Skip to content

bestdeejay-design/agent-skills / skills/docs-product

docs-product

Verified

Product documentation branch — the 'why' and 'what' of a project: VISION.md, PRD.md, ROADMAP.md, FEATURES.md. Written from an idea forward, before engineering docs. Order: VISION -> PRD -> ROADMAP -> FEATURES. Full catalog + checklist in references/product-docs.md, templates in templates/. Triggers: 'продуктовая документация', 'vision', 'prd', 'роадмап', 'roadmap', 'фичи документация', 'product docs', 'требования к продукту', 'документация продукта'.

Docs Product — product documentation («why» & «what»)

Use this skill to write the product-facing documents: vision, requirements, roadmap, feature catalog. Written from an idea forward — before (or in parallel with) engineering docs.

When to use

  • A project needs its product docs: VISION, PRD, ROADMAP, FEATURES.
  • User asks for "продуктовая документация", "vision", "prd", "роадмап", "требования к продукту", "product requirements".
  • Requirements must become the input for engineering docs.

Do NOT use

  • For engineering docs (architecture, ADR, tests, dev guide, map) — that is docs-project.
  • For the meta-guide (phases, levels L1/L2/L3, completeness checklist) — docs-system.

Which docs belong here

FilePurposeWhenTemplate
docs/VISION.mdWhy the product exists: audience, problem, value, principles, scope, long-term successPhase 1 — first, stays stabletemplates/VISION.tmpl
docs/PRD.mdWhat we build: functional + non-functional requirements, priorities, acceptance criteria, success metrics, user storiesAfter VISION, before architecturetemplates/PRD.tmpl
docs/ROADMAP.mdWhat ships when: milestones, value per milestone, proof (metrics)Phase 2+, updated each milestonetemplates/ROADMAP.tmpl
docs/FEATURES.mdFeature catalog + status (✅/📋) — the bridge to engineeringFrom requirements, kept currenttemplates/FEATURES.tmpl

The golden chain: VISION → PRD → ROADMAP → FEATURES. Vision spawns requirements, requirements spawn the plan and the feature catalog. Nothing is written "from the end".

Order of writing

  1. VISION — can you state the product in 1–2 sentences? If not, stop and clarify before writing anything else.
  2. PRD — goals/non-goals, stories with priorities, functional + non-functional requirements, acceptance criteria, success metrics (a milestone without a metric is a wishlist).
  3. ROADMAP — order the PRD's milestones by value (not effort), each with a target date, features, and proof.
  4. FEATURES — the living status board of every feature, ✅/📋 only against reality. This doc hands the product requirements to the engineering side.

Links across the boundary (with docs-project)

Engineering docTakes from productGives back
ARCHITECTURE.mdPRD non-functional requirementscomponent decisions → PRD "technical notes"
TEST_CASES.mdacceptance criteriaproof that a story is done
IMPROVEMENTS.mdroadmap drift (missed dates, changed scope)prioritized fix plan → next milestone
REVIEW.mdany doc-vs-reality mismatchreconciled product/eng truth

Checklist (product side)

  • VISION: 1 paragraph; audience named; explicitly listed out-of-scope items.
  • PRD: every story has a priority (MoSCoW/P0–P2) and links to a feature.
  • PRD: success metrics present (baseline → target) — not "quality" in prose.
  • ROADMAP: milestones ordered by value; each has a date/target + a metric.
  • FEATURES: ✅/📋 statuses match reality (no wishlist-only catalog).

Rule: product docs answer «why» and «what»; engineering docs answer «how». If a doc has no reader and no question it answers — it does not belong.

Boundaries

  • Do not use for implementation/runbook documentation; use docs-project.

Evidence and completion gate

Ground recommendations in the supplied repository or brief. State assumptions, missing inputs, and unresolved risks. Return a concrete artifact or checklist with an owner/action for each open item, then verify that the result answers the requested goal rather than merely repeating the framework.

rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 197kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 197kUpdated Claude CodeCodexVerifiedInstall