedbackAudit changed files and active token setsreference/token-system.md, reference/token-anti-patterns.md
    POLISHPick the highest-impact improvement that reinforces the systemPrefer visible, isolated, reusable fixesreference/token-system.md
    REFINEApply tokens, flatten architecture issues, and clean naming or lifecycle driftAvoid ad hoc overridesreference/token-lifecycle.md, reference/css-token-architecture-anti-patterns.md
    VERIFYConfirm responsive behavior, dark mode, accessibility, and token coverageRun palette-style contrast checks when colors changedreference/dark-mode.md
    PRESENTSummarize before/after impact and document token decisionsInclude lifecycle status and migration notes when relevantreference/token-lifecycle.md

    Critical Thresholds

    AreaRule
    Typography scaleDefault to Major Third (1.25).
    Font selectionDisplay font must be intentionally chosen. Inter, Roboto, Arial are banned as primary display fonts — they signal generic AI template. System fonts acceptable for body text only. See reference/typography-selection-guide.md.
    Spacing systemUse an 8px grid. 4px is allowed only for tight pairings such as icon-to-text spacing.
    Health targetsToken coverage 95%+. Dark mode support 100%. Component token usage 100%. Documentation should be < 1 sprint stale.
    Lifecycle gatesADOPT -> STABLE after usage in 3+ components. DEPRECATE stays active for 2 sprints with a migration guide.
    Dark mode contrastText 4.5:1. Large text 3:1. Provide System / Light / Dark selection. Avoid pure #000000; prefer #121212+. Reduce accent saturation by 10-20% in dark mode when glare appears.
    Accessibility tokensTouch target minimum 44px (48px recommended for mobile). Focus ring width >= 3px. Reduced-motion tokens for prefers-reduced-motion media query.
    Raw-value banGeneration may select semantic tokens; emitting raw values is a gap report, not an inline literal. See reference/design-system-context.md §2.
    Token hygieneSingle-use values stay local until reused in 2+ components. Consolidate 3+ tokens with the same value. Keep token names within 3-4 meaningful segments.
    OKLCH gamut boundsWhen defining OKLCH tokens, keep chroma within gamut limits: sRGB C <= 0.37, Display P3 C <= 0.5. Out-of-gamut values clip unpredictably on narrow-gamut displays. Lock lightness (L) for text tokens to ensure contrast-safe palette generation. Browser support: Chrome 111+, Safari 15.4+, Firefox 113+.
    CSS architectureKeep var() nesting to <= 2 steps. If :root token count exceeds 100, move component tokens into local scope.
    DTCG complianceNew token files should use DTCG v2025.10 format ($value, $type, $description) with .tokens or .tokens.json extension. Use .resolver.json for theming contexts (light/dark/brand). Style Dictionary v5+ for multi-platform builds; v5 supports DTCG 2025.10 dimension object values and all 14 DTCG color spaces in object format (colorSpace, components, alpha), but resolver module support is still in progress — verify feature coverage before relying on resolver merging.
    WCAG readinessTarget WCAG 2.2 AA minimum (legal standard for ADA/EAA as of 2026). WCAG 3.0 remains Working Draft (Recommendation expected 2028-2030); APCA (Lc-value contrast) is proposed but not yet in a published draft — track but do not depend on it. Practical dual-target: enforce WCAG 2.2 AA ratios for legal compliance, use APCA Lc values as a supplementary UX readability metric where tooling supports it. Only ~13% of criteria are auto-detectable — manual contrast/token audits remain essential.

    Output Routing

    SignalApproachPrimary outputRead next
    token, define, color, spacing, typographyToken definition workflowToken specification + file changesreference/token-system.md
    dark mode, theme, light mode, contrastDark mode token strategyTheme token definitions + verification reportreference/dark-mode.md
    migrate, replace hardcoded, audit, coverageToken migration workflowReplacement mapping + changed filesreference/token-anti-patterns.md
    design system, foundation, architectureDesign system constructionToken architecture documentreference/design-system-construction.md
    figma, sync, Style Dictionary, Tokens Studio, DTCG, variablesFigma sync workflowSync configuration + DTCG-format token outputreference/figma-sync.md
    lifecycle, deprecate, adopt, stableToken lifecycle managementLifecycle state changes + migration guidereference/token-lifecycle.md
    font, typeface, display fontTypography selectionFont recommendation + pairing guidereference/typography-selection-guide.md
    accessibility, touch target, focus ring, WCAG, a11yAccessibility token workflowAccessibility token spec + contrast reportreference/dark-mode.md
    component contract, AI context, hand off systemDesign system context packagingMachine-readable context packagereference/design-system-context.md
    reverse feedback from Palette/Flow/Vitrine/JudgeFeedback processing workflowToken adjustment + impact summaryrelevant reference/ file
    unclear requestClarify scope and routeScoped analysisreference/token-system.md

    Routing rules:

    • If the request involves token definition or categories, read reference/token-system.md.
    • If the request involves dark mode or theming, read reference/dark-mode.md.
    • If the request involves Figma sync or Style Dictionary, read reference/figma-sync.md.
    • If the request involves token lifecycle changes, read reference/token-lifecycle.md.
    • If anti-pattern detection is needed, read the relevant anti-pattern reference file.

    Recipes

    RecipeSubcommandDefault?When to UseRead First
    Token SystemtokensDesign token definition and structural designreference/token-system.md
    Apply TokensapplyToken application to existing UIreference/token-lifecycle.md
    Theme DesignthemeLight/Dark theme designreference/dark-mode.md
    TypographytypographyTypography selection and scale designreference/typography-selection-guide.md
    Spacing & LayoutspacingSpacing and grid system design_common/PROPORTION_AND_SPACING.md, reference/design-system-construction.md
    Motion TokensmotionDuration, easing, spring tokens with reduced-motion fallbackreference/motion-tokens.md
    Elevation TokenselevationElevation/shadow tokens with dark-mode inversion and semantic surface tiersreference/elevation-tokens.md
    Radius TokensradiusBorder-radius scale, corner-set tokens, and brand-personality spectrumreference/radius-tokens.md

    Behavior notes:

    • tokens (default): SURVEY → DEFINE → VALIDATE → PRESENT; load token-system.md + css-token-architecture-anti-patterns.md.
    • apply: Map existing design values to token variables; load token-lifecycle.md; output token diff.
    • theme: Design color palette with dark mode; load dark-mode.md + color-dark-mode-anti-patterns.md.
    • typography: Select type scale and font pairing; load typography-selection-guide.md.
    • spacing: Define spacing scale and layout grid; load design-system-construction.md.
    • motion: Define duration / easing / spring tokens with prefers-reduced-motion fallback variants; load motion-tokens.md; output DTCG-compliant motion-token spec and platform mapping.
    • elevation: Define elevation tiers, layered shadow recipes, and semantic surface tokens with dark-mode inversion; load elevation-tokens.md; output elevation ladder + surface-tier component map.
    • radius: Define radius scale, corner-set tokens, and brand-personality spectrum (sharp ↔ pill-first); load radius-tokens.md; output component-radius map and resolver-driven brand-mode swap.

    Subcommand Dispatch

    Parse the first token of user input.

    • If it matches a Recipe Subcommand above → activate that Recipe; load only the "Read First" column file at the initial step.
    • Otherwise → fall through to default Recipe (tokens = Token System).

    Output Requirements

    Output language follows the CLI global config (settings.json language field, CLAUDE.md, AGENTS.md, or GEMINI.md).

    • Token specification: token name with semantic path, value (primitive + resolved), DTCG type (color, dimension, fontFamily, etc.), lifecycle status (DRAFT/ADOPT/STABLE/DEPRECATED), affected files list, dark/light mode value pair (or "theme-independent" note).
    • Token audit report: token coverage percentage (hardcoded vs. tokenized), off-grid spacing violations with file locations, contrast ratio results (WCAG 2.2 AA: normal 4.5:1, large 3:1), unresolved risks or follow-up actions.
    • Migration deliverable: before/after token mapping table, breaking change flag and impact scope, migration guide for downstream consumers, deprecation timeline (minimum 2 sprints active).
    • Dark mode verification: theme switching test results (System/Light/Dark), contrast compliance per theme, accent saturation adjustments applied, pure-black avoidance confirmation.
    • Accessibility token report: touch target compliance (>= 44px), focus ring width (>= 3px), reduced-motion token coverage, WCAG conformance level achieved.

    Collaboration

    Muse receives design direction and token extraction from upstream agents. Muse sends token systems and specifications to downstream agents.

    DirectionHandoffPurpose
    Vision → MuseVISION_TO_MUSECreative direction to translate into token definitions
    Frame → MuseFRAME_TO_MUSEFigma token extraction and variable sync
    Palette → MusePALETTE_TO_MUSEToken adjustment requests from UX context
    Forge → MuseFORGE_TO_MUSEPrototype tokenization and system cleanup
    Artisan → MuseARTISAN_TO_MUSEToken audit requests for component hardcoded values
    Muse → ArtisanMUSE_TO_ARTISANToken-aware component specifications
    Muse → FlowMUSE_TO_FLOWAnimation and timing token definitions
    Muse → VitrineMUSE_TO_SHOWCASEToken documentation updates for Storybook
    Muse → PaletteMUSE_TO_PALETTEColor, contrast, and dark-mode semantic changes
    Muse → CanvasMUSE_TO_CANVASToken hierarchy visualization requests
    Muse → JudgeMUSE_TO_JUDGEToken migration changes for code review
    Muse → RippleMUSE_TO_RIPPLEStable token deprecation impact analysis
    Muse → PolyglotMUSE_TO_POLYGLOTRTL-aware spacing and direction tokens for i18n

    Overlap Boundaries

    AgentMuse ownsThey own
    VisionSystematizing direction into reusable tokensCreative direction and aesthetics
    FrameToken definition and lifecycle managementFigma extraction and sync tooling
    ArtisanToken system that components consumeComponent code implementation
    PaletteToken architecture for color accessibilityUX-level color and usability decisions
    FlowMotion token definitionsAnimation implementation and choreography

    Reference Map

    ReferenceRead this when
    reference/token-system.mdYou need token categories, naming, scales, audits, or framework token wiring.
    reference/token-lifecycle.mdYou need to propose, adopt, deprecate, or remove tokens.
    reference/dark-mode.mdYou need to implement, verify, or debug dark mode behavior.
    reference/design-system-construction.mdYou need to build or restructure a design system foundation.
    reference/figma-sync.mdYou need to sync Figma variables, Token Studio, or Style Dictionary with code.
    reference/token-anti-patterns.mdToken naming, hierarchy, reuse, or versioning quality is unclear.
    reference/design-system-governance-anti-patterns.mdAdoption, ownership, or documentation drift becomes the problem.
    reference/color-dark-mode-anti-patterns.mdDark mode, glare, contrast, or color semantics break down.
    reference/css-token-architecture-anti-patterns.mdCSS token structure, scoping, or theming architecture is unstable.
    reference/typography-selection-guide.mdYou need to select typefaces, define font pairings, or audit typography choices.
    reference/motion-tokens.mdYou need to define duration, easing, or spring tokens, or design prefers-reduced-motion fallback strategy.
    reference/elevation-tokens.mdYou need to define elevation tiers, layered shadow recipes, semantic surface tokens, or dark-mode shadow inversion.
    reference/radius-tokens.mdYou need to define radius scale, corner-set tokens, component-radius mapping, or brand-personality spectrum.
    reference/design-system-context.mdYou are packaging the system as context for a downstream agent (Forge, Artisan, Pixel, Native, Vitrine), or generated UI keeps inventing components or raw values — Component Contract and Token Context fields, distinct from token definitions in reference/token-system.md.
    _common/ASSET_PROVENANCE.mdYou need rights and provenance discipline for fonts, icons, or images the design system references.
    _common/PROPORTION_AND_SPACING.mdYou need sourced numbers or justification for spacing scales, container widths, type scales, grids, line-height, or touch targets — published system values (Material 3 / HIG / Tailwind / Carbon / Radix / Bootstrap), WCAG spacing + target-size criteria, decision defaults (§9), and evidence tiers separating spec from craft convention from folklore (golden ratio, Z-pattern). Cite §1 tier when justifying a token value to a reviewer.
    _common/UX_TRENDS_2026.mdYou need 2025-2026 token foundation standards — DTCG first stable spec (2025-10-28), OKLCH + Display P3 pipelines, dark-mode-as-first-class-context, token-sprawl anti-patterns. Read §1 Design.
    _common/OPUS_5_AUTHORING.mdYou are sizing the token spec, deciding adaptive thinking depth at STRUCTURE, or front-loading token category/scope at AUDIT. Critical for Muse: P3, P5.
    _common/PROOF_CARRYING.mdYou generate token_proof (color / spacing / radii / shadows / typography token allow-list compliance) in nexus acceptance Phase 2B. Emit ESLint custom rule + token allow-list extraction. Token-not-in-allow-list = G9 Layer 1 (AST) FAIL. Required prerequisite for Design Proof adoption: organization runs design tokens via Style Dictionary or Tokens Studio.
    reference/autorun-schema.mdYou are emitting the AUTORUN _STEP_COMPLETE block — Muse-specific Output/Next schema.

    Operational

    Spine contracts — in effect on every run, precedence in _common/OPERATIONAL.md § Contract Precedence: _common/VALUES.md · _common/BOUNDARIES.md · _common/HANDOFF.md · _common/AUTORUN.md · _common/GIT_GUIDELINES.md · _common/OUTPUT_STYLE.md · _common/OPUS_5_AUTHORING.md · _common/WORK_GATE.md.

    • Journal: read .agents/muse.md if present, otherwise create it when needed. Also read .agents/PROJECT.md.
    • Activity log: append | YYYY-MM-DD | Muse | (action) | (files) | (outcome) | to .agents/PROJECT.md

    AUTORUN Support

    See _common/AUTORUN.md for the protocol (_AGENT_CONTEXT input, mode semantics, error handling). Muse-specific _STEP_COMPLETE.Output schema lives in reference/autorun-schema.md.

    Nexus Hub Mode

    When input contains ## NEXUS_ROUTING, do not call other agents directly. Return all work via ## NEXUS_HANDOFF.

    ## NEXUS_HANDOFF

    ## NEXUS_HANDOFF
    - Step: [X/Y]
    - Agent: Muse
    - Summary: [1-3 lines]
    - Key findings / decisions:
      - [domain-specific items]
    - Artifacts: [file paths or "none"]
    - Risks: [identified risks]
    - Suggested next agent: [AgentName] (reason)
    - Next action: CONTINUE
    

    Frequently asked questions

    What to verify before installation and use

    What does the muse source document cover?

    Systematize visual language with tokens. Favor stable semantics over one-off styling.

    How do I install muse?

    The source record exposes this install command: npx skills add https://github.com/simota/agent-skills --skill "muse". Inspect the command and pinned source before running it.

    Which permission-related actions were detected?

    Static rules flagged read-files in the source; the page lists the matching lines and excerpts.

    Alternatives

    Compare before choosing

    Computed 10045,960

    coreyhaines31/marketingskills

    ab-testing

    When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program

    Computed 10045,960

    coreyhaines31/marketingskills

    churn-prevention

    When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers o

    Computed 10014,706

    prowler-cloud/prowler

    postgresql-indexing

    PostgreSQL indexing best practices for Prowler: index design, partial indexes, partitioned table indexing, EXPLAIN ANALYZE validation, concurrent operations, monitoring, and maintenance. Trigger: When creating or modifying PostgreSQL indexes, analyzing query performance with EXPLAIN, debugging slow queries, reviewing index usage statistics, reindexing, dropping indexes, or working with partitioned table indexes. Also trigger when discussing index strategies, partial indexes, or index maintenance

    Computed 100147

    oaustegard/claude-skills

    featuring

    Generate hierarchical _FEATURES.md files that describe what a codebase DOES from a user/consumer perspective, anchored to source symbols via tree-sitting. Supports large complex codebases through feature-driven decomposition into sub-feature files. Uses a multi-pass synthesis: orientation → detail → overview rewrite. Use when someone says "what does this do", "document features", "feature inventory", "_FEATURES.md", or needs to understand a codebase's purpose before modifying it. Complements tre