Index of every page on this site: llms.txt
All skills
Run it yourself

Write comment replies that read like they came from a real, sharp, caring human: substance first, the commenter's own words referenced, their language and register matched, no generic openers, no AI texture. Use when replying to genuine comments on your own posts, in English or Roman Urdu, on any platform.

  • 4 files
  • 18.1 KB
  • Updated 5 days ago
  • GitHub
Use this Skill: https://skilld.dev/gh/jokerhtml/needcraft-skills/human-reply

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

examplesreply-examples.md

≈1k tokens on demand. Your agent reads this file only when SKILL.md points to it.

Reply examples — good vs bad

All examples below were written for this skill as illustrations. They are not real replies, were never posted, and never received real engagement. Each pair shows the same comment answered badly (fails the anti-AI core) and well (passes it). Replace the topic with your own — these examples show the reply shape, not content to copy.

1. English — question about which routine works

Comment: "Tried the first watering schedule, plant still drooping. Is the second one actually better?"

Bad:

"Great question! Thanks for asking! I'd love to help you with this. The second schedule is excellent — feel free to reach out if you need anything else! 🙌"

Fails: generic opener, no reference to what they said, stock phrasing, emoji enthusiasm, zero substance.

Good:

"The second one worked for me where the first didn't — the difference is watering when the soil is dry, not on a fixed day. Try changing just that first and see if the leaves lift."

Passes: references their words, one specific useful point, plain language, stops after the point.

2. English — admitting limits

Comment: "Does this work for beginners or only experienced growers?"

Bad:

"Great question! This works for everyone! Let me know what you think!"

Fails: generic opener, a claim ("works for everyone") with no basis, no substance.

Good:

"Honestly I've only tested it as a beginner, so experienced growers I can't confirm. The structure should hold — same watering logic — but I wouldn't claim it without testing it there."

Passes: admits the limit plainly, offers what is known, no promise it cannot keep.

3. English — correcting a mistake, kindly

Comment: "You should water every day, that's the standard. Twice a week is not enough."

Bad:

"Thanks for your comment! I appreciate your perspective! Everyone has their own approach!"

Fails: performative warmth, dodges the substance, agrees with nothing and corrects nothing.

Good:

"Every day can work, but it depends on the pot — in a small pot the soil dries fast, in a big one it stays wet for days, so I check the soil first. Worth testing on your own plant before committing to daily."

Passes: disagrees with evidence, one correction, no pile-on, ends with something useful.

4. Roman Urdu — question about which routine works

Comment: "Pehla watering schedule try kiya, poda abhi bhi murjha raha hai. Dusra wala waqai behtar hai?"

Bad:

"Great question! Shukriya poochne ka! Dusra schedule boht excellent hai, feel free to reach out! 🙌"

Fails: English template opener pasted into Roman Urdu, no substance, same generic phrasing as the English bad reply.

Good:

"Dusre wale se mere pode ko farq para, pehle se nahi. Farq sirf ye hai ke mitti sookhne pe pani do, fixed din pe nahi. Pehle sirf woh badal ke dekho, phir batana kya farq para."

Passes: same language and register as the commenter, references their exact situation, one specific point, natural rhythm.

5. Roman Urdu — admitting limits

Comment: "Ye beginners ke liye bhi kaam karta hai ya sirf experienced growers ke liye?"

Bad:

"Great question! Ye sab ke liye kaam karta hai!"

Fails: generic opener, an untested claim stated as fact.

Good:

"Sach bataun to maine sirf beginner ke tor pe test kiya hai, experienced growers ka confirm nahi kar sakta. Structure wohi hai, watering logic same hai, lekin test kiye baghair daawa nahi karunga."

Passes: plain admission of the limit, offers what is known, no invented claim.

6. English — short casual comment (match the energy)

Comment: "This is actually useful, saved it."

Bad:

"Thank you so much for your kind words! I'm so glad you found it helpful! Let me know what you think about the next one! 🙌✨"

Fails: a lecture-length gush under a one-line comment; performative warmth; generic.

Good:

"Glad it landed. The second watering routine in the set is the one most people end up using."

Passes: matches their energy and length, one small useful point, then stops.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 90f40b1. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 4 days ago.

Activeupdated 5 days ago
Other metadata
metadata
{
  "version": "1.0.0",
  "date": "2026-11-16",
  "author": "Muhammad Saad Ranjha / NeedCraft"
}

README badge

README badge for jokerhtml/needcraft-skills/human-reply