suede-skills-mcp
A read-only MCP server for discovering Suede skills and generating Suede-style plans, audits, grades, and checklists.
List Suede skills and specialties, with optional area/specialty filters.
Search skills by task description and rank best-matching routes.
Fetch a skill’s metadata and optionally its full
SKILL.mdinstructions.Explain install options for Codex, Claude/plugin, MCP, and skill-copy surfaces.
Turn a goal into an ordered Suede skill workflow.
Create SEO/AEO/AI-EO copy audit scaffolds.
Create A–F visibility and code grading scaffolds.
Generate multi-lane QA checklists.
Check pasted copy for style issues, bans, weak phrasing, and missing CTAs.
Run a live public-page audit covering crawlability, AI answer bots, metadata, schema, CTAs, sitemap,
llms.txt, and share previews.
Install · The skills · Docs site · Skill catalog · Blog · MCP · @johnnysuede
By Jason Colapietro / Suede AI
Suede Awesome Everything
AI agent skills, scored 0–99.
Compare skills by their 0–99 quality scores: verified numeric scores from Suede’s published structural rubric, with source links and browsing by category and publisher. Published scores retain the current 99-point cap; quality scores do not certify security.
Compare scores · Categories · Publishers · Featured projects · Contribute a listing
Related MCP server: Omni Skills
Recognition and discovery
Suede AI SEO, the company’s AI search visibility practice, is #1 among Palm Beach County-based companies listed in The Manifest’s Florida AI Deployment directory, and #25 statewide, as of October 30, 2026. The county position is derived from the directory’s listed company locations. View the ranking. Gigawatt Group also compares Suede AI’s managed GEO practice with Profound.
The SEO skill is listed on seoskills.sh, updated October 24, 2026. The project’s Hysen Labs, Skills Directory and Trendshift badges link directly to their reports above.
Suede AI Skills for SEO and business growth
Suede AI Skills gives founders, marketers, and small teams reusable workflows for SEO audits, AI search visibility, conversion copy, and business operations. Run them in Claude Code or OpenAI Codex, with instructions you can inspect and adapt to your business.
Start with the business task:
Search visibility: audit a page with
suede-seo-audit, or plan content for AI search withsuede-ai-seo.Positioning and conversion: define your audience and offer with
suede-product-marketing, then write page copy withsuede-copy.Business operations: map bottlenecks with
suede-ops-assessmentand define the system withsuede-ops-architecture.
These are public, broadly reusable, open-source skill folders, installable from one path. Every skills/<name>/SKILL.md is readable on GitHub. The pack also covers campaign planning, code review, app delivery, and music release prep. Original work is MIT licensed; adapted components keep their upstream licenses, listed in NOTICE.md. No binaries, no telemetry, no accounts.
Install in 30 seconds
Claude Code — add the marketplace, install the pack:
/plugin marketplace add JasonColapietro/suede-creator-skills
/plugin install suede-skills@suedesuede-skills installs every skill. Want less? Three focused subsets: /plugin install suede-marketing@suede (40 marketing and growth skills), /plugin install suede-agent-workflows@suede (Suede Thought Graph shipping, orchestration, workflows, evals), and /plugin install suede-code@suede (review, grade, ship-gate).
Codex — add the Codex-native marketplace, install the complete plugin:
codex plugin marketplace add JasonColapietro/suede-creator-skills --ref main
codex plugin add suede-skills@suede-codexThe Codex plugin loads every skill and registers 1 read-only MCP server with 12 tools. Restart Codex after installing or updating.
Hermes Agent (Nous Research) — this repo is a skills tap. Subscribe to browse and search the whole pack, or install one skill without subscribing:
hermes skills tap add JasonColapietro/suede-creator-skills
hermes skills search seo
hermes skills install JasonColapietro/suede-creator-skills/skills/suede-seo-auditHermes installs the whole skill folder — references/, agents/, evals/ — into ~/.hermes/skills/, security-scans it first, and shows it as /suede-seo-audit in chat. It carries the skills only: the MCP discovery server and the bundled Suede Thought Graph workflow are Claude Code and Codex surfaces.
Any agent (Cursor, Copilot, Windsurf, Claude Code, Codex) via the skills CLI:
npx skills add JasonColapietro/suede-creator-skillsPython (PyPI): install the package, then load the pack into your agent. --target codex installs into Codex, and existing folders are kept unless you pass --force:
pipx install suede-creator-skills && suede-skills installPrefer a clone? install.sh copies every skill into ~/.claude/skills/ and prints the installed count:
git clone https://github.com/JasonColapietro/suede-creator-skills.git && bash suede-creator-skills/install.shYou can also copy individual skill folders into .claude/skills/ (project) or
~/.claude/skills/ (user). One exception: the hardened suede-graph-flo-xr JavaScript
workflow also requires the skill's bundled agents/suede-graph-flo-xr-*.md profiles in
~/.claude/agents and macOS sandbox-exec. The suede-skills and
suede-agent-workflows Claude plugins, plus install.sh, install those profiles;
a skill-folder-only or generic skills-CLI install does
not. Codex can use the skill's orchestration contract, but does not execute this
Claude Workflow runner. The caller passes the namespace explicitly on every
launch: suede-skills for the full plugin, suede-agent-workflows for the
focused plugin, and the empty string for clone or manual user-agent installs.
Codex — install one skill from GitHub:
python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \
--repo JasonColapietro/suede-creator-skills \
--path skills/suede-agent-teamsSwap skills/<skill> for any skill folder, or pass extra skills/<name> paths to install several at once. Restart Codex after installing.
Claude Code — project-level copy of a single skill:
git clone https://github.com/JasonColapietro/suede-creator-skills.git /tmp/suede-creator-skills
mkdir -p .claude/skills
cp -R /tmp/suede-creator-skills/skills/suede-agent-teams .claude/skills/For a user-level install, copy into ~/.claude/skills/ instead. Claude.ai and organization-managed Claude Skills may use upload or admin-managed flows instead of filesystem copy.
MCP — dependency-free stdio server:
node mcp/suede-skills-mcp.mjs --profile allExposes 12 tools (list_suede_skills, list_suede_specialties, search_suede_skills, get_suede_skill, plan_suede_workflow, suede_live_page_audit, suede_copy_check, suede_install_options, suede_copy_seo_audit, suede_visibility_grade, suede_code_grade, suede_qa_checklist), 7 resources, a suede://skill/{name} template, and 5 prompts over JSON-RPC. suede_live_page_audit grades any public URL A-F for Google and AI search from the HTML it serves. Run it in Docker with docker build -t suede-skills-mcp . && docker run -i --rm suede-skills-mcp.
Find it on
Listed on skills.sh · SkillsMP · SkillsLLM · HOL Plugin Registry · Skills Directory · ClaudSkills · PyPI · Official MCP Registry · npm · Glama · MCP Market · Awesome Claude Skills (awesomeclaude.ai) · VoltAgent/awesome-agent-skills · Trendshift.
All 34 directories, registries and curated lists: skills.suedeai.ai/listings.html
Try it right now
Install the pack, then give your agent a page to audit:
Use suede-seo-audit to audit this page for search visibility and return prioritized findings with exact copy fixes: [your page URL]For a nontrivial multi-file change, run the ship DAG:
Use suede-graph-flo-xr to take this change through the canonical Suede DAG: research it, build it in disjoint lanes, refute the review findings, and hand back evidence.If the pack saves you an hour, star the repo — stars are how other builders find it.
Orchestration: broad outcomes, adversarial review
Tell your agent "max effort, spare no compute, fix everything" and most of the time you get enthusiasm, not engineering. The orchestration lane turns that intent into structure:
suede-graph-flo-xrruns a Suede Thought Graph shipping search on a repo: generate competing plans, score and prune them, adversarially refute and improve survivors, aggregate compatible lanes, then build, review, and gate only the selected plan. Light/standard/deep are capped at 55/110/200 calls. Production reads only; it never deploys.suede-agent-teamswires complex changes into coordinated agent lanes with WIP collision detection, RFC mode, feature-flag strategy, rollback trees, and a handoff checklist that won't close without evidence. Its public-contribution mode adds scored issue queues, atomic leases, isolated worktrees, and authority-gated contribution packets.suede-ship-copyis a separate copy-only orchestration DAG for one high-stakes piece of writing: five blind research lenses, a claim audit that closes the set of assertable facts, disjoint section writers, adversarial refutation, a deslop pass, and a publish-readiness gate.
The A–F ship grade
suede-code runs a findings pass (TypeScript, React, Next.js, OWASP, and database checklists), then returns a grade card scoring seven lanes: Correctness, Security and permissions, Data and state, Domain truth, UX and release behavior, Tests and verification, and Deploy readiness. The weakest lane caps the grade, and auth and payment surfaces carry grade caps of their own.
If it hits an instant-F trigger — a hardcoded secret, a permission check bypassable via a request param — the grade locks to F with the exact file and line, and no other lane can raise it. A polite review tells you what could be better. A grade tells you whether to ship.
The skills
Every link below goes to the skill's folder in this repo; the skill catalog has the same list with install commands per skill.
Agent orchestration & workflows
Skill | What it does |
Coordinate agent lanes and public contribution programs with collision checks, atomic issue leases, review gates, and a signed handoff | |
Suede Thought Graph repo shipping: search competing plans, score and prune, refute and improve, aggregate compatible lanes, then mutate only the selected plan; 55/110/200-call caps; production reads only, never deploys | |
Copy-only orchestration DAG for one high-stakes piece: blind research, claim audit, section writers, refutation, publish gate | |
AI-SPEC artifacts, failure-mode rubrics, eval cases, and acceptance gates for LLM, RAG, classifier, and agent surfaces | |
Umbrella router that loads the full pack, picks the specialist, and hands back one scored next move as a runnable prompt | |
Map how work actually happens before anyone designs a system: interviews with the people doing it, a silo inventory, friction measured in the operation's own numbers | |
Fix the shape of a system before anyone builds it: entity schema, one write path per entity, each unit of work routed to an automation, an agent, or a human |
Code quality & shipping
Skill | What it does |
Review + A–F grade in one pass, 7 lanes, instant-F triggers; findings-only and grade-only modes | |
Write CI that gates the merge — stack/lockfile detection, one required check, branch protection | |
Hold one domain consistent across web, iOS, Android, and docs with a contract generated from the reference surface | |
Turn a clip, talk moment, or transcript into a clip-to-guide funnel package with rights routing and an evidence gate |
Design, copy & SEO
Skill | What it does |
SEO/AEO/GEO, metadata, schema, internal-link, and intent audit | |
Read-only whole-flow and UI diff reviews, plus authorized builds with existing brand, tokens, hierarchy, accessibility and rendered visual QA | |
Dev-only workbenches importing real components with synthetic states, stress fixtures and live variants | |
Read-only explanations of interface mechanisms, traced to source locations and observed behavior | |
Full writing lane: conversion and SEO copy, headline formulas, persuasion frameworks, A/B variants, anti-slop gate, copy score | |
Context-aware anti-slop cleanup or findings-only audit that preserves facts, voice, house style, and intentional phrasing, with a 50-point score gate | |
A–F page grades for findability, clarity, CTA pull, proof, and AI citation readiness | |
Funnel analysis, friction audit, conversion math, ranked quick-wins | |
Package work as a launch: docs, install commands, proof links, QA |
Mobile apps
Skill | What it does |
Convert any website into an App Store-ready iOS app: audit, 4.2 wrapper-risk gate, shell strategy, release gate | |
One prompt to a Play Store-ready native Android app: Kotlin + Jetpack Compose scaffold, Play Billing, ASO listing, signed release | |
Ship an Android release through the Play Developer API: credential preflight, AAB checks, staged rollout, and a track readback |
Creator rights & release
Rights and release-prep tooling for working musicians and creators — see the skill catalog for each one: suede-campaign-in-a-box, suede-sync-packaging, suede-release-linter, suede-rights-passport (rights gap audit, then the transfer package).
Marketing & growth
Thirty-eight skills covering paid acquisition and outbound, monetization, lifecycle and
retention, and the measurement and operations layer — suede-ads, suede-ad-creative,
suede-cold-email, suede-influencer-outreach, suede-prospecting, suede-public-relations, suede-directory-submissions,
suede-pricing, suede-offers, suede-paywalls, suede-onboarding,
suede-churn-prevention, suede-emails, suede-referrals, suede-co-marketing,
suede-community-marketing, suede-lead-magnets, suede-free-tools, suede-sms,
suede-marketing-loops, suede-analytics, suede-ab-testing, suede-revops,
suede-sales-enablement, suede-programmatic-seo, suede-content-strategy,
suede-marketing-plan, suede-marketing-council, suede-social,
suede-aso, suede-video, suede-image, suede-product-marketing, suede-competitors,
suede-competitor-profiling, suede-customer-research,
suede-ai-seo, suede-attribution.
The content-production lane adds one more workflow:
Skill | What it does |
Runs one idea through a six-role content pipeline — written role contracts, an inspectable campaign record, seven distribution entryways so no two assets argue the same thing, and a keep/test/stop review |
From the blog
Essays on why the pack is built the way it is:
Two skills, and the bugs that wrote them — Google Play publishing from the terminal, and a parity contract that keeps four surfaces of one product honest
71 skills installed. Your agent reads almost none of them. — progressive disclosure, Suede Thought Graph shipping search, and the MCP layer
Why breadth is free now, and what that changes — the economics of broad skill packs
NOT FOR: the two words that make a big skill pack work — how skills route without colliding
Your memory file is a tax you pay on every prompt — why memory belongs in skills
Two new lanes: a next-action recommender and a one-prompt Android app factory
Public pages
GitHub Pages site — public documentation generated from this repo
Skill docs catalog — every skill with install and resource links
Agent Skills Directory (data) — other authors' public skills in sixteen category directories, each scored 0–99 by the published, graded Suede Skill Check and linked to its source; listings scoring 80–99 offer separate numeric and A/B README shields, both linking to their listing. Authors can request a listing, score help or badge verification; displaying either valid linked badge (or both) can qualify for a limited-time feature placement after verification. Security scan status is separate from the structural score
Installs and MCP page — install commands plus the Suede AI Skills MCP
S-Tier: the builder's book (source, PDF) — a free, roughly 29,900-word book on how Agent Skills work and how to get genuinely good with them
MCP server
The repo ships a dependency-free stdio MCP server at mcp/. It implements initialize, tools/list, tools/call, resources/list, resources/read, prompts/list, and prompts/get.
node mcp/suede-skills-mcp.mjs --profile allTools (9) | Resources (7) | Prompts (5) |
| catalog, specialties, plugins, copy-seo-audit, visibility-grade, code-grade, qa-checklist | discovery and audit prompts |
Safety
Core local workflows inspect current files, pages, repos, and local folders without uploading by default or granting new authority. Explicit browser, deployment, marketplace, publishing, or support workflows use the operator's existing authenticated access, and only when that action is authorized. The skills never request secrets.
The creator skills generate private drafts by default: reports and packages can contain names, payment notes, file names, hashes, rights claims, and provenance notes. Review and redact before publishing or sending outside the intended workflow.
CLI flags on the creator scripts: --include-hidden, --include-other, --include-absolute-paths, and --force. Scripts skip hidden files, secret-like files, dependency folders, and build outputs by default, and refuse to write a package into or under its source folder.
Every skill ships with a skill card — a release record following the NVIDIA skill-card template that states the skill's purpose, owner, license, dependencies, known risks and mitigations, output, and release evidence, so a reviewer can evaluate it without opening the source first.
Status
The creator scripts are dependency-light Python and run on the standard library. Optional enhancements use installed packages when available — Pillow for artwork dimension checks, PyYAML for YAML metadata:
python3 -m pip install PyYAMLFrequently asked questions
What is Suede AI Skills?
Suede AI Skills is an open-source pack of agent skills for Claude Code and OpenAI Codex. Each skill is a folder with a SKILL.md that teaches the agent a repeatable workflow: SEO audits, AI search visibility, conversion copy, code review, ship gates and app delivery.
Who created Suede AI Skills?
Jason Colapietro, founder and CEO of Suede AI, created Suede AI Skills and maintains it at github.com/JasonColapietro/suede-creator-skills.
How do I install Suede AI Skills in Claude Code?
Run /plugin marketplace add JasonColapietro/suede-creator-skills, then /plugin install suede-skills@suede. See Install in 30 seconds for the focused subsets.
How do I install Suede AI Skills in Codex?
Run codex plugin marketplace add JasonColapietro/suede-creator-skills --ref main, then codex plugin add suede-skills@suede-codex, and restart Codex.
Is Suede AI Skills free?
Yes. Original work is MIT licensed, and adapted components keep their upstream licenses, listed in NOTICE.md. The pack has no binaries, no telemetry and no accounts.
Does Suede AI Skills include an MCP server?
Yes. A dependency-free stdio MCP server ships in mcp/ and is published to npm as suede-skills-mcp and listed in the Official MCP Registry and on Glama.
Which skills help with SEO, AEO and GEO?
Start with suede-seo-audit to audit a page for search visibility, and suede-ai-seo to plan content for AI search and answer engines. The skill catalog lists the rest.
About the creator
Jason Colapietro created and maintains Suede AI Skills. He is an engineer, author, and the founder and CEO of Suede AI, an agentic platform company in West Palm Beach, Florida, and wrote The Claude Code Bible and Codex in Production, operator's guides to the two coding agents this pack runs in. He spent years watching hired marketing firms skip the fundamentals on his own products; this pack turns those misses into reusable, inspectable agent workflows instead of one-off fixes. Suede AI is a member of Claude for Startups, Anthropic's startup program.
Jason Colapietro’s training includes Claude Academy / Anthropic badges in the Claude API, Claude Code, Model Context Protocol (MCP), Claude with Amazon Bedrock and Claude on Google Cloud. His search training includes HubSpot Academy’s AEO Fundamentals and Semrush Academy certificates in AI search, keyword research, on-page SEO, local SEO and digital PR. IBM SkillsBuild covers prompt engineering; Google Skills and Databricks Academy cover generative AI. Seven Microsoft Learn module achievements cover Azure AI Agents, Foundry IQ, Visual Studio Code, Microsoft 365, workflows and Microsoft Agent Framework. View the individual credentials and training-module records.
Follow: X / @johnnysuede · suedeai.ai · suedeai.ai/founder · jasoncolapietro.com · GitHub
License and contributions
The original work is released under the MIT License. Adapted components retain their upstream licenses, listed in NOTICE.md.
Contributions are welcome for docs fixes, install-path corrections, lint rules, template improvements, and public-safe workflow improvements. Do not submit private catalogs, unreleased media, credentials, seed phrases, private Suede API details, payment secrets, or third-party copyrighted files.
Available Tools
12 toolsget_suede_skillGet Suede SkillARead-onlyIdempotent
Return details for one Suede skill, optionally including its full SKILL.md instructions.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Skill name, with or without a leading dollar sign. | |
| includeBody | No | Include the skill's SKILL.md instructions instead of catalog metadata only. |
Output Schema
| Name | Required | Description |
|---|---|---|
| body | No | |
| found | Yes | |
| skill | No | |
| bodyTruncated | No |
list_suede_skillsList Suede SkillsBRead-onlyIdempotent
List Suede skills available through the current MCP profile.
| Name | Required | Description | Default |
|---|---|---|---|
| area | No | Optional area filter (which plugin bundle ships the skill). | |
| specialty | No | Optional specialty filter (how the pack is browsed): ship, craft, found, demand, revenue, position. |
Output Schema
| Name | Required | Description |
|---|---|---|
| skills | Yes |
list_suede_specialtiesList Suede SpecialtiesARead-onlyIdempotent
List the pack's specialities, their sub-lanes, and how many skills each holds. Call this first to pick a specialty, then pass it to list_suede_skills or search_suede_skills.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| specialties | Yes |
plan_suede_workflowPlan Suede WorkflowARead-onlyIdempotent
Turn a goal ("launch my app", "get cited by ChatGPT", "fix a page that gets no signups") into an ordered sequence of Suede skills: strategy first, then build and craft, then visibility, demand and revenue.
| Name | Required | Description | Default |
|---|---|---|---|
| area | No | Optional area filter. | |
| goal | Yes | The outcome to plan for. | |
| maxSteps | No | Maximum steps, up to 8. Defaults to 5. |
Output Schema
| Name | Required | Description |
|---|---|---|
| goal | Yes | |
| steps | Yes |
search_suede_skillsSearch Suede SkillsARead-onlyIdempotent
Rank Suede skills against a task description and return the best-matching routes.
| Name | Required | Description | Default |
|---|---|---|---|
| area | No | Optional area filter. | |
| limit | No | Maximum matches to return, up to 25. | |
| query | Yes | Task, problem, or intent to route. | |
| specialty | No | Optional specialty filter: ship, craft, found, demand, revenue, position. |
Output Schema
| Name | Required | Description |
|---|---|---|
| query | Yes | |
| matches | Yes |
suede_code_gradeSuede Code GradeBRead-onlyIdempotent
Create a Suede A-F code grading scaffold for a diff, PR, branch, MCP server, plugin, API, app surface, public-site change, or release candidate.
| Name | Required | Description | Default |
|---|---|---|---|
| diff | No | Optional pasted diff or change summary. | |
| repo | No | Optional repository or project path. | |
| notes | No | Optional constraints, verification notes, or risk context. | |
| intent | No | Intended behavior or release goal. | |
| target | No | Target repo, PR, branch, diff, file, or change to grade. | |
| context | No | Optional pasted context or review notes. |
Output Schema
| Name | Required | Description |
|---|---|---|
| intent | Yes | |
| target | Yes |
suede_copy_checkSuede Copy CheckARead-onlyIdempotent
Check pasted copy against the pack's copy rules and return an A-F score with each finding: house bans (em dashes, "unlock", "seamless"), hedges, buzzwords, throat-clearing openers, passive voice, long sentences, reading grade, reader focus, and a missing call to action.
| Name | Required | Description | Default |
|---|---|---|---|
| copy | Yes | Copy to check, up to 20000 characters. | |
| houseStyle | No | Apply the Suede AI house bans. Defaults to true; pass false for another brand's copy. | |
| primaryAction | No | Optional action the copy must ask for. |
Output Schema
| Name | Required | Description |
|---|---|---|
| grade | Yes | |
| score | Yes | |
| metrics | Yes | |
| findings | Yes |
suede_copy_seo_auditSuede Copy SEO/AEO/AI EO AuditBRead-onlyIdempotent
Create a Suede-specific SEO/AEO/AI EO copy audit scaffold for a page, repo, or docs surface.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | Optional URL to audit. | |
| copy | No | Optional pasted copy to audit. | |
| pageType | No | Page or docs type when no URL is available. | |
| primaryIntent | No | Primary search intent or reader action. |
Output Schema
| Name | Required | Description |
|---|---|---|
| target | Yes | |
| primaryIntent | Yes |
suede_install_optionsSuede Install OptionsBRead-onlyIdempotent
Return public Codex skill, local plugin, MCP, and skill-copy install options.
| Name | Required | Description | Default |
|---|---|---|---|
| surface | No | Install surface to explain. |
Output Schema
| Name | Required | Description |
|---|---|---|
| plugins | Yes | |
| surface | Yes |
suede_live_page_auditSuede Live Page AuditARead-onlyIdempotent
Fetch a public URL and grade what crawlers and answer engines actually receive: status, HTTPS, noindex, robots.txt for Google and AI answer bots (ChatGPT, Perplexity, Claude), canonical, title, description, H1, readable text, JSON-LD, FAQ, llms.txt, sitemap, calls to action and share previews. Returns an A-F grade per lane, every check, and the top fixes.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public http(s) URL to audit. A bare domain is treated as https. | |
| primaryAction | No | Optional main action the page should drive, checked against its links and buttons. |
Output Schema
| Name | Required | Description |
|---|---|---|
| ok | Yes | |
| page | No | |
| error | No | |
| lanes | No | |
| checks | No | |
| robots | No | |
| status | No | |
| fetchMs | No | |
| overall | No | |
| finalUrl | No | |
| topFixes | No | |
| fetchedAt | No | |
| htmlBytes | No | |
| notChecked | No | |
| requestedUrl | No | |
| htmlTruncated | No |
suede_qa_checklistSuede QA ChecklistCRead-onlyIdempotent
Generate a multi-lane QA checklist for Suede skills, local plugin notes, MCP servers, docs, or public pages.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | QA depth, such as fast, full, release, seo, or mcp. | |
| target | No | Target repo, URL, skill, MCP server, page, or change. |
Output Schema
| Name | Required | Description |
|---|---|---|
| scope | Yes | |
| target | Yes |
suede_visibility_gradeSuede Visibility GradeBRead-onlyIdempotent
Create a Suede A-F visibility and CTA grading scaffold for a public page, docs surface, repo page, launch page, or campaign page.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | Optional URL to grade. | |
| copy | No | Optional pasted page copy. | |
| notes | No | Optional context, screenshot notes, or constraints. | |
| pageType | No | Page or docs type when no URL is available. | |
| primaryAction | No | Main action the page should drive. |
Output Schema
| Name | Required | Description |
|---|---|---|
| target | Yes | |
| primaryAction | Yes |
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
12 tool updates
v0.1.0- First observed
get_suede_skill - First observed
list_suede_skills - First observed
list_suede_specialties - First observed
plan_suede_workflow - First observed
search_suede_skills - First observed
suede_code_grade - First observed
suede_copy_check - First observed
suede_copy_seo_audit - First observed
suede_install_options - First observed
suede_live_page_audit - First observed
suede_qa_checklist - First observed
suede_visibility_grade
TDQS
Scored across 12 tools
Discovery tools (list_skills, list_specialties, search_skills, get_skill) are cleanly separated by intent, and the scaffold vs. live-audit split is mostly clear. The main risk is the cluster of graders — suede_visibility_grade (scaffold), suede_live_page_audit (fetch + grade), suede_copy_seo_audit (scaffold), and suede_copy_check (copy rules) — where an agent could pick the wrong one without reading carefully.
All names are snake_case and carry the 'suede' brand token, but the convention flips: discovery tools put the verb first (list_suede_skills, get_suede_skill), most graders put the noun first (suede_code_grade, suede_copy_check), and plan_suede_workflow returns to verb-first. The suede_ prefix sits in different positions, so the pattern isn't predictable.
Twelve tools is a well-scoped size for a skills pack that needs discovery, retrieval, install guidance, workflow planning, and evaluation scaffolds. It's slightly weighted toward auditing — six of twelve tools are grading/checklist generators — but none appear redundant enough to cut.
The surface covers the full read lifecycle for skills: browse specialties, list, search, fetch details, plus install options and workflow orchestration, backed by concrete evaluation scaffolds. Minor gaps remain — no way to record or export audit results, and no tool to execute a skill's instructions beyond retrieving SKILL.md.
Maintenance
Related MCP Connectors
Hosted MCP server for live public-data APIs and Skills for AI agents.
Read-only MCP server over 50 book-based agent skills: routes a task to the right framework.
Read-only catalog of verified MCP servers and Agent Skills by dev task, with practical verdicts.
Unified 15-tool SEO, SERP, clean Markdown & GEO (LLM citation Share-of-Voice) MCP server.
Related MCP Servers
- AlicenseBqualityCmaintenanceMCP (Model Context Protocol) Server for skill4agent - Search, view, and install AI skills in AI conversations.324 npm4MIT
- AlicenseNot gradedqualityBmaintenanceMCP server that unifies and synchronizes AI coding skills across multiple tools, exposing skill discovery and retrieval via list_skills and read_skill.33 npm14MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that adapts, activates, and shares local Agent Skills for runtimes like OpenAI Agents SDK and Claude Code, enabling dynamic discovery and shareable HTML/image artifacts.41 npm3MIT
- AlicenseNot gradedqualityCmaintenanceA local, read-only MCP server that lets coding agents search the complete AAS skill catalog, compose and validate agent-chosen skill stacks, and generate reproducible, reviewable plans without uploading project code.6,098 npm1MIT