Agent skill

Sdd

A skill your agent uses when the user wants a written spec, acceptance criteria, or a task graph before a non-trivial implementation, or runs the WrongStack /sdd workflow.

MITAuto-check passedProduct & Project Management

Install Sdd

skills CLI

$ npx skills add WrongStack/WrongStack --skill sdd -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install WrongStack/WrongStack sdd --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/core/skills/sdd .claude/skills/sdd && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "sdd" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/sdd into .claude/skills/sdd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/sdd

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add WrongStack/WrongStack --skill sdd -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install WrongStack/WrongStack sdd --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/core/skills/sdd .agents/skills/sdd && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "sdd" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/sdd into .agents/skills/sdd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add WrongStack/WrongStack --skill sdd -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install WrongStack/WrongStack sdd --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/core/skills/sdd .cursor/skills/sdd && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "sdd" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/sdd into .cursor/skills/sdd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/WrongStack/WrongStack.git --path packages/core/skills/sdd

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add WrongStack/WrongStack --skill sdd -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install WrongStack/WrongStack sdd --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/core/skills/sdd .gemini/skills/sdd && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "sdd" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/sdd into .gemini/skills/sdd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install WrongStack/WrongStack sdd

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add WrongStack/WrongStack --skill sdd -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/core/skills/sdd .github/skills/sdd && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "sdd" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/sdd into .github/skills/sdd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add WrongStack/WrongStack --skill sdd -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install WrongStack/WrongStack sdd --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/core/skills/sdd .opencode/skills/sdd && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "sdd" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/sdd into .opencode/skills/sdd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: sdd
GitHub stars: 370
Token cost: ~1.7k tokens
SKILL.md length: 785 words
Files: 2
Skills in repo: 38
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

A skill your agent uses when the user wants a written spec, acceptance criteria, or a task graph before a non-trivial implementation, or runs the WrongStack /sdd workflow.

Works in 6 steps: Every non-trivial task needs a spec… → Spec must have acceptance criteria —… → Record real dependencies between tasks,… → …
The user wants a written spec
SKILL.md covers Overview, Rules, When to use and The SDD workflow, plus 10 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Sdd is an agent skill from WrongStack/WrongStack. Use this skill when the user wants a written spec, acceptance criteria, or a task graph before a non-trivial implementation, or runs the WrongStack /sdd workflow. Triggers: user says "/sdd", "spec", "specification", "task graph", "SDD", "acceptance criteria".

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `SKILL.save.md`).

It sits in Product & Project Management, covering User stories. The repository describes itself as: An AI coding agent that reads your code, edits files, runs commands, and reasons through bugs — across a terminal REPL, a full-screen TUI, and a browser UI, while you keep your… The licence is MIT.

When your agent uses it

The user wants a written spec
Acceptance criteria
A task graph before a non-trivial implementation
Runs the WrongStack /sdd workflow

Example prompts

“specification”
“task graph”
“acceptance criteria”
“/sdd”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

Every non-trivial task needs a spec before writing code — you'll rewrite it anyway.
Spec must have acceptance criteria — without them, you can't know when it's done.
Record real dependencies between tasks, and only real ones — unchained tasks are the ones that can run in parallel.
Spec must be specific: "Users authenticate via OAuth2 with PKCE" not "improve auth".
Skipping /sdd for urgent tasks backfires — the spec is what makes "urgent" possible.
When the spec reveals a multi-file refactor, delegate to refactor-planner first.

What it can do on your machine

Read from SKILL.md and the folder at commit 57f6018. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sdd loads about 1.7k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 785 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~66
When it runs · the whole SKILL.md, loaded when a task matches: ~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from WrongStack/WrongStack at commit 57f6018, republished under its MIT licence (© WrongStack). 785 words, ~1,674 tokens.

Download SKILL.mdSave it as .claude/skills/sdd/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: sdd
description: Use this skill when the user wants a written spec, acceptance criteria, or a task graph before a non-trivial implementation, or runs the WrongStack /sdd workflow. Triggers: user says "/sdd", "spec", "specification", "task graph", "SDD", "acceptance criteria".
version: 2.1.0
required-capabilities: work.plan, filesystem.write

Spec-Driven Development — WrongStack

Overview

Every non-trivial change starts with a spec. The spec is the source of truth — it defines what to build, how to verify it, and what counts as done. SDD uses /sdd slash commands to create specs, generate task graphs, and track execution.

Rules

Every non-trivial task needs a spec before writing code — you'll rewrite it anyway.
Spec must have acceptance criteria — without them, you can't know when it's done.
Record real dependencies between tasks, and only real ones — unchained tasks are the ones that can run in parallel.
Spec must be specific: "Users authenticate via OAuth2 with PKCE" not "improve auth".
Skipping /sdd for urgent tasks backfires — the spec is what makes "urgent" possible.
When the spec reveals a multi-file refactor, delegate to refactor-planner first.

When to use

New feature implementation
Bug fix with complexity
Refactoring with scope
Any task requiring more than 1 hour

The SDD workflow

1. /sdd new [title]          → Build spec from questions
2. /sdd tasks <id>           → Generate task graph from spec
3. /sdd graph <id>           → Visualize dependencies
4. /sdd critical <id>        → Find bottlenecks
5. /sdd execute <id>         → Run tasks (or execute manually)

Task lifecycle commands

Command	What it does
`/sdd tasks`	Show task list with progress bar (sorted: in_progress → pending → review → blocked → failed → completed)
`/sdd next`	Show next executable task + blockers
`/sdd done <N>`	Complete a task (by number or fuzzy title match)
`/sdd skip <N>`	Skip a task back to pending
`/sdd fail <N>`	Mark a task as failed
`/sdd review <N>`	Send a task to review
`/sdd edit <N> <text>`	Edit task title (short text) or description (long text)
`/sdd undo`	Undo last task completion
`/sdd graph`	ASCII task dependency visualization
`/sdd critical`	Critical path analysis + bottlenecks

Spec templates

Template	Best for
`feature`	New feature development
`bugfix`	Bug fix with root cause analysis
`refactor`	Code refactoring with goals
`infra`	Infrastructure/tooling changes
`integration`	External service integration
`cli-command`	New CLI commands/slash commands

Spec structure

A complete spec has:

Overview — What problem does this solve?
Requirements — [priority] description format
Architecture — High-level design (if needed)
API Design — Endpoints, inputs, outputs (if applicable)
Acceptance Criteria — How do we know it's done?

Requirement format

[critical] Users can authenticate with OAuth2
[high] Rate limiting: 100 req/min per user  
[medium] Response time < 200ms p95
[low] Support dark mode

Task graph generation

Each requirement generates one or more tasks. Tasks have states:

pending → in_progress → review → completed
              ↓
           blocked (waiting on dependencies)
              ↓
           failed

Critical path

The critical path finds:

Bottleneck tasks blocking the most downstream work
Parallel groups that can run concurrently
Ready tasks that can start immediately
Execution order respecting all dependencies

Goal & Eternal Mode

/sdd pairs with /goal for autonomous execution:

Command	What it does
`/goal set <text>`	Set an autonomous mission
`/goal pause`	Pause at end of current iteration
`/goal resume`	Resume a paused goal
`/goal journal [N]`	Show recent journal entries
`/goal clear`	Clear goal and stop eternal mode
`/autonomy eternal`	Run goal loop indefinitely
`/autonomy stop`	Stop eternal mode

Eternal stage flow: decide → execute → reflect → sleep | paused | stopped Stage shown in real-time. Pause stops after current iteration completes.

Show full SKILL.md (331 more words)Show less

Anti-patterns

Writing code before the spec — you'll rewrite it anyway
Spec that's too vague — "improve auth" is not a spec, "Users authenticate via OAuth2 with PKCE" is
Invented dependencies — chaining independent tasks serializes work that could run in parallel
Spec without acceptance criteria — how do you know when it's done?
Skipping /sdd for urgent tasks — the spec is what makes "urgent" possible

Out of scope

Don't start coding before the spec exists. You'll rewrite the code anyway — the spec is what makes the rewrite possible. SDD comes first or the spec is fiction.
Don't accept a spec without acceptance criteria. "Done" must be a checkable state. Without criteria, the task has no formal end and the verifier has nothing to run.
Don't write vague requirements. "Improve auth" is not a requirement; "Users authenticate via OAuth2 with PKCE, sessions expire after 24h" is. If a requirement can't be tested, it's not a requirement.
Don't skip /sdd because the task is urgent. Urgency without a spec produces urgency-shaped rework. The spec is what makes "urgent" possible to ship correctly.
Don't start a multi-file refactor from SDD. When the spec reveals a refactor, delegate to refactor-planner for the phased plan. SDD defines the goal; refactor-planner sequences the work.
Don't execute the task graph yourself unless the user asks. SDD produces the plan and task graph; an executor (the leader, a subagent, or the user) picks it up.

Before returning

Spec has explicit acceptance criteria the verifier can run as commands
Every requirement is specific enough to be tested, not "improve X"
Real dependencies recorded; independent tasks left unchained so they can run in parallel
Spec template matches the work type (feature/bugfix/refactor/infra/integration/cli-command)
Multi-file refactors are routed to refactor-planner, not absorbed into SDD tasks
Critical path called out; bottlenecks named; parallel groups identified

Skills in scope

refactor-planner — when the spec reveals a multi-file refactor
bug-hunter — when a bugfix spec needs a root cause analysis section
multi-agent — for executing parallel task groups
output-standards — for standardized <nextsteps> formatting

Files

SKILL.md and 1 other file in packages/core/skills/sdd of WrongStack/WrongStack.

SKILL.md
SKILL.save.md

Open the folder on GitHubat commit 57f6018

Compare with similar skills

Sdd next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sdd compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Sdd this skillWrongStack/WrongStack	370	—	~1.7k	Automated safety check: Pass	MIT	yesterday
User Story Writerdeanpeters/Product-Manager-Skills	7.2k	2 repos	~2.9k	Automated safety check: Pass	Custom licence	1 mo ago
To Specbestofjs/bestofjs	3.1k	22 repos	~757	Automated safety check: Pass	MIT	4 days ago
Walking Skeleton Roadmap Scopingprime-radiant-inc/iterative-development	181	—	~1.7k	Automated safety check: Pass	Apache-2.0	4 mo ago
Design Sprintwondelai/skills	2.4k	—	~3.8k	Automated safety check: Pass	MIT	28 days ago
Execute Issuelbedner/aegis-stack	143	—	~1.1k	Automated safety check: Pass	MIT	today

Similar skills

User Story Writer
deanpeters/Product-Manager-Skills
Writes user stories in Mike Cohn's format with Gherkin acceptance criteria, turning user needs into development-ready work with testable conditions.
7.2k GitHub starsUsed in 2 repos~2.9k tokens
Product & Project ManagementAuto-check passed
To Spec
bestofjs/bestofjs
Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
3.1k GitHub starsUsed in 22 repos~757 tokens
Product & Project ManagementAuto-check passed
Walking Skeleton Roadmap Scoping
prime-radiant-inc/iterative-development
Turns extracted requirements into a roadmap by choosing a walking skeleton iteration with its first journey scenario and ordering the remaining work into follow-on iterations.
181 GitHub stars~1.7k tokensUpdated 4 mo ago
Product & Project ManagementAuto-check passed
Design Sprint
wondelai/skills
Run a structured 5-day process to prototype, test, and validate product ideas with real users.
2.4k GitHub stars~3.8k tokensUpdated 28 days ago
Product & Project ManagementAuto-check passed
Execute Issue
lbedner/aegis-stack
A skill your agent uses when handed a GitHub issue (number or URL) to execute end to end.
143 GitHub stars~1.1k tokensUpdated today
Product & Project ManagementAuto-check passed
Refactor Design Report
penwyp/ClaudePreference
Produce a professional, code-grounded refactor or implementation design report from identified technical problems, product gaps, review findings, architecture concerns, or frontend-backend contract…
136 GitHub stars~1.4k tokensUpdated 4 mo ago
Product & Project ManagementAuto-check passed

More from WrongStack/WrongStack

All 38 skills in this repo

Design Craft
WrongStack/WrongStack
Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique.
370 GitHub stars~2k tokensUpdated yesterday
Auto-check passed
Design Critique
WrongStack/WrongStack
A skill your agent uses to audit an interface that already exists and say precisely why it looks generated, templated, or unfinished — a scored rubric across composition, typography, color, states…
370 GitHub stars~3k tokensUpdated yesterday
Auto-check passed
Mailbox Bridge
WrongStack/WrongStack
A skill your agent uses when external coding agents (Claude Code, Aider, custom scripts) need to participate in the project's shared WrongStack mailbox, or when a user asks to "expose the mailbox"…
370 GitHub stars~3.9k tokensUpdated yesterday
Auto-check passed
Multi Agent
WrongStack/WrongStack
A skill your agent uses whenever work can be split across multiple AI agents running in parallel, or when orchestrating leader/worker patterns in WrongStack.
370 GitHub stars~3.6k tokensUpdated yesterday
Auto-check passed
Web Platform Baseline
WrongStack/WrongStack
Use this skill before asserting that a CSS, HTML or accessibility capability is available, unavailable, or the right tool — it carries dated, refreshable platform facts and refuses to let stale…
370 GitHub stars~1.6k tokensUpdated yesterday
Auto-check passed
Wrongstack Mailbox
WrongStack/WrongStack
A skill your agent uses when the user wants to communicate with WrongStack's shared project mailbox from outside WrongStack — read messages sent by WrongStack agents, send replies, broadcast to all…
370 GitHub stars~3.5k tokensUpdated yesterday
Auto-check passed

Questions about Sdd

What does Sdd do?

A skill your agent uses when the user wants a written spec, acceptance criteria, or a task graph before a non-trivial implementation, or runs the WrongStack /sdd workflow. Sdd is an agent skill from WrongStack/WrongStack. Use this skill when the user wants a written spec, acceptance criteria, or a task graph before a non-trivial implementation, or runs the WrongStack /sdd workflow.

When should I use Sdd?

Sdd fits situations like: the user wants a written spec; acceptance criteria; A task graph before a non-trivial implementation; runs the WrongStack /sdd workflow.

How do I install Sdd in Claude Code?

Run `npx skills add WrongStack/WrongStack --skill sdd -a claude-code`. Or copy the skill folder (packages/core/skills/sdd in WrongStack/WrongStack) into .claude/skills/sdd in your project. Claude Code loads it when a task matches its description.

How do I install Sdd in Codex?

Run `npx skills add WrongStack/WrongStack --skill sdd -a codex`. Or copy the skill folder (packages/core/skills/sdd in WrongStack/WrongStack) into .agents/skills/sdd in your project. Codex loads it when a task matches its description.

Can I use Sdd in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add WrongStack/WrongStack --skill sdd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sdd, .gemini/skills/sdd, .github/skills/sdd and .opencode/skills/sdd in your project.

What does Sdd need to run?

SKILL.md names no scripts, command-line tools or credentials: Sdd is instructions for the agent only.

Does Sdd access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sdd safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Sdd use?

Sdd is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sdd use?

About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Sdd?

Skills that share tags, products or a category with Sdd: User Story Writer (deanpeters/Product-Manager-Skills, 7.2k stars), To Spec (bestofjs/bestofjs, 3.1k stars), Walking Skeleton Roadmap Scoping (prime-radiant-inc/iterative-development, 181 stars) and Design Sprint (wondelai/skills, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sdd?

WrongStack (a GitHub organization) maintains it in WrongStack/WrongStack, which has 370 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on October 7, 2026.

Source: WrongStack/WrongStack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Sdd

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Spec-Driven Development — WrongStack

Overview

Rules

When to use

The SDD workflow

Task lifecycle commands

Spec templates

Spec structure

Requirement format

Task graph generation

Critical path

Goal & Eternal Mode

Anti-patterns

Out of scope

Before returning

Skills in scope

Files

Compare with similar skills

Similar skills

More from WrongStack/WrongStack

Related

Questions about Sdd