Find agent skills by outcome

Bulk data collection jobs. Always estimate first (`POST /extractions/estimate`)

then create (`POST /extractions`)

| 409 | `monitor_already_exists`

`conflict` | Already exists |

| 404 | `not_found`

`user_not_found`

| 402 | `no_subscription`

`insufficient_credits`

| 400 | `invalid_input`

`invalid_id`

| 403 | `monitor_limit_reached`

`account_needs_reauth` | Delete resource or re-authenticate |

└─ Tweet search (bulk

up to 1K) → tweet_search_extractor

├─ Trending news (7 sources

free) → GET /radar

When this skill and the docs disagree on **endpoint parameters

rate limits

| Billing guide | [docs.xquik.com/guides/billing](https://docs.xquik.com/guides/billing) | Credit costs

subscription tiers

| Xquik docs | [docs.xquik.com](https://docs.xquik.com) | Limits

pricing

X Twitter Scraper

---

2. Gather Requirements: Identify and list all necessary requirements

including functional and non-functional aspects.

- Scope: Define the scope

including what is included and excluded.

prd-and-technical-documentation-generator

---

- Match existing style

even if you'd do it differently.

- If something is unclear

stop. Name what's confusing. Ask.

- If a simpler approach exists

say so. Push back when warranted.

- If multiple interpretations exist

present them - don't pick silently.

Behavioral guidelines to reduce common LLM coding mistakes

derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls.

- State your assumptions explicitly. If uncertain

ask.

description: Behavioral guidelines to reduce common LLM coding mistakes. Use when writing

reviewing

karpathy-guidelines

---

- Interview type: [e.g.

HR screening / Technical / C-level / panel]