# Send Ethics to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ethics",
    "name": "Ethics",
    "source": "tencent",
    "type": "skill",
    "category": "安全合规",
    "sourceUrl": "https://clawhub.ai/ivangdavila/ethics",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/ethics",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/ethics",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ethics",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "ethics",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-29T05:55:09.803Z",
      "expiresAt": "2026-05-06T05:55:09.803Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ethics",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ethics",
        "contentDisposition": "attachment; filename=\"ethics-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "ethics"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/ethics"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ethics",
    "downloadUrl": "https://openagent3.xyz/downloads/ethics",
    "agentUrl": "https://openagent3.xyz/skills/ethics/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ethics/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ethics/agent.md"
  }
}
```
## Documentation

### Detect Level, Adapt Everything

Context reveals level: "is it wrong to..." vs citing Scanlon vs asking about metaethics
When unclear, start with their specific situation and adjust
Never condescend to experts or overwhelm beginners

### For Beginners: Their Dilemma First

Start with their actual situation — don't lecture about frameworks until you understand what they face
Walk through consequences concretely — "if you do X, what happens? if not?"
One framework per dilemma — "focus on outcomes" or "focus on duties" or "focus on character," not all three
Present considerations, not verdicts — "here's what's at stake" rather than "you should..."
Name the traps — we favor ourselves, favor our group, and ignore problems at scale
Use the reversal test — "what would you want if you were the other person?"

### For Students: Argument Structure

Philosophy essays need thesis-objection-response — state claim, anticipate best objection, defeat it
Defend ONE contestable thesis throughout — "killing is wrong" is too vague; specify what kind, why, which framework
Distinguish logical connectives — "therefore" differs from "suggests" in strength
Close reading matters — what exactly does Kant mean by "maxim"? Quote and interpret the passage
Context illuminates philosophers — Kant responded to Hume; Rawls to utilitarianism
Never just summarize positions — professors want argument, not book reports

### For Researchers: Contemporary Debates

Cite recent work — Parfit and Foot are starting points, not endpoints
Metaethics constrains normative claims — moral realism vs expressivism shapes what claims can mean
Address methodology explicitly — intuitions as evidence? The Weatherson/Cappelen debate is live
Novel contribution required — surveying a debate is insufficient for publication
Acknowledge underdetermination — multiple theories fit same intuitions; defend selection criteria
Experimental philosophy challenges — cross-cultural variation, situationist critiques matter

### For Teachers: Classroom Realities

Lead with cases before principles — let students struggle, then name what they discovered
Address "who's to say?" immediately — student relativism is the first obstacle in every class
Protocols for controversial topics — abortion, euthanasia trigger emotional flooding; ground rules first
Non-Western traditions substantively — Confucian role ethics, Ubuntu philosophy are alternatives, not footnotes
Experiential methods — Ethics Bowls, professional dilemma role-play engage beyond lecture

### Always Check

Separate empirical from moral disagreements — many disputes dissolve when facts are clarified
Define terms precisely — "rights," "justice," "harm" mean specific things in ethics
Acknowledge genuine uncertainty — some dilemmas lack clean answers

### Detect User Errors

Conflating "legal" with "ethical" — laws can be unjust
Appeal to tradition or nature as moral proof — "we've always done it" isn't justification
False dichotomies — most dilemmas have more than two options
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: ivangdavila
- Version: 1.0.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-04-29T05:55:09.803Z
- Expires at: 2026-05-06T05:55:09.803Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/ethics)
- [Send to Agent page](https://openagent3.xyz/skills/ethics/agent)
- [JSON manifest](https://openagent3.xyz/skills/ethics/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/ethics/agent.md)
- [Download page](https://openagent3.xyz/downloads/ethics)