From straion
Guides users through rules-first feature implementation from idea to production code. Validates specs, tasks, and implementation against project rules at every step. Use when building features, implementing specs, creating implementation plans, breaking down specs into tasks, or when user says "help me build", "implement this", "add feature", "plan this", "break down this spec", "create tasks", or wants rules compliance.
How this skill is triggered — by the user, by Claude, or both
Slash command
/straion:developing-with-rulesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- **Rules First**: Build features that meet documented rules
Transform a rough idea into a clear, lightweight specification.
Ensure the spec complies with project rules BEFORE planning.
Run the Straion CLI to find matching rules:
straion find-rules \
--title "<spec title>" \
--body "<full spec content>" \
--summary "<brief summary>"
See ../shared/STRAION_CLI.md for full CLI reference.
Analyze compliance for each returned rule:
Gate: Only proceed when spec has no critical violations.
Break down the validated spec into compliant implementation tasks.
VALIDATION GATE: Each task MUST be validated before adding to plan
For each task:
straion find-rules for this task:
straion find-rules \
--title "<task title>" \
--body "<task description>" \
--summary "<overall spec summary>"
Address any violations or gaps across all tasks
Present complete, validated plan for user approval
Do NOT present plan until all tasks pass validation
Execute the validated tasks while maintaining compliance.
| Mode | When | Flow |
|---|---|---|
| Full | Starting from rough idea | Step 1 → 2 → 3 → 4 |
| From Spec | Have existing spec | Step 2 → 3 → 4 |
| Validate Only | Just check compliance | Step 2 only |
| Plan Only | Create validated implementation tasks | Step 3 only |
See references/EXAMPLE.md for a complete SSO login implementation walkthrough.
✅ User understands what was built and why ✅ Spec and tasks are validated ✅ Critical violations are addressed ✅ Implementation works and passes tests ✅ Solution meets rules
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub straion-dev/straion-claude-marketplace --plugin straion