skills/post-match-tweet-thread/SKILL.md
# Post-Match Tweet Thread Skill Receives a raw match object and returns a structured 5-tweet thread in Brazilian Portuguese ready to be scheduled on the team's social account. ## Workflow: `generate-tweet-thread` Takes a single input `match_data` (a JSON object with the match facts) and returns a thread of exactly 5 perspective-tagged tweets. Each tweet is character-counted server-side so the publisher doesn't have to. ### Tweet positions | # | role | content angle
npx skillsauth add machina-sports/machina-templates skills/post-match-tweet-threadInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Receives a raw match object and returns a structured 5-tweet thread in Brazilian Portuguese ready to be scheduled on the team's social account.
generate-tweet-threadTakes a single input match_data (a JSON object with the match facts)
and returns a thread of exactly 5 perspective-tagged tweets. Each tweet
is character-counted server-side so the publisher doesn't have to.
| # | role | content angle | |---|------------------|----------------------------------------------------------| | 1 | hook | placar + momento decisivo, gancho pra reter o leitor | | 2 | key_moment | gol/lance mais importante com contexto narrativo | | 3 | stat_spike | número que surpreende (xG, distância percorrida, posse) | | 4 | talking_point | controvérsia / debate (arbitragem, escalação, lance) | | 5 | call_to_action | próximo jogo, engajamento ("conta pra gente…") |
match_data (object): payload da partida. Mínimo: home_team,
away_team, score, scorers[]. Extras opcionais que melhoram o
resultado: key_moments[], xg, possession, competition,
next_match.Example input:
{
"competition": "Brasileirão Série A",
"home_team": "Palmeiras",
"away_team": "Corinthians",
"score": "2-1",
"scorers": [
{ "name": "Estêvão", "minute": 22, "team": "Palmeiras" },
{ "name": "Yuri Alberto", "minute": 58, "team": "Corinthians" },
{ "name": "Endrick", "minute": 89, "team": "Palmeiras" }
],
"key_moments": [
{ "minute": 71, "type": "red_card", "player": "Cacá", "team": "Corinthians" }
],
"xg": { "Palmeiras": 2.4, "Corinthians": 1.1 },
"possession": { "Palmeiras": 58, "Corinthians": 42 },
"next_match": { "team": "Palmeiras", "vs": "São Paulo", "when": "domingo" }
}
{
"tweet_thread": {
"thread": [
{ "position": 1, "role": "hook", "tweet": "...", "char_count": 144 },
{ "position": 2, "role": "key_moment", "tweet": "...", "char_count": 220 },
{ "position": 3, "role": "stat_spike", "tweet": "...", "char_count": 178 },
{ "position": 4, "role": "talking_point", "tweet": "...", "char_count": 199 },
{ "position": 5, "role": "call_to_action", "tweet": "...", "char_count": 132 }
]
},
"workflow-status": "executed"
}
char_count retornado é checado pelo
prompt antes de emitir.match_data, não
use o número.| Use this skill when… | Use the other one instead |
|----------------------------------|----------------------------------------------------------|
| You need a thread for X/Twitter | match-stats-formatter for plain-prose chat summaries |
| Output should be Brazilian PT | match-headline-generator for English headline variants |
| You want 5 perspective-tagged | (single-shot caption tools — not in this repo yet) |
tools
# World Cup 2026 Intelligence Skill This skill organizes and packages the real-time predictive analytics, market data aggregation, and social sentiment indexing capabilities of the FIFA World Cup 2026 pod into a cohesive, SDK-discoverable, and Studio-renderable capability. ## Overview The `world-cup-intelligence` skill wraps low-level background workflows (ingestion, identity crosswalking, Dixon-Coles model solving) into high-level, client-facing methods exposed via the `@machina-sports/sdk`
devops
# Project Manifest Generator Generates a draft `project.manifest.yml` for a Machina template by statically scanning a list of workflows and aggregating the credentials, connectors, datasets and agents they reference. Built to scale **Sprint 1A** of the Pipeline Platform Cleanup (the hand-written botandwin manifest at `entain-templates`) to every template in `machina-templates` without writing each one by hand. ## What it does 1. **Deterministic extraction (always)** — a pyscript connector wa
data-ai
# Press Conference Extractor Skill This skill processes a raw transcript from a press conference and extracts structured insights. ## Use Case Use this skill when you have a long text of a press conference and need to quickly identify the key topics discussed, who said what, and which quotes are the most impactful for news reporting or analysis. ## Inputs - `transcript`: A single long string containing the full text of the press conference. ## Example Output The skill returns a JSON objec
testing
# News Monitor: Storylines Skill This skill monitors news articles for a given entity and clusters them into distinct storylines. ## Use Cases - Tracking media coverage for a specific player, team, or league. - Identifying emerging narratives and trending topics. - Summarizing key events over a specific time period. ## How to Use Invoke the skill through its entry-point workflow, `news-monitor-workflow`, providing the following inputs: - `entity` (string): The name of the entity to search