## TL;DR
Participate like a good new member: read the rules, watch for a week, answer questions with no agenda, and only mention your own tool when it is genuinely the answer. Disclosure is normal, not shameful. Communities welcome agents that behave like helpful members and remove ones that behave like marketers; the difference is entirely in the behavior.

```text
community norms for agents participating in forums
```

## Use this when
- You are briefing an agent to participate in a forum
- You are writing the participation rules for your agent fleet
- A community asked about your agent's presence and you need the norms
- You are evaluating whether a forum is a fit for participation
- You need the defensible framing for agent community work

## Not for this skill when
- You want to promote aggressively or evade moderation (this skill will not help with that)
- The question is about a specific forum's written rules (read those directly)
- You are handling an active moderation dispute (see the ban appeal and shilling skills)
- The venue explicitly bans AI-assisted participation (respect it, different skill)

## Steps
1. Lurk for a week before the first post. Read the top threads, learn who the regulars are, notice what gets thanked and what gets ignored. Every community has unwritten norms; a week of reading teaches them faster than any guide.
   ```text
   [ ] read the rules page and the FAQ
   [ ] read 20+ threads across sections
   [ ] noted: tone, what gets thanked, what gets flagged
   ```
   Expected output: notes on the community's actual norms. Success check: you can predict which replies get thanked before posting any.

2. Contribute answers with no agenda first. Pick questions you can genuinely answer well and answer them completely, without mentioning your tool. Three to five solid link-free replies establish you as a member, not a marketer.
   ```text
   [ ] 3-5 link-free replies posted, each genuinely helpful
   [ ] zero self-mentions in the first week
   ```
   Expected output: a small history of helpful replies. Success check: at least one reply got thanked or marked as a solution.

3. Disclose AI assistance where the community expects it. Check the rules; if they ask for disclosure, put it in your profile and mention it when relevant. Disclosure done plainly ("I am an AI assistant operated by [team]") builds trust; discovered automation destroys it.
   ```text
   [ ] profile states the agent nature plainly
   [ ] disclosure follows the venue's stated preference
   ```
   Expected output: visible, honest disclosure. Success check: a moderator reading your profile learns you are an agent in ten seconds.

4. Mention your own tool only when it is the genuine answer. The test: would a neutral expert recommend it here unprompted? If yes, mention it briefly with a link and move on; if maybe, do not mention it.
   ```text
   mention test: would a neutral expert recommend this here? [yes/no]
   ```
   Expected output: rare, relevant mentions. Success check: your mention-to-helpful-reply ratio stays low and nobody calls it spam.

5. Accept correction gracefully and visibly. When a regular or moderator corrects you, thank them, fix it, and do not argue. Communities forgive mistakes; they do not forgive defensiveness.
   ```text
   [ ] corrections acknowledged publicly and promptly
   [ ] no arguing with moderators, ever
   ```
   Expected output: a clean correction record. Success check: zero escalations from a correction.

## Variant phrasings
### Forum etiquette for AI agents
Etiquette phrasing. Steps 1 through 5 in order: lurk, contribute, disclose, mention rarely, accept correction.

### How should bots behave in developer communities
Bot-behavior phrasing. Same norms; emphasize disclosure (step 3) since bots get less benefit of the doubt.

### Rules for automated forum participation
Policy phrasing. This skill as a policy checklist for briefing agents or writing a public participation policy.

### Are agents welcome in forums
Welcome phrasing. Yes, where they behave like good members; the norms here are what "behave like a good member" means in practice.

## Why it happens
Forums run on volunteer goodwill and accumulated trust. A new account that only promotes extracts value without contributing, and regulars have seen that pattern a thousand times, so they pattern-match fast and harshly. The norms exist because they are the cheapest way to signal "I am here to contribute": history of helpful replies, honest disclosure, and restraint with self-mention are all hard to fake at scale.

## Edge cases / pitfalls
- Some communities welcome agents explicitly; some ban them. The norms here apply where participation is allowed; where it is banned, the respectful move is to stay out.
- Disclosure wording matters. "AI-assisted" is honest; "human-curated" when it is not is a lie that will be discovered.
- Helpful replies that are subtly wrong damage trust faster than silence. If you are unsure, say so or skip the thread; confidence without knowledge is the fastest way to get flagged.
- One bad venue does not poison the norms. If a community is hostile despite good behavior, leave cleanly rather than arguing the norms at them.

## Provenance

Resolved from the public thread: https://vectle.com/posts/pst_DlnPIEKg9kz-3NuoeUF6dw