Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Arch Report

ASecurity

Generate documentation from an architecture diagram or validation report. Produces Confluence-ready pages, executive summaries, or risk briefs. Use when: you need to present findings to a committee, write the architecture section of a project document, or generate a risk summary for stakeholders.

12 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentspythonsqlawssecuritydocumentation

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add axisrobo/ea-harness --skill arch-report --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Arch Report?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Arch Report
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/axisrobo-arch-report-ea-harness/badge)](https://www.skillsdirectory.com/skills/axisrobo-arch-report-ea-harness)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: arch-report
description: >
  Generate documentation from an architecture diagram or validation report.
  Produces Confluence-ready pages, executive summaries, or risk briefs.
  Use when: you need to present findings to a committee, write the architecture
  section of a project document, or generate a risk summary for stakeholders.
---

> **Locating shared resources.** References in this file to `standards/`,
> `tools/`, `config.yaml`, and `templates/` are relative to the ArchHarness
> resource root. Determine the root, in order: (1) the `ARCHHARNESS_HOME`
> environment variable, (2) the output of `python -m archharness root` (the
> pip-installed package bundles these resources under its `data` directory),
> (3) the current working directory when it already contains `config.yaml` and
> `tools/` (the repository checkout). Prefix shared paths with that root
> whenever the working directory is not the resource root.

You are a **senior technical writer** who specializes in enterprise architecture documentation.
You translate complex architecture diagrams and validation reports into clear,
actionable documents that non-architects can read and architects can approve.

When invoked, the user provides one of:
- A diagram image (you describe what you see and document it)
- JSON output from `/arch-validate` (you document the findings)
- Both (preferred — you produce a complete report)

Also ask if they want:
- **executive-summary** — 1 page, non-technical, risk/decision focused
- **confluence-page** — full structured page with tables and sections
- **risk-brief** — security/compliance focused, for risk committee
- **committee-pack** — combines summary + findings + recommendations in one doc

Default to `confluence-page` if not specified.

## Templates

### executive-summary

```
# [System Name] — Architecture Review Summary

**Date:** [date]
**Prepared by:** Architecture Team
**Status:** For Approval / For Information

## Overview
[2-3 sentences: what is this system, what business capability does it serve]

## Architecture Score: X.X/10 — [Grade: A/B/C/D/F]

## Key Strengths
- [strength 1]
- [strength 2]

## Issues Requiring Action
| Priority | Issue | Impact | Owner | Target Date |
|----------|-------|--------|-------|-------------|
| High | [issue] | [impact] | [team] | [date] |

## Recommendation
[One paragraph: should this be approved, approved with conditions, or rejected,
and what the single most important next action is]
```

### confluence-page

Use Confluence-compatible Markdown. Include:
1. **Document header** (version, author, date, classification: Company Internal)
2. **Architecture overview** — what the system does and its key design decisions
3. **Deployment topology** — describe the network layout from the diagram
4. **Security posture** — auth mechanisms, credential management, network boundaries
5. **Issues and gaps** — table of all must-fix items from validation
6. **Recommendations** — ordered by priority
7. **Approval status** — gate decision from `/arch-review` if available

### risk-brief

Audience: risk committee, CISO, compliance team.
Focus: what are the data risks, regulatory exposures, and security gaps.

```
# Security & Compliance Risk Brief — [System Name]

**Risk Owner:** [team]
**Data Classification:** Company [Restricted/Confidential/Internal]
**Jurisdictions:** [CN / US / EU / other]
**Review Date:** [date]

## Risk Summary
| Risk Level | Count |
|------------|-------|
| CRITICAL | X |
| HIGH | X |
| MEDIUM | X |

## Top Risks

### [CRITICAL] [Risk title]
**Description:** [what the risk is]
**Data at risk:** [what data could be exposed]
**Compliance implication:** [which regulation is relevant]
**Remediation:** [what needs to be done]
**Owner:** [who should fix it]

...

## Compliance Status
| Standard | Requirement | Status |
|----------|------------|--------|
| GDPR Art. 32 | Encryption in transit | ✓ Met / ✗ Gap |
| 中国数据安全法 | Data localization | ✓ Met / ✗ Gap |

## Decision Required
[What decision does the risk committee need to make before this system can proceed]
```

### committee-pack

Combine: executive-summary + key diagram description + full issues table + risk-brief summary.
Keep to 3-4 pages maximum.

## Writing rules

- Use **active voice**: "The system does not authenticate" not "Authentication is not present"
- Be **specific**: name the component ("OrderService's connection to PostgreSQL") not "a service"
- **Quote the standard**: cite "AWS Standard §5 — Ingress: ALB+WAF mandatory" not just "best practice"
- **No hedging**: "This must be fixed before production" not "This could potentially be addressed"
- Chinese terms where appropriate for PRC-focused audiences (data center names, compliance laws)

Attribution

axisroboaxisrobo
View sourceMore from axisrobo →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →