KeiSeiKit-1.0/skills/content-pipeline/SKILL.md
Parfii-bot 036bc6a52e docs: SKILL.md triggers + STATUS-TRUTH footer + phase placeholders
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>
2026-05-02 21:41:41 +08:00

63 lines
2.2 KiB
Markdown

---
name: content-pipeline
description: Use when creating content — research, outline, draft, SEO, format for platform, social promo
arguments:
- name: topic
description: Content topic or title
required: true
- name: platform
description: "Target platform: blog, medium, dev.to, docs"
required: false
- name: audience
description: Target audience
required: false
---
# Content Pipeline Workflow
## When to use
- Writing a blog post, article, or documentation page from scratch (research → outline → draft → SEO → format → social promo).
- Producing platform-targeted content for blog, Medium, Dev.to, or project docs.
- Creating launch content for a product or feature release.
## Step 1: Research
- WebSearch for existing content on the topic (top 5 results)
- Identify gaps — what's NOT covered well?
- Find data, statistics, examples to reference
- Check if project has existing content to build on
## Step 2: Outline
Structure (adapt to content type):
- Hook — why should reader care? (1-2 sentences)
- Context — background needed to understand
- Main sections (3-5, each with a clear takeaway)
- Code examples / visuals where applicable
- Conclusion with actionable next steps
Present outline to user for approval before drafting.
## Step 3: Draft
- Write in the voice/tone matching the brand
- Technical content: accurate, code-tested, no hand-waving
- Marketing content: benefit-driven, concise, scannable
- Include code blocks with language tags
- Add internal links to other project content if available
## Step 4: SEO Optimization
- Target keyword in title, H1, first paragraph
- Related keywords in H2s and body
- Meta description: <155 chars, compelling
- Internal and external links (2-3 each)
- Image alt text
## Step 5: Platform Formatting
- **Blog/Next.js:** MDX with frontmatter (title, date, tags, description)
- **Medium:** clean markdown, no custom components
- **dev.to:** frontmatter (title, published, tags, cover_image)
- **Docs:** follow existing docs structure and style
## Step 6: Social Promotion
- Generate 2-3 social snippets (for social-post skill)
- Key quote or stat for sharing
- Thread-worthy breakdown if content is long