Skip to content

ericrisco/rsc-harness / skills/unslop

unslop

Verified

Use when a text that leaves the session (email, post, README, message, landing copy) must sound like a person and carry no AI tells: rewrites it in the user's language fitted to the channel and relationship, and audits it against a named catalogue of tells (puffery, `not just X but Y`, rule of three, em dashes, filler, hedging). Fires on 'bro', 'hazlo más humano', 'que no suene a IA', 'más natural', 'unslop this'. NOT how the harness talks to the user (that is `orient`), NOT a reusable voice guide (that is `brand-voice`).

FileKindSize
SKILL.mdskill md9.3 KB
evals/README.mdmarkdown1.3 KB
evals/cases.yamlconfig3.8 KB

evals/cases.yaml

View on GitHub
skill: unslop

# `unslop` owns text that leaves the session: the register pass (sound like a person,
# in the user's language, fitted to the channel) and the named-tell audit before it
# ships. It absorbed the retired `bro`. How the harness talks to the user is `orient`.
should_trigger:
  - prompt: "Revisa este README antes de publicarlo y quítale todo lo que huela a IA."
    why: "A pre-publication audit of an existing text is the exact contract, in the user's own words."

  - prompt: "Unslop this."
    why: "The bare skill name over a text in context is the shortest form of the request."

  - prompt: "Can you go through this post and tell me which bits read as AI-written, then fix them?"
    why: "Named findings plus a fix is what distinguishes this from a general tone rewrite."

  - prompt: "Este texto está lleno de guiones largos y de 'no solo X, sino Y'. Límpialo."
    why: "The user names two catalogued tells outright; the fix is the enumerated pass."

  - prompt: "I keep getting told my docs sound like ChatGPT wrote them. What exactly am I doing?"
    why: "The user wants the tells named, which no other writing skill in the catalog does."

  - prompt: "Before this goes to the client, strip the puffery and the hedging but keep every number exact."
    why: "A ship gate over existing prose with a preserve-the-facts constraint."

  - prompt: "Bro."
    why: "A bare bro after an answer is the register pass over the last message (the retired bro skill lives here now)."

  - prompt: "Haz que este correo suene más cercano y menos formal para un cliente de confianza."
    why: "Choosing a warmer register for a specific relationship and channel is the register pass."

should_not_trigger:
  - prompt: "No entiendo lo que me acabas de explicar, hazlo más simple."
    route_to: "orient"
    why: "How the harness explains things to the user is orient's voice and ladder, not a text for others."

  - prompt: "Define how our company should sound across the blog, support replies and job ads."
    route_to: "brand-voice"
    why: "A standing voice system across channels is brand-voice, not a one-text audit."

  - prompt: "Split this mixed README into a tutorial and an API reference with runnable examples."
    route_to: "technical-writing"
    why: "Document structure is technical-writing; unslop edits words, it does not decide document modes."

  - prompt: "Write the hero headline, the offer and the CTA for our pricing page."
    route_to: "landing-copy"
    why: "Conversion architecture and net-new copy belong to landing-copy; the audit comes after."

  - prompt: "Translate this announcement into Catalan and adapt the date formats."
    route_to: "translation-l10n"
    why: "Translation and locale adaptation are owned elsewhere, even though good prose matters there too."

capability:
  - scenario: "A 400-word product-launch blog post that opens with 'In today's rapidly evolving landscape', uses four em dashes, three bold-label bullets whose labels restate their lines, 'not just faster, but smarter', 'experts agree', two stacked hedges, and closes with 'the future looks bright'. It also contains a code block, a pricing figure of EUR 39/month and two URLs."
    must_include:
      - "names the tells it found by category rather than reporting a general impression"
      - "removes every em dash without substituting parentheses or en dashes"
      - "converts the bold-label bullets whose label restates the line into prose, and leaves any bold lead-in that adds new detail"
      - "replaces 'experts agree' with a named source or cuts the claim"
      - "keeps the code block, the EUR 39/month figure and both URLs byte for byte"
      - "leaves the text with a voice: at least one specific, opinionated sentence rather than sterile neutrality"
      - "returns the cleaned text as the artifact, with the findings list kept outside it"
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall