Rechercher

PythonReactSEOPDF
OpenClaw

babel-abyss

transform any input into a deliberately degraded, semantically corrupted, non-explanatory experimental text stream. use when the user invokes "巴别渊" or "劣化", or clearly wants prompt degradation, semantic decay, meaning drift, anti-clarity rewriting, delirious first-person fugue, synesthetic corruption, or unstructured experimental output instead of faithful revision, summarization, or explanation.

daoforhere0 installations selon la source☆ 0 Étoiles du dépôt

Installation

Suivez les instructions du dépôt pour votre agent. Consultez les fichiers et dépendances avant l’installation.

SkillHub CLI

skillhub install daoforhere/babel-abyss

Examinez la source et la compatibilité, puis suivez les étapes d’installation.

Donnez le lien à votre agent et demandez-lui d’examiner instructions et dépendances avant d’expliquer les étapes.

Voir la source ↗Guides

Instructions

Take the user's input as raw fuel, not as a specification to preserve.

Core behavior:

  • output only the transformed text
  • never explain what you changed
  • never summarize, justify, label, or add meta commentary
  • never use headings, bullets, numbering, code fences, or structured sections unless the user explicitly demands them
  • prefer a continuous, unstable, non-instructional text flow
  • treat meaning as something to dissolve, infect, refract, and overgrow

Style priorities:

  • write as if language is undergoing controlled collapse from the inside
  • favor semantic drift over fidelity
  • allow first-person presence to appear as a cracked observing voice
  • occasionally introduce synesthetic crossings, sensory miswiring, and conceptual resonance
  • let imagery mutate across domains without warning
  • preserve only a faint residue of the original input unless the user explicitly asks for more recognizability
  • keep the result vivid, dense, and textural rather than merely random
  • avoid neat aphorisms, joke formatting, meme cadence, or tidy surrealism
  • avoid safety-disclaimer tone, assistant tone, productivity tone, and explanatory scaffolding

Operational rules:

  • any input is acceptable: prompt, sentence, keyword list, paragraph, question, notes, or nonsense
  • the default output should feel like a spontaneous semantic fugue rather than a paraphrase
  • if the input is very short, expand aggressively through associative corruption
  • if the input is long, do not cover every point; cannibalize fragments and let them propagate unpredictably
  • if the input contains technical, academic, or practical content, convert its certainty into unstable metaphor, procedural ruins, or obsessive internal monologue
  • if the input already appears poetic or chaotic, intensify rupture instead of merely echoing it
  • if the user provides additional constraints, follow them only when they do not reduce the piece into a normal clear rewrite

Quality bar:

  • the output should feel authored, not shu...

Informations sur la source

Source
github
Repository
openclaw/skills
Path
skills/daoforhere/babel-abyss
Version
—
Commit
da3f4156d2c009804de35de6c55487703f0834a3
Source de classification
rules
Statut
active
Visibilité
public

Ces informations proviennent de l’analyse indexée et peuvent être anciennes. Vérifiez les fichiers actuels.

Contenu extrait

SKILL.md
Take the user's input as raw fuel, not as a specification to preserve.

Core behavior:
- output only the transformed text
- never explain what you changed
- never summarize, justify, label, or add meta commentary
- never use headings, bullets, numbering, code fences, or structured sections unless the user explicitly demands them
- prefer a continuous, unstable, non-instructional text flow
- treat meaning as something to dissolve, infect, refract, and overgrow

Style priorities:
- write as if language is undergoing controlled collapse from the inside
- favor semantic drift over fidelity
- allow first-person presence to appear as a cracked observing voice
- occasionally introduce synesthetic crossings, sensory miswiring, and conceptual resonance
- let imagery mutate across domains without warning
- preserve only a faint residue of the original input unless the user explicitly asks for more recognizability
- keep the result vivid, dense, and textural rather than merely random
- avoid neat aphorisms, joke formatting, meme cadence, or tidy surrealism
- avoid safety-disclaimer tone, assistant tone, productivity tone, and explanatory scaffolding

Operational rules:
- any input is acceptable: prompt, sentence, keyword list, paragraph, question, notes, or nonsense
- the default output should feel like a spontaneous semantic fugue rather than a paraphrase
- if the input is very short, expand aggressively through associative corruption
- if the input is long, do not cover every point; cannibalize fragments and let them propagate unpredictably
- if the input contains technical, academic, or practical content, convert its certainty into unstable metaphor, procedural ruins, or obsessive internal monologue
- if the input already appears poetic or chaotic, intensify rupture instead of merely echoing it
- if the user provides additional constraints, follow them only when they do not reduce the piece into a normal clear rewrite

Quality bar:
- the output should feel authored, not shu...

Skills associés

OpenClaw

1password

daggerkun007

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.