Skip to content

sifter-ai/sifter / .agents/skills/sdd

Story Driven Development workflow. Use this skill whenever working in a project that has `.sdd/config.yaml`, or when the user mentions SDD, sdd sync, story driven development, spec-driven development, change requests, bugs, or asks to implement a feature described in `product/` or `system/`. Also trigger on phrases like "sync the docs", "mark synced", "apply this CR", "fix this bug" when an SDD project is detected.

FileKindSize
SKILL.mdskill md4.8 KB
references/bugs.mdmarkdown729 B
references/change-requests.mdmarkdown997 B
references/file-format.mdmarkdown1.8 KB

references/file-format.md

View on GitHub
# File Format and Status Lifecycle

## YAML Frontmatter

Every `.md` file in `product/` and `system/` must start with this YAML frontmatter:

```yaml
---
title: "File title"
status: new
author: ""
last-modified: "2025-01-01T00:00:00.000Z"
version: "1.0"
---
```

## Status values

- **`new`** — new file, needs to be implemented
- **`changed`** — modified since last sync, code needs updating
- **`deleted`** — feature to be removed, agent should delete related code
- **`synced`** — already implemented, up to date

## Version

Patch-bump on each edit: 1.0 → 1.1 → 1.2

## Last-modified

ISO 8601 datetime, updated on each edit.

## How sync works

`sdd sync` generates a structured prompt for the agent based on pending files:

- **`new` files**: the agent reads the full documentation and implements it from scratch
- **`changed` files**: SDD uses `git diff` to compute what changed in the documentation since the last commit, and includes the diff in the sync prompt — this way the agent sees exactly what was modified and can update only the affected code
- **`deleted` files**: the agent removes the related code

This is why **committing after every mark-synced is mandatory** — the git history is what SDD uses to detect changes.

## UX and screenshots

When a feature has UX mockups or screenshots, place them next to the feature doc:

- **Simple feature** (no screenshots): `product/features/auth.md`
- **Feature with screenshots**: use a folder with `index.md`:

```
product/features/auth/
  index.md          ← feature doc
  login.png         ← screenshot
  register.png      ← screenshot
```

Reference images in the markdown with relative paths:

```markdown
## UX

![Login screen](login.png)
![Register screen](register.png)
```

Both formats work — use a folder only when you have screenshots or multiple files for a feature.
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: 471kUpdated 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: 198kUpdated 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: 198kUpdated 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: 198kUpdated Claude CodeCodexVerifiedInstall