Skills for Real Engineers. Straight from my .agents directory.
owner-intent-audit
Agent skill fromsno-ai/sno-station-skills
Check agent-produced plans, tests, or code against the owner's actual intent. Find missing meaning, unrequested work, stale truth, unreachable decisions, unsupported completion claims, and implementation debt. Use before approval or merge.
How to install owner-intent-audit
npx skills add sno-ai/sno-station-skills# or add only this skill to Claude Code: copy the folder
plugins/sno-station-standalone/skills/owner-intent-audit/
# into
~/.claude/skills/owner-intent-audit/ (all projects)
.claude/skills/owner-intent-audit/ (one project)
1# Owner Intent Audit23The question this review answers is not "is the artifact good" but **"is this what the owner4meant, and what did the agent leave behind while making it?"** (The owner is whoever owns the5work and decides what it should be; often that is the user.) An agent can produce a PRD (product6requirements document), a plan, or a diff that is locally excellent and still specify a different product, carry work7nobody asked for, or hide the debts agents characteristically create. Reviewing the artifact8for its own defects — bugs, security holes, silent death — is peer-review's job, not this one;9the two are run separately and neither substitutes for the other.1011- **Plan mode:** PRDs, designs, specs, task lists, refactor plans, and test plans.12- **Code mode:** diffs, files, tests, or subsystems substantially written by agents.1314Start with the ordinary user and system flow. Realistic common-path failure outranks exotic15edge cases.1617## What must be established1819### 0. Did the artifact preserve the product meaning?2021This is not “did every source bullet appear?” A locally plausible artifact can retain the22same nouns while specifying a different product.2324Determine:2526- who needs the outcome and who decides;27- what result they actually need;28- when the behavior applies and when it must not;29- which exceptions, prohibitions, priorities, and trade-offs matter;30- how separate answers constrain or explain each other;31…
Excerpt shown under the repository's Apache-2.0 license.
More skills in sno-station-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
