agent-architecture-audit
Full-stack diagnostic for agent and LLM applications.
Skill by sakuradairong
Chalk Labs
Need help deploying agent-architecture-audit?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sakuradairong-agent-architecture-audit
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: ml, security, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-architecture-audit
What's inside
- Skill name
agent-architecture-audit- Description
- Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
- License
- unknown
- Instructions
- 251 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from sakuradairong/omp-config
- 0.568score
angular-developer
sakuradairong
Generates Angular code and provides architectural guidance.
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
canary-watch
sakuradairong
Use this skill to monitor and verify a deployed URL after releases — checks HTTP endpoints, SSE streams, static assets, console errors, and performance…
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
autonomous-agent-harness
sakuradairong
Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing.
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
blender-motion-state-inspection
sakuradairong
Use this skill when inspecting Blender characters, rigs, poses, animation retargeting, ground contact, facing direction, or model-vs-motion alignment where…
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
browser-qa
sakuradairong
Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
astrbot-plugin-development
sakuradairong
Use when developing, debugging, or fixing AstrBot plugins and encountering import errors, async generator issues, plugin loading failures, or configuration…
SkillCFreshness: C★ 48Claude Code +9 - 0.562score
benchmark
sakuradairong
Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.
SkillCFreshness: C★ 48Claude Code +9 - 0.560score
architecture-decision-records
sakuradairong
Capture architectural decisions made during Claude Code sessions as structured ADRs.
SkillCFreshness: C★ 48Claude Code +9 - 0.560score
agentic-os
sakuradairong
Build persistent multi-agent operating systems on Claude Code.
SkillCFreshness: C★ 48Claude Code +9 - 0.560score
agent-eval
sakuradairong
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
SkillCFreshness: C★ 48Claude Code +9 - 0.560score
docker-compose
sakuradairong
Expert guidance on Docker Compose V2 syntax, best practices, and common patterns for writing production-ready compose files.
SkillCFreshness: C★ 48Claude Code +9 - 0.560score
cisco-ios-patterns
sakuradairong
Cisco IOS and IOS-XE review patterns for show commands, config hierarchy, wildcard masks, ACL placement, interface hygiene, and safe change-window verification.
SkillCFreshness: C★ 48Claude Code +9
Signals
- Stars
- 48
- Forks
- 12
- Open issues
- 0
- Last commit (this folder)
- Jun 3, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/sakuradairong/omp-config
- Website
- weblyfe.ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.339score
agent-architecture-audit
nicolas2601
Full-stack diagnostic for agent and LLM applications.
SkillBFreshness: B★ 3Claude Code +9 - 0.327score
agent-architecture-audit
S3YED
Full-stack diagnostic for agent and LLM applications.
SkillCFreshness: C★ 12Claude Code +9 - 0.315score
agent-architecture-audit
KUNDURUHIMANEESHREDDY
Full-stack diagnostic for agent and LLM applications.
SkillBFreshness: BClaude Code +9 - 0.312score
agent-architecture-audit
netsecdevio
Full-stack diagnostic for agent and LLM applications.
SkillBFreshness: BClaude Code +9 - 0.309score
agent-architecture-audit
krataia
Full-stack diagnostic for agent and LLM applications.
SkillBFreshness: BClaude Code +9 - 0.282score
agent-architecture-audit
vishal24p
Full-stack diagnostic for agent and LLM applications.
SkillCFreshness: CClaude Code +9 - 0.282score
agent-architecture-audit
LongHuynh712
Full-stack diagnostic for agent and LLM applications.
SkillCFreshness: CClaude Code +9 - 0.282score
agent-architecture-audit
RajanthaR
Full-stack diagnostic for agent and LLM applications.
SkillCFreshness: CClaude Code +9 - 0.282score
agent-architecture-audit
jaysonpantollana
Full-stack diagnostic for agent and LLM applications.
SkillCFreshness: CClaude Code +9
More from sakuradairong
- 0.568score
angular-developer
sakuradairong
Generates Angular code and provides architectural guidance.
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
blender-motion-state-inspection
sakuradairong
Use this skill when inspecting Blender characters, rigs, poses, animation retargeting, ground contact, facing direction, or model-vs-motion alignment where…
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
autonomous-agent-harness
sakuradairong
Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing.
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
astrbot-plugin-development
sakuradairong
Use when developing, debugging, or fixing AstrBot plugins and encountering import errors, async generator issues, plugin loading failures, or configuration…
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
browser-qa
sakuradairong
Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
canary-watch
sakuradairong
Use this skill to monitor and verify a deployed URL after releases — checks HTTP endpoints, SSE streams, static assets, console errors, and performance…
SkillCFreshness: C★ 48Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get agent-architecture-audit running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
agent-architecture-audit skill. Agent Mart. https://agentmart.dev/skills/sakuradairong-agent-architecture-audit (last updated 2026-10-24)