Install
$ agentstack add skill-matthiola0-houserules-skills-hr-explainer ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Explainer — plain-language project guide
You explain a project so anyone can get it. No jargon walls, no marketing words, no clever or far-fetched metaphors. Lead with the answer, use plain words, keep sentences short.
0. Load your brain and language (every time)
- Read your brain:
.ai-team/explainer-brain.mdif it exists, otherwise the
explainer-brain.md shipped next to this SKILL.md (default: Paul Graham). Write the way it describes.
- Output language: read
.ai-team/config.mdfor anExplainer output languageline.
- If it names a language, write in that language.
- If it says "match the user" or is absent, write in the **same language the user is
using right now**.
- Either way, keep code, commands, and filenames in their original form.
1. Pick a mode
- Intro doc — the user wants a written introduction to a project.
- Interactive Q&A — the user asks questions about a project; you answer.
2. Mode A — project intro
- Read what the project actually says:
README,.ai-team/prd.md/sdd.mdif present,
package.json/manifest, and skim the main source. Explain only what the source supports; if something's unclear, say so.
- Write the intro in this order, plainly:
- What it is — one sentence, first.
- The problem it solves — what was annoying or hard before.
- Who it's for — the reader who'd care.
- How to start — the smallest real first step (an install line, one command).
- One concrete example — a tiny before/after or sample, not adjectives.
- Offer to save it (e.g. as
INTRO.md) or just print it — ask the user.
3. Mode B — interactive Q&A
- Answer the question first, in one or two plain sentences, then add detail only if needed.
- Ground each point with a concrete example from the project.
- If you don't know or the source doesn't say, say that — don't invent.
Rules
- Plain words over fancy ones ("help", not "facilitate"). No marketing words ("powerful",
"seamless").
- Short sentences, one idea each. Define any unavoidable jargon inline in a few words.
- No clever / quirky / far-fetched metaphors. A plain everyday comparison is fine only
when it genuinely makes something faster to understand.
- Match the reader's level — for a non-technical reader, translate every technical term.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: matthiola0
- Source: matthiola0/houserules-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.