ae-sdd-discovery
Discover high-level architectural requirements for change-set specs
Best use case
ae-sdd-discovery is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Discover high-level architectural requirements for change-set specs
Teams using ae-sdd-discovery should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ae-sdd-discovery/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ae-sdd-discovery Compares
| Feature / Agent | ae-sdd-discovery | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Discover high-level architectural requirements for change-set specs
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# SDD Discovery
Analyze high-level architectural requirements for implementing change-set specs to ensure proper alignment and identify potential concerns.
## Required Skills
- `spec-driven-development` (state management, phase gates)
- `research`
- `architecture-fit-check`
- `architecture-workshop`
## Inputs
> [!IMPORTANT]
> Resolve the change set by running `ls changes/ | grep -v archive/`. If exactly one directory exists, use it. Only prompt the user when multiple change sets are present.
## Instructions
1. Load `spec-driven-development` skill and read current state from `changes/<name>/state.toml`. Apply state entry check per skill guidelines. If lane is not `full` or phase doesn't permit discovery, redirect the user.
2. Read `proposal.md` and any existing specs in `changes/<name>/specs/`.
3. Discovery answers how a change fits into or extends the existing architecture:
- Use `research` skill to understand current architectural patterns
- Use `architecture-fit-check` to assess alignment
- If concerns exist (technical debt, messy workarounds), enter Daedalus Mode:
- Explain concerns clearly
- Explore solutions (light-touch vs. architectural)
- Reach consensus with the user on approach
4. Document findings: Capture explorations, tradeoffs, and decisions in `changes/<name>/thoughts/`
5. Do not update phase status in this command. After documenting discovery artifacts, suggest `ae-sdd-next <name>` when the user wants to proceed.
## Success Criteria
- Architecture fit assessed and documented
- Any concerns captured in thoughts/ directory
- Discovery artifacts complete and ready for `ae-sdd-next`
- User ready to proceed to tasks phase
## Usage Examples
### Do
- "This change slots cleanly into the existing Notification pattern."
- "Implementing this directly would create circular dependencies. Should we introduce an event bus instead?"
### Don't
- Start planning implementation tasks or file-level changes.
- Guess at architectural alignment without researching the codebase.Related Skills
customer-discovery
Find where potential customers discuss problems online and extract their language patterns. Provides starting points for community research, not exhaustive coverage.
code-discovery
Helpers to discover, rank, and invoke repository symbols from natural language with minimal context.
blueprint-discovery
Discovery phase for blueprint workflow - interview triggers, acceptance criteria, and feature classification
api-documentation-discovery
Use when APIs fail repeatedly with version-related errors (method not found, wrong arguments, unknown flag) or when about to use library APIs with uncertain knowledge - guides finding current, accurate documentation instead of guessing from training data
guid-universal-technology-discovery
Discover and identify any technology, framework, or system without prior knowledge. Analyzes files, configurations, dependencies, and usage patterns to understand project technology stack from C source files to Kubernetes manifests.
skills-discovery
Search for and install Agent Skills that give you specialized capabilities. Before starting work, ask might a skill exist that handles this better than my base knowledge? If the task involves specific technologies, frameworks, file formats, or expert domains. Search proactively, even if the user doesn't mention skills. Skills encode best practices, tools, and techniques you wouldn't otherwise have. Also use when users explicitly ask to find, install, or manage skills.
project-context-discovery
Discover project structure, package managers, test frameworks, and automation without hardcoded assumptions
discovery-interview
Deep interview process to transform vague ideas into detailed specs. Works for technical and non-technical users.
De-novo-motif-discovery
This skill identifies novel transcription factor binding motifs in the promoter regions of genes, or directly from genomic regions of interest such as ChIP-seq peaks, ATAC-seq accessible sites, or differentially acessible regions. It employs HOMER (Hypergeometric Optimization of Motif Enrichment) to detect both known and previously uncharacterized sequence motifs enriched within the supplied genomic intervals. Use the skill when you need to uncover sequence motifs enriched or want to know which TFs might regulate the target regions.
architecture-discovery
Guide users through discovering and defining system architecture through structured conversation. Triggers on "I want to build", "design a system", "architect", "planning a new project", "how should I build X".
architectural-pattern-discovery
Discovers architectural and design patterns across all abstraction levels. Analyzes structural patterns, component relationships, recurring solution approaches, and design principles. Works with any technology stack without prior framework knowledge to provide comprehensive pattern understanding from code-level to system-level architecture.
agent-ops-potential-discovery
Analyze incoming content (text, files, folders, URLs) to extract purpose, create summaries, and identify potential value for the current project.