blueprint-docs-currency
Enforce same-commit landing of code and docs (APIs, formats, ADRs). Use when committing API/format changes, promoting research to docs/, or landing an ADR decision.
What this skill does
# Blueprint Docs Currency
Same-commit discipline for code and documentation. This skill is the
reusable version of claude-plugins' `.claude/rules/docs-currency.md`,
refined for blueprint-driven projects.
## When to Use This Skill
| Use this skill when… | Skip when… |
|---------------------|------------|
| Committing code that changes a public API, format spec, or error enum | Refactoring internal helpers with no external surface change |
| Promoting research findings from `tmp/` to `docs/` | Scratch work that will not ship |
| Landing an architectural decision | Implementation detail with no branching trade-off |
| Advancing a tracker entry past "in progress" | Small task completion that does not cross a phase gate |
| A reviewer flags missing documentation | Typo fixes or whitespace changes |
## The Rule
> Code + its docs land in the same commit. Research promotes to `docs/`
> before the feature advances past "in progress." ADR-worthy decisions
> land with a new or updated ADR in the same commit.
## Same-commit scope
| Change kind | Doc target |
|-------------|-----------|
| Public API / exported type | Inline docstring + reference doc under `docs/api/` (or tool-appropriate) |
| File-format spec | `docs/format-spec/<name>.md` (hand-written prose, not generated) |
| Error enum / protocol code | `docs/errors/<name>.md` or the protocol reference |
| Milestone / phase status | Feature-tracker entry + `docs/PLAN.md` if the phase advanced |
| Architectural decision | New ADR under `docs/adrs/NNNN-<title>.md` |
| New CLI flag or subcommand | README + relevant `docs/cli/` page |
Forward-reference `blueprint-plugin:blueprint-curate-docs` for how to
produce the prose that goes into `docs/ai_docs/` when the code change
surfaces an AI-context gotcha worth capturing.
## Research promotion workflow
Research findings arrive in `tmp/` (gitignored). Before the dependent
feature advances past "in progress" in the blueprint feature tracker:
1. Move the findings into `docs/` at a canonical path (e.g.
`docs/research/<topic>.md`, or directly into `docs/format-spec/<name>.md`
if the research *is* the spec).
2. If the research produced a decision, file an ADR. ADRs without a
decision record are a code smell — revert to research notes.
3. Update the feature-tracker entry with the `docs/` path in its
evidence field (`blueprint-plugin:feature-tracking` handles the
mechanical edit).
4. Only then flip the tracker status from `in_progress` to `done`.
See `blueprint-plugin:blueprint-curate-docs` for the prose-production
mechanics; see `blueprint-plugin:blueprint-sync` for the drift detection
that catches stale generated content drifting from source PRDs.
## Sidecars are not documentation
| Layer | Lives at | Authoritative? |
|-------|----------|----------------|
| `TODO.md`, feature tracker JSON | Repo root or `docs/blueprint/` | No — sidecar |
| `docs/PLAN.md`, `docs/roadmap.md` | `docs/` | Yes |
| `docs/format-spec/`, `docs/api/` | `docs/` | Yes |
| ADRs in `docs/adrs/` | `docs/adrs/` | Yes |
| `tmp/research/…` | gitignored | No — scratch |
Sidecars record priority, status, and notes for humans. If a reader
needs the information to port, debug, or onboard, it belongs in `docs/`,
not the sidecar.
## Pre-commit checklist
Before `git commit`, ask:
- [ ] Does this change the public API, file format, error enum, or milestone status?
- [ ] Same commit touches the corresponding `docs/` file?
- [ ] Decision made → new / updated ADR in the same commit?
- [ ] `tmp/research/` either empty or intentionally scratch for this change?
- [ ] Feature tracker entry's evidence field cites the new `docs/` path?
If any box is unchecked, the commit is not ready. Pattern-match on what
the code changed, then fix the doc gap in place.
## Pre-merge checklist
Before a PR's final review:
- [ ] `git log main..HEAD` — each commit that touches a scoped surface
has a same-commit doc edit
- [ ] `find tmp -type f` — empty, or the contents are scratch that
should not ship
- [ ] No `docs: follow-up` commits planned for after merge
Deferred doc follow-ups are the failure mode this skill exists to
prevent. "I'll write the spec after the code is in" is the signal to
stop and write the spec now.
## Quick Reference
| Signal | Action |
|--------|--------|
| Adding a new exported function | Same commit: update the reference doc |
| Changing a binary format header | Same commit: update `docs/format-spec/<name>.md` |
| Adding an error code | Same commit: update error enum docs |
| Choosing library A over library B | Same commit: file an ADR |
| Promoting `tmp/research/foo.md` → feature | Move to `docs/` first, advance tracker second |
## Related
- `.claude/rules/docs-currency.md` — claude-plugins' dogfood version of this rule
- `blueprint-plugin:blueprint-curate-docs` — mechanics of producing ai_docs prose
- `blueprint-plugin:blueprint-sync` — drift detection for generated docs
- `blueprint-plugin:feature-tracking` — tracker entry mechanics
- `.claude/rules/conventional-commits.md` — commit types that co-evolve with docs
> Evidence: research landed without a same-commit `docs/` update — the
> spec had to be reconstructed in a follow-up PR. The inverse pattern
> (same-commit code + spec) survived grep-based re-investigation months
> later without loss.
Related in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".