Each skill now asks the user up front whether to produce a diagram, and in
which format (HTML default, Figma via MCP, pencil.dev via MCP, or markdown
only). The full token block + per-skill pattern CSS + structure template
is inlined in each SKILL.md per the reliability-over-composition principle.
Visual style faithfully matches the three Astro components on the live
how-to-use page — same tokens, same class names, same opacity hierarchy
for blueprint lanes (frontstage / backstage / support). Self-contained
HTML output: no external fonts, no external CSS, no JS. Light + dark via
prefers-color-scheme baked in.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
End-user testing surfaced two showstoppers with the bash path:
1. Bash tool output gets collapsed to a preview by Claude Code,
hiding most of the banner behind a "ctrl+o to expand" prompt.
2. Bash tool calls require user approval on first use, which
breaks the "confident reduction" discipline the banner aims for.
The spec anticipated this risk (§9) and allowed downgrading to
markdown-only as primary. Pivoting now. The hooks/banner.sh and
hooks/check-banner-map.sh stay in the repo as reference / future
tooling but are no longer in the /intent rendering path.
Loses indigo color (markdown can't render ANSI from model text).
Keeps: 16-mark meaningful frame, 8 categories, glyphs, wordmark,
thesis, opening question, shared left margin. All structural
identity moves intact.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds storytelling.mdc / storytelling.md and updates the four host skills
(journey, blueprint, strategize, evaluate) plus intent (anti-pattern catalog
Category 10) across Cursor and Copilot distributions. AGENTS.md and
copilot-instructions.md updated for the new skill count.
Fix plugin install failure on Claude Code 2.1.114 by removing the
manifest path overrides that triggered schema rejection on the agents
field. Source skills/ and agents/ are now the canonical distribution
for Claude Code — frontmatter lives in the source agent files, and
auto-discovery handles the rest.
- Bake frontmatter into each agents/*.md (name, description, tools,
plus model: opus for sage). Drop AGENT_META heredocs from build.sh.
- Remove skills and agents path overrides from .claude-plugin/plugin.json
and the unrecognized $schema root key from marketplace.json.
- Delete generated .claude/skills/ and .claude/agents/ trees; Claude Code
now reads source directly.
- Move agents/HOW-TO-USE.md to repo root to keep agents/ limited to real
agent files.
- Simplify build.sh to Cursor + Copilot generation only; update release
workflow zip to pack skills/ + agents/ + HOW-TO-USE.md.
- Add claude plugin validate gate to release.sh so manifest regressions
block the release before the tag goes out.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
README: fix stale Rune/Sage taxonomy (now Rune → /specify,
Sage → /philosopher) and expand the Claude Code plugin section to
mention that agents are now registered alongside skills.
HOW-TO-USE.md: new "Option 4: Claude Code plugin" deployment section
covering /plugin install and @<agent> subagent invocation.
Distributions: regenerated .claude/agents/ (new — 6 agents with
build-time frontmatter), .claude/skills/intent + measure (scope
limits + loop-back content), .cursor/rules/, and .github/ to match.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Paths filter prevented workflow from running on empty commits.
Added workflow_dispatch for manual triggering from Actions tab.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
GitHub Pages was trying to build with Jekyll. This adds:
- Astro build + deploy workflow triggered on pushes to docs/, skills/, agents/
- .nojekyll file to disable Jekyll processing
Requires GitHub Pages source set to "GitHub Actions" in repo settings.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fix race condition in build.sh (mktemp instead of hardcoded /tmp path)
- Fix file permissions (644) on strategize SKILL.md and HOW-TO-USE.md
- Standardize strategize frontmatter to multi-line description format
- Add defensive .gitignore entries (.env, *.log, *.tmp)
- Update all URLs from ghaida/claude-design-skills to ghaida/intent
- Split Cursor intent.mdc reference docs into 8 separate on-demand .mdc
files (166KB → 37KB always-loaded, 129KB loads when relevant)
- Reframe README agents section around combined-skill value
- Remove Claude Projects install instructions and agents-only release zip
- Add release.sh for automated version bumping, building, tagging, pushing
- Add stress test plan (21 scenarios across 5 tiers)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add .claude-plugin/plugin.json and marketplace.json for installation
via /plugin marketplace add ghaida/claude-design-skills
- Add version: 1.0.0 and user-invocable: true to all 15 skill frontmatters
- Add GitHub Actions release workflow that builds zip archives for all
platforms (Claude Code, Cursor, VS Code Copilot, Claude Projects)
- Update build.sh to preserve .github/workflows/ during rebuilds
- Rename "Design with Reason" to "Design with Intent" across all agents
and skills
- Add Install section to README with plugin command
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace the original 6 generic agents and skills with a comprehensive
design strategy system: 15 discipline-specific skills (strategize,
investigate, blueprint, journey, organize, articulate, evaluate, fortify,
include, transpose, localize, measure, philosopher, specify, plus the
intent foundation) and 6 named agent personas (Noor, Ember, Wren, Vigil,
Rune, Sage) with clear routing, handoffs, and shared principles.
Includes review fixes: articulate missing section, Rune clarifications,
fortify state inventory example, evaluate annotated example, measure
sample size reference table.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Ghaida Zahran