talk-stack-humans-architect-ai-writes-code
Use when the user asks about Paul Stack's talk "The Humans Architect the System, the AI Writes the Code" (System Initiative / Eldest One Club, 2026) — including questions about why his team stopped writing code, the no-PR open-source policy, CLAUDE.md as executable constraints, the planner/adversarial-reviewer loop, swamp the AI-native ops CLI, UAT as source of truth, "vibes don't scale", "intent is the new architecture", supply-chain integrity in AI-era OSS, or applying his architecture-first / agents-write-all-code workflow to the user's own team.
62
74%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./talk-stack-humans-architect-ai-writes-code/SKILL.mdLow
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The runtime workflow described is an issue-triage skill (“triage an issue… fetches the details of the issue”) that processes outsider-authored issue text via “skill”+CLI into planning/adversarial loops and tests, so external contributors can inject free text through the issue submission path that the agent reads without an initial item selection step.
- Repository
- AINativeDev/aidevcon-2026-ldn
- Commit
1887349
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.