Ovid/paad / preview/paad/skills/agentic-architecture
agentic-architecture
VerifiedUse when assessing the architectural health of a codebase — before a major refactor, when onboarding to an unfamiliar repo, after rapid growth, when planning a redesign, or to surface structural strengths and risks before they become expensive. Not for fixing what it finds, and not for reviewing a branch diff.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 26.5 KB |
| references/paad-analyst.md | markdown | 4.0 KB |
| references/report-template.md | markdown | 3.1 KB |
references/report-template.md
View on GitHub# Report Template — additional instructions
> **Read this file before writing the architecture report.** This is parent-side material for `/agentic-architecture` Phase 4. The orchestrator (the agent that activated this skill) reads these instructions when entering the report-writing phase — there is no subagent dispatch for this phase. The report template below is binding for the Phase 4 deliverable.
**Report template:**
```markdown
# Architecture Report — <repo-name or current folder>
* **Date:** YYYY-MM-DD
* **Model:** <the model you are running as — from your environment; "unknown" if unavailable>
* **PAAD version:** <plugin version from your on-invocation announce line>
* **Commit:** <full-sha>
* **Languages:** <primary languages/frameworks>
* **Key directories:** <list>
* **Scope:** <full repo or specific paths>
## Repo Overview
Brief description of the codebase: what it does, how it's structured, approximate size.
## Strengths
Ranked by impact (High/Medium/Low), 5–15 items:
### [S-ID] <Strength label>
- **Category:** <S1-S14 category name>
- **Impact:** High / Medium / Low
- **Explanation:** 1-2 sentences
- **Evidence:** `path:line-range` (`symbol`), excerpt: "short excerpt"
- **Found by:** <specialist name(s)>
## Flaws/Risks
Ranked by impact (High/Medium/Low), 10–25 items:
### [F-ID] <Flaw label>
- **Category:** <flaw type 1-34 name>
- **Impact:** High / Medium / Low
- **Explanation:** 1-2 sentences
- **Evidence:** `path:line-range` (`symbol`), excerpt: "short excerpt"
- **Found by:** <specialist name(s)>
## Coverage Checklist
### Flaw/Risk Types 1–34
| # | Type | Status | Finding |
|---|------|--------|---------|
| 1 | Global mutable state | Observed / Not observed / Not assessed | #F-ID or — |
(continue for all 34)
### Strength Categories S1–S14
| # | Category | Status | Finding |
|---|----------|--------|---------|
| S1 | Clear modular boundaries | Observed / Not observed / Not assessed / Not applicable | #S-ID or — |
(continue for all 14)
When a security file was written this run, rows 30, 33 and S10 read `See security file` in Status and `see paad/security/` in Finding regardless of what was found, and every other row's status counts only this report's own findings; state that above the checklist in one line: `Statuses count this report's findings only; routed findings are in the security file's checklist.`
## Hotspots
Top 3 files/directories to review:
1. `path/` — brief why (can include risk hotspots and strong core hotspots)
2. ...
3. ...
## Next Questions
Up to 5 questions to guide follow-up investigation. Questions only — no suggested solutions.
## Analysis Metadata
- **Agents dispatched:** <list with focus areas>
- **Scope:** <files analyzed>
- **Raw findings:** N (before verification)
- **Verified findings:** M (after verification)
- **Filtered out:** N - M
- **By impact:** X high, Y medium, Z low (this report's findings only; routed findings are excluded)
- **Security:** N finding(s) written to paad/security/<file> (only when a security file was written)
- **Steering files consulted:** <list or "none found">
```
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 | Unverified | 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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |