MCPInstall

ss-resolve

Compile the effective StyleSeed rule bundle for one artifact, or inspect install and evidence health read-only. Use before setup or build, or to diagnose rule drift.

Installs
571
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/bitjaru/styleseed --skill ss-resolve
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads ss-resolve automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Before this workflow, follow the once-per-session update preflight.

Resolve effective StyleSeed context

Use the bundled scripts/resolve-context.mjs; do not hand-compose the rule stack.

  1. Resolve the project boundary first: if either .styleseed/project.json or .styleseed/artifacts/index.json exists, require a complete, valid registry. Do not fall back to STYLESEED.md on a registry error. Only use that lock when no registry exists.
  2. Keep the working directory at the user's project root. Invoke the script by its installed path; do not cd into the skill directory.
  3. Legacy single-artifact projects should prefer --from-lock STYLESEED.md. Registry projects use .styleseed/project.json plus .styleseed/artifacts/*.json and must resolve with --artifact or --all; in registry mode, edit project-owned config instead of passing selection overrides.
  4. Read the emitted bundle before building: legacy writes .styleseed/effective-rules.md; registry writes .styleseed/bundles/<artifact-id>.md.
  5. Preserve the manifest output: legacy uses .styleseed/manifest.json; registry uses .styleseed/manifests/<artifact-id>.json.
  6. Use --check to detect context drift without rewriting files.

For spacing recommendations and scoped control, see the spatial roles guide. Optional project/artifact spacing compiles into a role table and artifact-scoped CSS in the bundle. recommend-spacing.mjs --project-root . --artifact <id> emits a read-only starting proposal; it does not inspect or rewrite implementation tokens and does not establish design acceptance. Optional --measurement <project-relative-report.json> adds source-bound rendered diagnostics; stale or inconsistent reports are rejected, and starting values remain explicitly heuristic.

For installation or project-health questions, run the read-only diagnostic first:

For a requested legacy-to-registry migration, inspect migrate-project.mjs --dry-run first. Follow the reviewed migration guide for the plan format and apply sequence. The bare --write path deliberately refuses unreviewed defaults. Applying a migration requires a complete human-reviewed plan, the current lock hash, a one-to-one section-to-artifact mapping, and --confirm-plan matching that plan's exact hash. A valid schema or dry-run is not proof that the design decisions were preserved; never infer approval or run a write from a diagnosis request.

node <installed-ss-resolve>/scripts/styleseed-doctor.mjs --project-root . --json

It checks the local distribution inventory, project configuration, compiled rules, and stored evidence against current inputs. Use --artifact <id> to narrow a registry check. It never sets up, migrates, recompiles, renders, or updates the project. Follow its next actions only within the user's authorization. Exit 0 means current evidence for all selected artifacts, not an independent visual judgment; exit 1 means attention needed; exit 2 means invalid invocation. Legacy projects can have current rules while evidence remains unsupported. Installation integrity does not prove host discovery, publisher authenticity, or the latest upstream revision.

node <installed-ss-resolve>/scripts/resolve-context.mjs \
  --from-lock STYLESEED.md \
  --agent codex

Registry project:

node <installed-ss-resolve>/scripts/resolve-context.mjs \
  --project-root . \
  --artifact app-dashboard \
  --agent codex

Without a lock:

node <installed-ss-resolve>/scripts/resolve-context.mjs \
  --agent claude \
  --grammar operations-console \
  --adapter product-ui \
  --domain saas \
  --page dashboard \
  --recipe enterprise-workbench \
  --palette cobalt-instrument \
  --key-color "#175CD3" \
  --palette-character balanced \
  --palette-mode light \
  --palette-harmony auto \
  --surface-temperature cool \
  --profile swiss

Use --list to print supported IDs. --recipe auto maps the selected grammar to a maintained default; --palette auto maps that recipe to a contrast-verified semantic palette. Pass explicit values when the product needs a different morphology or color posture. The default output directory is .styleseed/ in the project root. For a project-local reference grammar, pass reference:<slug> and ensure .styleseed/rulesets/<slug>/RULESET.md exists. Registry projects require the full six-file reference contract: RULESET.md, tokens.json, evidence.json, checks.md, reference-board.html, and adapter.json.

When a key color is present in flags or the lock, the resolver uses the shared OKLCH generator and writes .styleseed/palette.json plus .styleseed/palette.css. The manifest records the generation inputs. The maintained recipe still supplies product posture and semantic restrictions; its fixed hex values become fallbacks rather than overriding the generated system.

Do not load llms-full.txt after a bundle resolves successfully. Load a larger source document only when the bundle names an unresolved ambiguity that requires it.

FAQ

What does the ss-resolve skill do?

Compile the effective StyleSeed rule bundle for one artifact, or inspect install and evidence health read-only. Use before setup or build, or to diagnose rule drift.

How do I install ss-resolve?

Run npx skills add https://github.com/bitjaru/styleseed --skill ss-resolve in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/ss-resolve/ (personal) or .claude/skills/ss-resolve/ (project).

Which AI agents can use ss-resolve?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is ss-resolve safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains ss-resolve?

It is published by bitjaru in bitjaru/styleseed. It has 571 recorded installs.

More from bitjaru/styleseed

View all →

ss-audit

bitjaru/styleseed

Audit screens for UX issues using Nielsen's heuristics and modern mobile UX best practices

Security864 installs

ss-review

bitjaru/styleseed

Review UI code for design system compliance, accessibility, and best practices

ss-setup

bitjaru/styleseed

Configure StyleSeed by selecting the output grammar, domain, page type, brand recipe, semantic palette recipe, optional aesthetic profile, and bounded brand tokens before scaffolding a first screen.

Marketing & SEO863 installs

ss-a11y

bitjaru/styleseed

Audit a component or page for accessibility issues and fix them

Frontend & Design862 installs

ss-lint

bitjaru/styleseed

Quick automated lint — detects common design system violations in seconds

ss-feedback

bitjaru/styleseed

Add appropriate user feedback states (loading, success, error, empty) to a component or page

Frontend & Design852 installs

Popular education & science skills

View category →

teach

mattpocock/skills

Teach the user a new skill or concept, within this workspace.

Education & Science874K installs

scaffold-exercises

mattpocock/skills

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.

Education & Science488.2K installs

paper-context-resolver

lllllllama/rigorpilot-skills

Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.

Education & Science478.3K installs

caveman-learn

juliusbrussee/caveman

Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.

Education & Science107.9K installs

gsap-plugins

greensock/gsap-skills

Official GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer, SplitText, ScrambleText, SVG and physics plugins, CustomEase, EasePack, CustomWiggle, CustomBounce, GSDevTools. Use when the user asks about a GSAP plugin, scroll-to, flip animations, draggable, SVG drawing, or plugin registration.

Education & Science67.9K installs

teach-impeccable

pbakaus/impeccable

DEPRECATED: Use /impeccable teach instead. This command has been folded into the impeccable skill.