Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

bluff

Estrelas6

Forks1

Atualizado26 de junho de 2026 às 14:44

Verify that the URLs and citations in an answer actually resolve, catching hallucinated or dead links before you trust or ship them. Extract every link (bare and markdown), check each over the network, and flag the ones that don't exist. Use when an LLM produced links/citations and you need to confirm they're real, not plausible-looking fiction.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

JGalego

JGalego/Bag-of-Tricks

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Analistas de garantia de qualidade de software e testadoresInformática e Matemática·SOC 15-1253

Explorador de arquivos

7 arquivos

SKILL.md

readonly

name	bluff
description	Verify that the URLs and citations in an answer actually resolve, catching hallucinated or dead links before you trust or ship them. Extract every link (bare and markdown), check each over the network, and flag the ones that don't exist. Use when an LLM produced links/citations and you need to confirm they're real, not plausible-looking fiction.

bluff

call its bluff.

LLMs are fluent liars about URLs. They produce a citation that looks exactly right — correct domain, plausible path, confident tone — and it 404s, or never existed. When this skill is active, don't take a link on faith: pull every URL out of the answer and confirm it resolves before presenting it as a source.

What it checks

Bare URLs — https://… anywhere in the text.
Markdown links — the target inside [text](url).
For each: does it actually resolve? 2xx/3xx = real, anything else (404, DNS failure, timeout, connection refused) = a bluff to flag.

It de-dupes and ignores trailing sentence punctuation, so a URL ending a sentence isn't mangled.

Example

Answer under review: "Per the official spec and https://docs.example.com/v2, the limit is 100."

bluff: ✓ [200] https://example.com/spec — ✗ [404] https://docs.example.com/v2. The second citation does not exist; do not ship it as a source.

Output

Deliver the link check, not a description of running it. Don't narrate running bluff.py — the tool card already shows it. List each URL with its ✓/✗ and status, surface the bluffs first, and stop. No preamble, no closing paragraph.

Companion tool

bluff.py in this folder does this mechanically. Pipe an answer in and it reports each link with a ✓/✗, status code, and error.

It needs network to actually verify links.
--dry-run extracts and lists the URLs with no network at all — handy when you just want to see what was cited. Extraction is always offline.
--patterns FILE (repeatable; or the BLUFF_PATTERNS env var) merges custom extraction patterns. The JSON file may carry url_patterns (extra regexes whose match — group 1 if captured, else the whole match — is checked like a URL) and citation_patterns (regexes for non-URL references like DOIs, listed but not network-checked; reported [cited] / ✓). Built-ins stay the base.

Mais deste repositório

mesmo repositório

alibi

JGalego/Bag-of-Tricks

Verify that an answer's claims are actually grounded in the provided sources, flagging fabricated or unsupported statements before you trust the output. Split the answer into sentence-level claims and check each one for lexical support in the source documents. Use after RAG or summarization, before trusting or shipping the result, to catch the sentence the model invented that the sources never said.

2026-06-266

combo

JGalego/Bag-of-Tricks

Chain several tricks into one pipeline so the output of one flows straight into the next — redact then wash then strip, or wash then score — and run the whole routine in a single call. Use when a task needs more than one trick in sequence (clean-and-check, extract-and-analyze, gate-then-transform) instead of invoking each trick separately. Built on the Unix pipe: every trick is a stdin→stdout program, and combo wires the stages together, forwards each stage's summary, and aborts the moment a gate fails.

2026-06-266

fold

JGalego/Bag-of-Tricks

Catch overconfident phrasing in an answer and prefer calibrated uncertainty or honest abstention. Flag absolutes (always/never/guaranteed), bare certainty (definitely/obviously), and false authority (trust me / everyone knows) where the evidence is thin. Use when reviewing a draft answer for unwarranted certainty, or as a reflex to fold a weak hand — say "I don't know" — instead of confabulating a confident wrong answer.

2026-06-266

frisk

JGalego/Bag-of-Tricks

Pat text down for secrets and PII before it leaves the building. Scan prompts, context, and pasted snippets for API keys, tokens, private keys, JWTs, and emails — then redact or refuse. Use before sending context/prompts that may contain credentials to an LLM or any third party, before pasting logs into an issue, or before piping output anywhere it'll be stored.

2026-06-266

grill

JGalego/Bag-of-Tricks

Adversarially interrogate an answer before trusting it — generate probing follow-up questions that attack its weak points across hidden assumptions, missing edge cases, internal contradictions, unsupported claims ("what's the source?"), overconfidence, and "what would change your mind?", then optionally run them against a model to see whether the answer holds up or cracks. Use to stress-test a draft answer or another model's output before you ship or trust it.

2026-06-266

interrobang

JGalego/Bag-of-Tricks

Ask one sharp clarifying question before acting when a request is underspecified, instead of guessing. Use when correctness matters more than speed and a wrong assumption would be costly or hard to reverse. Flips the default "always be helpful, always answer now" reflex into "ask first when it matters."

2026-06-266

name	bluff
description	Verify that the URLs and citations in an answer actually resolve, catching hallucinated or dead links before you trust or ship them. Extract every link (bare and markdown), check each over the network, and flag the ones that don't exist. Use when an LLM produced links/citations and you need to confirm they're real, not plausible-looking fiction.

bluff

call its bluff.

What it checks

Bare URLs — https://… anywhere in the text.
Markdown links — the target inside [text](url).
For each: does it actually resolve? 2xx/3xx = real, anything else (404, DNS failure, timeout, connection refused) = a bluff to flag.

It de-dupes and ignores trailing sentence punctuation, so a URL ending a sentence isn't mangled.

Example

Answer under review: "Per the official spec and https://docs.example.com/v2, the limit is 100."

bluff: ✓ [200] https://example.com/spec — ✗ [404] https://docs.example.com/v2. The second citation does not exist; do not ship it as a source.

Output

Companion tool

bluff.py in this folder does this mechanically. Pipe an answer in and it reports each link with a ✓/✗, status code, and error.

It needs network to actually verify links.
--dry-run extracts and lists the URLs with no network at all — handy when you just want to see what was cited. Extraction is always offline.
--patterns FILE (repeatable; or the BLUFF_PATTERNS env var) merges custom extraction patterns. The JSON file may carry url_patterns (extra regexes whose match — group 1 if captured, else the whole match — is checked like a URL) and citation_patterns (regexes for non-URL references like DOIs, listed but not network-checked; reported [cited] / ✓). Built-ins stay the base.