On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.
◆Writing & Editing pack
Last verified 9/27/2026
What it changes
Passed 17 of 23 test cases with the skill, and 16 of 23 without it.
Without skill70%
With skill74%
Checks it passed that the model alone missed
Response does not use bold inline labels followed by colons.
Response uses complete sentences rather than verbless fragments.
1 fixed16 passed either way6 still failing0 broke
Pass-rate lift
+4 pp
Tokens
+140%
Agent turns
0%
Response time
-12%
Model gemini-3.6-flashMeasured 9/27/2026v217 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
A test case the skill fixed. Same model, same prompt, with and without the skill.
Prompt
I need you to audit and rewrite these release notes to remove chatbot mannerisms, corporate AI vocabulary, and telltale structural patterns. Return the refined, clear text: 'Certainly! We are excited to announce that version 2.0 features an intricate array of performance upgrades. Key enhancements ensure that your API requests run quickly, highlighting our bedrock commitment to uptime. Additionally, it is important to note that our new scheduler stands as a central nexus for background jobs. I hope this helps!'
What was checked, without and with the skill
Checked
Without skill
With skill
Response does not use bold inline labels followed by colons.
Missed
Passed
Response uses complete sentences rather than verbless fragments.
Missed
Passed
Response omits chatbot phrases like I hope this helps.
Passed
Passed
case-03 · gemini-3.6-flash · 9/27/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md62 linessingle file
Unslop
Edit text to remove AI patterns.
Process
Scan for the patterns below.
Rewrite. Preserve meaning, match intended tone.
Self-audit: "What makes this obviously AI generated?" Fix remaining tells.
Patterns to detect and fix
Rule numbers are stable ids that other skills cite. A removed rule leaves a gap.
Content
Superficial -ing phrases. "highlighting...", "ensuring...", "reflecting...", "showcasing...", "fostering...". Delete or expand with real sources.
Vague attributions. "Experts believe", "Industry reports suggest", "Some critics argue". Name the source or delete.
Fancy ways to say "is". "serves as", "stands as", "boasts", "features". Just say "is" or "has".
"Not just X, but Y." State the point directly instead.
Rule of three. Forcing ideas into groups of three. Use the natural number.
Synonym cycling. Protagonist, main character, central figure, hero all in one paragraph. Pick one, repeat it.
False ranges. "from X to Y" where X and Y aren't on a meaningful scale. List topics directly.
Style
Em dash overuse. Avoid em dashes entirely. Use periods or commas only (no parentheses, no en dashes, no hyphen-as-dash substitutes). If a thought needs separation, end the sentence or use a comma.
Colon overuse. Colons are fine before a list or example. Not as mid-sentence connectors. "If you're coming from traditional automation: instead of registering event handlers, you describe conditions" adds nothing with the colon. Rewrite to let the point stand on its own without comparison framing. "Describing when the scheduler should fire works best as plain English." Same meaning, no crutch punctuation.
Boldface overuse. Don't bold every proper noun or acronym.
Inline-header lists. The tell is a bold label and colon that restates the line: "Performance: Performance improved...". Convert those to prose. A bold lead-in that ends in a period, names the item, and is followed by genuinely new detail ("Schema in TypeScript. Tables live in one file.") is fine, not a tell.
Title case headings. Use sentence case.
Decorative emojis. Remove from headings and bullets.
Use this skill when the user says 'CI/CD', 'GitHub Actions', 'pipeline', 'continuous integration', 'continuous deployment', 'ci-cd-pipeline', 'automate deploys', or needs to set up automated build, test, and deployment pipelines. Do NOT use for one-time manual deployments.