im-shashanks/claude-plugins / shaktra/skills/shaktra-stories
shaktra-stories
VerifiedStory creation, enrichment, and related schemas. Defines HOW to create and validate user stories, WHAT fields exist per tier (story-schema), WHICH tier a story belongs to (story-tiers), and sprint state format (sprint-schema). Loaded by scrummaster and other story-consuming agents.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.5 KB |
| sprint-schema.md | markdown | 2.2 KB |
| story-creation.md | markdown | 6.3 KB |
| story-schema.md | markdown | 5.0 KB |
| story-tiers.md | markdown | 2.6 KB |
story-tiers.md
View on GitHub# Story Tiers
4-tier classification system for user stories. Tier determines required fields, quality gates, and coverage thresholds. Field definitions and YAML schema live in `story-schema.md` — this file defines only the tier matrix, detection logic, and gate behavior.
## Tier Summary
| Tier | Typical Scope | Required Fields | Coverage Threshold | Check Depth |
|---|---|---|---|---|
| **Trivial** | Typo fix, config change, docs update | 3 | `settings.tdd.hotfix_coverage_threshold` | Quick |
| **Small** | Single-function change, minor bugfix | 5 | `settings.tdd.small_coverage_threshold` | Quick |
| **Medium** | Feature addition, multi-file change | 12 | `settings.tdd.coverage_threshold` | Full |
| **Large** | Cross-cutting feature, architectural change | 18+ | `settings.tdd.large_coverage_threshold` | Thorough |
## Auto-Detection Logic
```
if story has no acceptance criteria AND estimated_hours <= 1:
tier = Trivial
else if files_touched <= 3 AND no new public API:
tier = Small
else if files_touched <= 10 OR new public API:
tier = Medium
else:
tier = Large
```
The auto-detected tier is a suggestion. The user or TPM can override it explicitly in the story file.
## Gate Behavior Matrix
| Gate | Trivial | Small | Medium | Large |
|---|---|---|---|---|
| Failing test before code (Red) | Skip | Required | Required | Required |
| Tests pass after code (Green) | Required | Required | Required | Required |
| Coverage threshold | `settings.tdd.hotfix_coverage_threshold` | `settings.tdd.small_coverage_threshold` | `settings.tdd.coverage_threshold` | `settings.tdd.large_coverage_threshold` |
| Quality check depth | Quick | Quick | Full | Thorough |
| Design review | Skip | Skip | Required | Required |
| PR review | Skip | Required | Required | Required |
## Check Depth Definitions
Check depth controls **review scope**, not check loading. All ~36 checks from `shaktra-quality/quick-check.md` are always loaded regardless of tier. Depth determines how findings are treated and whether comprehensive review runs.
**Quick (Trivial/Small):** sw-quality runs quick-check only. All ~36 checks loaded, but P2+ findings are reported as observations, not blockers. No comprehensive review phase.
**Full (Medium):** sw-quality runs quick-check at each TDD gate + comprehensive review (dimensions A-M + N) at QUALITY phase. Standard severity enforcement — P0 blocks, P1 threshold applies, P2 reported.
**Thorough (Large):** Full depth + expanded comprehensive review with architecture impact analysis, performance profiling review, dependency audit, and cross-cutting concern validation.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |