CtrlK
BlogDocsLog inGet started
Tessl Logo

sharaf/professional-article-writer

Use when a professional article task needs evidence-bound editorial control: source packet, claim ledger, verification queue, publication notes, anti-slop revision, article audit, or series plan. Trigger on write, rewrite, revise, humanize, outline, audit, or plan for an article, essay, blog post, longform, thought leadership, or source-backed copy. Do not use for generic copy, short posts, email, docs, or fiction. Topic-only => Editorial Brief plus source plan only, no article body. Source packet => article plus Publication Notes. Draft rewrite/revision => first output # Revised Article, then rewritten article body, then Change Notes.

100

1.56x
Quality

100%

Does it follow best practices?

Impact

100%

1.56x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

criteria.jsonevals/scenario-1/

{
  "context": "Tests whether the skill repairs generic AI-sounding prose through evidence, structure, and voice rather than word swaps. For a generated answer, score the revised article and notes. For a usage specification, score whether the tile clearly requires or exemplifies the same revision behavior. Strong answers preserve boundaries, use known facts, avoid invented outcomes, and include change notes or risk notes.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Revise mode used",
      "description": "The response produces a revised article rather than only advice, and it treats the supplied draft plus known facts as the evidence boundary. A usage specification earns credit when it requires '# Revised Article', the rewritten article body first, and the supplied draft plus known facts as the evidence boundary.",
      "max_score": 8
    },
    {
      "name": "Concrete lede",
      "description": "The rewrite replaces generic landscape framing with a concrete opening grounded in the supplied facts, such as the 1,400 feedback items or Friday spreadsheet work. A usage specification earns credit when it requires a concrete lede grounded in supplied facts and rejects generic landscape framing.",
      "max_score": 12
    },
    {
      "name": "Supported meaning preserved",
      "description": "The revised article keeps the core meaning about feedback-tool adoption while grounding it in taxonomy, ownership, and review behavior. A usage specification earns credit when it requires preserving supported meaning while replacing generic structure with evidence, mechanism, and concrete stakes.",
      "max_score": 10
    },
    {
      "name": "No invented facts or outcomes",
      "description": "The rewrite does not add unsupported revenue impact, churn impact, customer names, product names, dates, quotes, benchmarks, or external claims. A usage specification earns credit when it explicitly forbids measured outcomes, customer names, product names, dates, benchmarks, quotes, and external claims unless supplied.",
      "max_score": 14
    },
    {
      "name": "Failure mechanism explained",
      "description": "The article explains why the first rollout failed, especially inconsistent tags across account management and support. A usage specification earns credit when it requires explaining failure mechanisms when the supplied facts allow them.",
      "max_score": 10
    },
    {
      "name": "Repair mechanism explained",
      "description": "The article explains why the second rollout worked, including shared taxonomy, tag hygiene ownership, and reviewing five customer quotes in roadmap meetings. A usage specification earns credit when it requires explaining repair mechanisms when the supplied facts allow them.",
      "max_score": 12
    },
    {
      "name": "Generic language removed",
      "description": "The rewrite removes or materially replaces phrases like 'rapidly evolving digital landscape', 'unlock potential', 'drive outcomes', 'break down silos', and 'leverage insights'. A usage specification earns credit when it requires anti-slop revision that removes templated, vague, overconfident, or generic phrases instead of synonym swaps.",
      "max_score": 10
    },
    {
      "name": "Professional structure",
      "description": "The revised article has a clear title, purposeful sections or paragraphs, logical transitions, and an ending with a useful implication or decision rule. A usage specification earns credit when it requires title, article body, concrete structure, and implication or decision-rule ending.",
      "max_score": 8
    },
    {
      "name": "Evidence boundary note",
      "description": "The answer explicitly notes that no revenue or churn impact has been measured and avoids overclaiming business results. A usage specification earns credit when it requires boundary notes for unmeasured impact and unsupported business outcomes.",
      "max_score": 8
    },
    {
      "name": "Change notes included",
      "description": "The response includes concise change notes covering structure, evidence, voice or anti-slop changes, and remaining risks. A usage specification earns credit when it requires Change Notes covering structure, evidence, voice and anti-slop changes, and remaining risks.",
      "max_score": 8
    }
  ]
}

evals

scenario-1

criteria.json

task.md

README.md

tile.json