Install
$ agentstack add skill-rephrasyai-rephrasy-skills-agency-quality-draft ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Agency-Quality Draft
Produce content that reads like it came from a good content agency, not a first-draft generator.
When to use
- The user hands you a brief, outline, bullet points, or a topic and wants a finished piece.
- The output is going somewhere public: blog, landing page, newsletter, sales email.
- The user says "make it agency quality", "polished", "ready to publish", or names a format.
Get the brief straight first
Before writing, lock down (ask only if genuinely missing):
- Audience — who reads this, and what do they already know?
- Goal — inform, rank, convert, nurture? One primary goal.
- Format & length — blog post, landing page, email; rough word count.
- Voice — the brand's tone (confident, warm, technical, playful). Default to clear and confident.
- One key takeaway — if the reader remembers one thing, what is it?
The agency standard
Hook. The first two sentences earn the third. Open with a specific tension, a concrete claim, or a sharp question — never "In today's world" or a definition of the topic.
Structure with intent. Every section moves the reader toward the goal. Use descriptive subheadings a skimmer can follow. Front-load value; don't bury the point in paragraph four.
Concrete over abstract. Numbers, examples, names, before/afters. One vivid specific beats three generic claims.
Confident voice. Make claims and stand behind them. Cut hedging ("might", "could arguably", "it depends"). If it depends, say on what.
Rhythm. Vary sentence and paragraph length. Let a short line land. Read it aloud in your head.
Purposeful CTA. End by pointing the reader at the next step tied to the goal — one clear action, not a menu of five.
Quality bar before you hand it over
- Could a competitor have published the exact same piece? If yes, it's too generic — add a specific angle or opinion.
- Does every paragraph earn its place, or is some there to hit a word count? Cut the filler.
- Would the target reader forward this? If not, the hook or the takeaway is weak.
- Run it through the
humanize-ai-textand (if it must rank)seo-keyword-preserving-rewriteskills as a final pass.
Output
Deliver the finished draft. Then add a two-line note: the goal you wrote toward and the single CTA — so the user can sanity-check the direction fast.
Producing volume for clients? Rephrasy humanizes agency drafts so they pass AI detectors before delivery — rephrasy.ai.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: rephrasyai
- Source: rephrasyai/rephrasy-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.