Group G — markdown tech-debt cleanup (post-audit 2026-05-02).
- 36 SKILL.md files: added "## When to use" section. Was missing across the
catalog; orchestrator routing by keyword could not auto-dispatch.
- 20 code-implementer agent .md files: added Output Footer block prescribing
RULE 0.16 STATUS-TRUTH MARKER schema in agent's final report. Previously only
code-implementer-rust.md had it; other 27 language/role variants were silent
about the marker, breaking RULE 0.16 §3 status-truth aggregation for non-Rust
batches.
- skills/site-create/: added phase-5-preview.md and phase-6-deploy.md skeleton
files. SKILL.md table-of-contents referenced 7 phases; only 5 existed on disk.
- skills/{ai-animation,rag-pipeline}/skill.md: added migration banner comment
noting they should be SKILL.md (canonical filename). Case-rename via git is a
separate orchestrator task (macOS APFS is case-insensitive; Linux deploy needs
explicit rename).
- 3 deprecated skills (site-builder, competitor-analysis, design-inspiration):
added concrete removed-after dates (was vague "before v2").
- docs/CONVERGENCE-PLAN.md:129: TBD on _blocks/evidence-grading.md duplicate
resolved (file exists, not duplicated).
- docs/DNA-INDEX.md: count edits made then overwritten by auto-encyclopedia-refresh
hook during agent run. The .kei-registry-ignore files in test fixtures (Group F)
are the structural fix; kei-registry walker implementation is the follow-up.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
3.6 KiB
3.6 KiB
| name | description | arguments | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| batch-workflow | Use when running multi-skill pipelines — new-feature, marketing-launch, design-to-code, web-creation, full-audit, rag-setup workflows |
|
Batch Workflow — Multi-Skill Pipelines
When to use
- Running a multi-step workflow that chains several skills together (new-feature, marketing-launch, design-to-code, web-creation, full-audit, rag-setup).
- Kicking off a named workflow pipeline rather than invoking individual skills manually.
- Orchestrating sequential tasks that each depend on the output of the previous step.
Available Workflows
new-feature
Full feature development pipeline:
/brainstorming— explore requirements and design/test-gen— write tests for the feature (TDD)- Implementation (manual or via
/quick-apifor API features) /refactor— if code needs restructuring/pr-review— self-review before committingdoc-writeragent — update docs
marketing-launch
Product launch content pipeline:
/competitor-analysis— understand the landscape/landing-page— create product landing page/content-pipeline— write launch blog post/social-post platform=all— create social media posts/email-sequence type=launch— create launch email sequence/seo-audit— audit the landing page
design-to-code
Design implementation pipeline:
/figma-to-code— convert Figma design to code/design-system— extract/create tokens if needed/ui-component— build reusable components/responsive-audit— verify responsiveness
web-creation
Elite website pipeline (7-level constructor):
- Brief & goal definition (manual — product, audience, goal, tone)
/competitor-analysis— market positioning, 3-5 competitors/design-inspiration— reference board from awwwards/godly/dribbble/21st.dev/site-teardown— deconstruct best reference into recipe + tokens/frontend-design— design direction from tokens + archetype/design-system— create design system from tokens/landing-page recipe=<type>— implement page with recipe- Animation skills as needed (
/scroll-animation,/motion-design,/web-effects) /web-assets pipeline— optimize all images, fonts, video/a11y-audit scan— WCAG 2.2 AA compliance/seo-audit— meta, schema, OG tags/responsive-audit— 6 breakpoints/perf-audit— Lighthouse >90/web-deploy— deploy to Cloudflare Pages
rag-setup
RAG knowledge base setup pipeline:
/rag-pipeline init— choose embedding provider + vector DB- Document ingestion — PDF/text/image processing
/rag-pipeline ingest— chunk, embed, store/rag-pipeline search— test retrieval quality- Integration — connect to app (tool_use or context injection)
full-audit
Comprehensive project audit:
/perf-audit target=full— performance check/seo-audit— SEO check (if web project)/responsive-audit— responsive check (if web project)/a11y-audit scan— accessibility check (if web project)auditoragent — Constructor Pattern audit
Execution
- Present the workflow steps to user BEFORE starting
- Execute skills sequentially, passing context between them
- After each skill: report results, ask if user wants to continue or skip
- Track progress in TODO tasks