The skill was pure aesthetic prose with no self-review. This adds three
sections, reworded from cited sources and kept under 500 lines:
- Concrete anti-default moves: font-by-vibe picks, layout archetypes, type
contrast, semantic CSS-variable tokens, one orchestrated page-load.
- An objective self-critique rubric the model runs before returning (WCAG 2.2
AA contrast/semantics/alt/focus/reflow plus craft checks), framed honestly
since models tend to over-praise their own output.
- An optional, cross-platform validation note (html-validate static; pa11y or
axe for rendered DOM), including an opt-in vision-only Playwright screenshot
loop that text-only models skip.
Adds tests/frontend-design.test.mjs to guard the additions. The command is
regenerated from the skill and stays in sync.
The "Critical: only HIGH-SIGNAL issues should be flagged" block appeared
twice, back to back, in code-review's SKILL.md and command. The second copy
was a strict subset of the first (it dropped the "Concrete edge cases"
bullet), so it was pure redundancy. The duplicate is removed; the complete
first copy stays.
The skill-lint suite gains a per-skill "no duplicated block" check (no
non-empty line >= 50 chars repeats within a SKILL.md or its command), which
catches this class of copy-paste error. SKILL.md and command stay in sync.
A generation step had truncated nine command descriptions at ~200
characters, cutting them mid-sentence. Each commands/*.md description is
restored to match its SKILL.md source, so the slash-command menu shows the
full text and skill and command stay in sync.
Adds a zero-dependency node:test suite (tests/skill-lint.test.mjs) that
enforces the invariants going forward: directory name matches the
frontmatter name and slug regex, description length within 1..1024 and not
truncated, SKILL.md body under 500 lines, and each command inlines its
SKILL.md body, shares its description, and ends with $ARGUMENTS. A GitHub
Actions workflow runs the suite on every push and pull request.
The skill described OpenCode's rules loading as a priority order between
AGENTS.md and CLAUDE.md. The actual behavior is first-match-wins per
directory: when both files coexist in the same directory, OpenCode loads
only AGENTS.md and silently ignores the CLAUDE.md.
This corrects the behavior description, replaces the tip that suggested
keeping an orphaned CLAUDE.md, and adds the shadowed-CLAUDE.md case to the
list of issues to flag. The skill's own description is also rewritten to be
more precise and trigger-specific; in the command it was previously
truncated mid-sentence. SKILL.md and command stay in sync.
opencode-power-pack bundles eleven Claude Code skills as an OpenCode plugin
under one config line, with each skill also exposed as a slash command.
Skills (by category):
Review
code-review multi-agent PR review with cross-check pass and
concrete reproduction scenarios
security-review OWASP-bucketed three-stage filtering with mandatory
PoC per finding
Feature dev
feature-dev seven-phase guided workflow
code-explorer deep codebase analysis sub-task
code-architect decisive architecture blueprint sub-task
code-reviewer two-pass adversarial review sub-task
Design
frontend-design distinctive, production-grade UI generation
Authoring
mcp-builder build high-quality MCP servers (Python or TypeScript)
skill-creator author new SKILL.md files
Project memory
agents-md-improver audit and update AGENTS.md / CLAUDE.md
agents-md-revise capture session learnings into the rules file
Architecture:
- .opencode/plugins/opencode-power-pack.js auto-registers skills/ via
config.skills.paths.push() (live config singleton modification, pattern
adapted from obra/superpowers).
- skills/<name>/SKILL.md hold the workflows the model executes.
- commands/<name>.md ship physical slash command files that inline the
full SKILL.md content, so the model receives the actual workflow as
its prompt rather than a meta-instruction. Symlinked into
~/.config/opencode/commands/ during install.
Almost all skill content is ported or translated from upstream Anthropic
projects (claude-code/plugins, skills, claude-code-security-review,
claude-plugins-official). The plugin loader pattern is adapted from
obra/superpowers. See README.md -> Acknowledgments for per-skill
attribution; each SKILL.md frontmatter also carries a license field
naming its specific upstream.