OpenSEO is an open-source SEO platform for keyword research, rank tracking, competitor analysis, backlink analysis, site audits, and AI visibility work. It connects SEO data to AI agents through an MCP server and reusable agent skills, while allowing users to supply their own DataForSEO API key and self-host the tool. Catalogue add-ons guide agents through OpenSEO's SEO workflows.
Borrowing it
Nothing to install: this file belongs to every-app/open-seo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/every-app/open-seo/main/.agents/skills/deslop/SKILL.mdgit clone --depth 1 https://github.com/every-app/open-seoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/every-app/open-seo/deslop)<a href="https://agentmods.dev/skills/every-app/open-seo/deslop"><img src="https://agentmods.dev/badge/skills/every-app/open-seo/deslop/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/every-app/open-seo/deslop"><img src="https://agentmods.dev/badge/skills/every-app/open-seo/deslop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.00552 |
| Opus 5.5 | $0.00024 | $0.00221 |
| Sonnet 5.5 | $0.00012 | $0.00110 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
deslop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 21d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deslop
Make prose sound like a specific person wrote it. Fix each tell by stating the underlying claim plainly, not by swapping in a new flourish.
Cut or rewrite
- Filler: throat-clearing ("Here's the thing:"), emphasis crutches ("Let that sink in."), meta-commentary ("In this section, we'll explore..."), "It's worth noting," and business jargon ("navigate the landscape," "leverage").
- Staged contrasts like "Not X. Y." or "It's not X, it's Y." State Y.
- Manufactured rhythm: dramatic fragments ("Speed. That's it."), rhetorical questions answered right away ("The result? Devastating."), three-part phrasing that exists only for cadence ("fast, simple, and powerful"), and paragraphs that end on a one-liner restating the paragraph.
- AI vocabulary: "delve," "tapestry," "quietly," "serves as," "highlighting its importance," invented concept labels ("the supervision paradox"), and inflated stakes.
- Vagueness: declaratives that name nothing ("The reasons are structural"), "experts argue" with no name, and "every," "always" or "never" doing vague work.
- False agency, where a thing does a person's verb ("the complaint becomes a fix"). Name who did it.
- Signposting: announcing what you're about to say, then summarizing what you said. "In conclusion." "Despite these challenges."
- Formatting tells: em dashes, unicode arrows, and lists where every item opens with a bolded keyword.
Keep
Specifics (names, numbers, examples), "you" for the reader in blog posts, varied sentence length, and short plain lines that carry information. Keep bullet points and numbered steps for actions and instructions; don't fold them back into paragraphs. When editing someone else's writing, keep their voice.
Example
Before: "Here's the thing: most pipelines break in production. Not because the code is bad. Because the data is bad. Let that sink in."
After: "Most pipelines break in production. The code runs fine. The data doesn't match the assumptions baked into it."
Adapted from stephenturner/skill-deslop (MIT, see LICENSE).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 21d ago Changed · -100 lines · -102 tokens per session 0b5127dc7b2c
- 1mo ago First seen · 134 lines · 163 tokens per session scan A 29d9ef462029
deslop is a skill published in the GitHub repository every-app/open-seo (25,345 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 552 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
altorank
Run AltoRank through its hosted MCP server: readiness audits, Search Console, keyword research, and SEO drafts into a review queue.
setup-svelte-vitals
Set up svelte-vitals in a SvelteKit project: inspect what the project already uses, derive a svelte-vitals.config from its markuplint / eslint-plugin-check-file config and its actual directory conventions, measure each candidate rule before adopting it, and hand the remaining targets to svelte-vitals install. Use when…
wordstat-collector
A tool that collects search statistics from Yandex Wordstat, the Yandex service for researching what people search for. It returns search phrases and their frequencies for Russian-language market research.
improve-svelte
Survey a whole SvelteKit codebase as a senior Svelte/SvelteKit engineer, using svelte-vitals' scan as evidence, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when…
seo-pipeline-llm
4-stage SEO content pipeline: keyword research → competitor scraping → SEO analysis → content creation. Outputs local files, no CMS integration.
seo-pipeline-bash
One-shot SEO content pipeline: scrape keywords from SERP and produce article markdown files via Browser Use SDK or DuckDuckGo fallback.