Suede Directory Submissions logo

Suede Directory Submissions

Community
JasonColapietro
suede-directory-submissions

Use when asked "plan our directory submissions" or to select and sequence startup, SaaS, AI, MCP, marketplace or review listings. Suede AI adapts truthful positioning, maintains entity consistency and tracks submission evidence and verified backlinks. NOT FOR: release packaging (use suede-launch-packaging), scaled destination pages (use suede-programmatic-seo), or AI visibility audits (use suede-ai-seo).

Overview

PublisherJasonColapietro
Repositorysuede-creator-skills
Skill namesuede-directory-submissions
Stars
126
Forks
12
Bundled files
7
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 7 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by JasonColapietro on GitHub. Read the source before you install it.

Installation

Install the Suede Directory Submissions AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/JasonColapietro/suede-creator-skills/tree/main/skills/suede-directory-submissions
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/JasonColapietro/suede-creator-skills.git /tmp/suede-creator-skills
mkdir -p .claude/skills
cp -r /tmp/suede-creator-skills/skills/suede-directory-submissions .claude/skills/suede-directory-submissions
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Suede Directory Submissions in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Suede Directory Submissions on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Suede Directory Submissions is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Suede AI Directory Submissions Skills

Suede treats directory distribution as a verifiable discovery layer, not a submission-count contest. Build the user's backlink and buyer-discovery foundation by selecting the right directories, sequencing them around real launch moments, adapting truthful positioning, and checking that each listing and backlink actually landed.

Iron Law, approval is per destination:

No external submission, account creation, paid placement, or review request
happens without explicit approval for that exact destination, copy, assets,
timing, and maximum cost. Approval for research or for another destination
never transfers. Any delta is re-approved before it ships.

Compatibility

An agent with web access for directory research and a local tracker. Each actual submission needs separately authorized destination access; a plan requires no new account or paid placement.

Before Starting

Check for product marketing context first: If .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.


Core Philosophy

Directory submissions can add discovery surfaces, referral paths, and backlinks, but their value varies by product, directory, listing quality, and current platform rules. Treat each benefit as a hypothesis to verify with listing status, referral analytics, search data, and qualified outcomes. A directory plan complements destination pages and other distribution; it does not guarantee authority, citation, traffic, ranking, or leads.

The full directory catalog lives in references/directory-list.md. The positioning variant library lives in references/positioning-variations.md. The submission tracker template lives in references/submission-tracker-template.csv.


Three Operating Rules

Rule 1: Foundation before submission

Before recommending a submission, verify the directory's current official requirements and record the source URL and check date. The linked page should be publicly reachable, truthful, useful to the directory's audience, and measurable. Prepare only the assets the current form requires, using real product screenshots and approved brand files. Add pricing, legal pages, video, schema, or additional formats when the product, jurisdiction, or verified directory rules call for them; do not invent universal prerequisites.

Rule 2: Destination pages before directories

Choose the most relevant verified destination for each audience: a homepage, use-case page, integration page, comparison page, template, or documentation page. It must accurately fulfill the listing promise and have a measurable next step. Do not impose a fixed page count or block a suitable listing merely because an unrelated content type does not exist.

Rule 3: Positioning varies by directory type

Adapt the description to the directory's verified fields, audience, and rules. Reuse approved facts, but change emphasis when that improves relevance; do not claim that duplicate descriptions trigger a search or AI penalty without current evidence. See references/positioning-variations.md for templates.

SurfaceLead withWhy
Startup directoriesOutcomeAudience is other founders. They care what it does.
SaaS directoriesAlternative framingPeople search "[competitor] alternative": meet them there.
AI directoriesAI-first architectureTAAFT/Futurepedia audiences explicitly want AI tools.
Agent/MCP directoriesAgent/MCP angleUse only for a live compatible capability.
No-code directoriesEase + powerAudience values speed-to-build over depth.
Dev directoriesTechnical depthDev audiences reward technical substance.
B2B review sitesROI + use caseBuyers want outcomes and case studies.

Workflow

Step 1: Readiness assessment (Phase 0)

Assess the selected directory against current requirements:

  1. Is the product publicly accessible (no password wall)?
  2. Is there a pricing page (even "free while in beta")?
  3. Are privacy policy + terms live?
  4. Are the required approved logo, screenshot, and video assets available?
  5. Does the destination page match the proposed listing copy and CTA?
  6. Is referral and conversion measurement configured?
  7. Does the current directory policy allow this product, claim set, and category?
  8. For review sites, are there genuine eligible users and a policy-compliant ask?
  9. Who has authority to create the account, accept terms, and submit?

A missing current platform requirement, truthful destination, or submission authority is a hard block for that directory. At the block: stop work on that directory, name the blocker in one line (": missing "), list the resolution options (obtain the requirement, substitute a truthful destination, get explicit submission authority, or drop the directory from the tier), and wait for the user's pick before submitting there. Other gaps are prioritization inputs, not universal launch blockers.

Step 2: Choose the tiers

Full catalog in references/directory-list.md. Summary:

TierWhenIllustrative candidates to verify
Flagship launchAround a relevant launchProduct Hunt, BetaList, HN Show HN, Fazier, DevHunt
Startup/SaaSLaunch and rollingAlternativeTo, SaaSHub, G2, Capterra, F6S
AI directoriesIf the product has a substantiated AI capabilityTAAFT, Futurepedia, Toolify, Future Tools
Agent/MCP registriesIf a live compatible integration existsGlama, APITracker, LF MCP Registry
No-code directoriesIf the product genuinely serves that audienceNoCodeFinder, No Code MBA
Integration marketplacesWhen the integration shipsThe integration owner's official marketplace
Profiles and vertical directoriesWhen audience and category fitRelevant company profiles or industry-specific catalogs

Triage rule: Only submit where the product is a genuine fit under the platform's current eligibility and category rules.

Step 3: Prepare asset variations

For each tier, prep distinct variants from references/positioning-variations.md only after inspecting the destination's current form:

  • Tagline sized to the verified field limit
  • Short description sized to the verified field limit
  • Long description sized to the verified field limit
  • Category tags limited to the verified taxonomy and product fit
  • Logo assets
  • Screenshots + demo video URL
  • Founder story (2–3 sentences)

Keep facts consistent and approved. Adapt length and emphasis to each verified form without inventing features, customers, outcomes, or platform support.

Step 4: Batch submit

Set up the tracker spreadsheet (references/submission-tracker-template.csv). Work in evidence-backed approval batches of 3–5 directories. At the cap, submit, verify, and report that batch's results before opening the next one. Every submission is gated by the Iron Law: show the exact public copy, assets, account, destination, timing, and maximum cost first.

Per submission:

  1. Verify the current form, rules, price, and account identity.
  2. Prepare the exact field values and assets as a reviewable draft.
  3. Obtain explicit approval for that destination (Iron Law).
  4. Fill and upload only the approved values.
  5. Pause before any changed price, upsell, or materially different rendered preview; re-approve the delta.
  6. Submit once, then capture confirmation.
  7. Log: date, URL, status, moderator notes.
  8. Once live, fetch the canonical listing URL, locate the anchor pointing at the destination in the rendered HTML, and record its rel value, redirect behavior, resolved destination, and the check date in the tracker. Absence of rel in response headers does not prove link attributes: inspect the rendered page, and log the method used.

Reporting rule: a listing is reported live only when the tracker's Live URL, Rendered Link Attributes, and Destination Verified cells are all filled with a check date. Anything else is reported as submitted, unverified.


Flagship Launch Listing

For any time-sensitive launch surface, research the platform before building the plan. Use its current official help, submission form, and community rules; record the URLs and check date. Do not present remembered algorithm behavior, ideal launch times, asset dimensions, hunter effects, or engagement thresholds as facts.

Preparation milestones

  • Confirm eligibility, account standing, moderation rules, scheduling options, required assets, and prohibited promotion.
  • Draft truthful positioning, an approved maker story, real product visuals, and a working destination CTA in the exact current form limits.
  • Preview the listing and test the product, signup, analytics, and support path.
  • Build a communication plan from channels the user owns or is authorized to use.
  • Assign a responder for genuine questions and feedback.

Launch and follow-through

  • Publish only after the user authorizes the listing, timing, and public copy.
  • Follow current solicitation and outreach policies. Do not manipulate voting, fabricate engagement, or message people without a legitimate relationship and authorization.
  • Respond helpfully, log referrals and qualified outcomes, and capture lessons.
  • Share a recap only where current community rules permit it.

Reviews Playbook

Review directories can help buyers evaluate products, but eligibility, incentive, moderation, badge, report, and paid-plan rules change. Before recommending a campaign:

  1. Read the current official review and incentive policy for the chosen platform.
  2. Record the source URL, check date, eligibility rules, deadlines, and maximum verified cost.
  3. Identify real users with firsthand product experience; never manufacture, gate, pre-score, or script reviews.
  4. Get explicit authorization for the recipient list, wording, channel, cadence, and any incentive before outreach.
  5. Track requests, completed reviews, moderation status, referral outcomes, and complaints. Set targets from the actual eligible pool and user goals.

Do not claim a badge threshold, report cutoff, ownership relationship, incentive permission, plan price, or expected response rate unless it was verified from a current authoritative source. A small customer base is a planning constraint, not automatic proof that a listing is worthless.


Destination Pages Strategy (What the Backlinks Point At)

Match each listing to the most useful truthful page available. A homepage can be appropriate when it satisfies the audience and promise; a specialized page may be better when evidence supports it.

Page typeBuild it when
Alternatives page (/alternatives/[competitor])Current customer or search evidence shows comparison intent
Use-case / ICP page (/for/[audience], /use-cases/[use-case])Demand and product evidence justify a dedicated page
Template or asset gallery (/templates/[slug])Templates carry standalone value and activation is measurable
Self-authored category roundupThe team can research the category and disclose its methodology
Integration pageThe integration is live and the page explains setup, capabilities, and limits

On any comparison or roundup page: verify material competitor claims, state clearly when each option fits, date the comparison, and correct it when the facts change. Set output volume from quality capacity and measured demand, not a borrowed traffic or revenue story, and do not promise ranking or AI citation.

Page production at scale belongs to suede-programmatic-seo; comparison-page strategy belongs to suede-competitors.


Directories as AEO/GEO inputs

Answer engines recommend brands that the wider web corroborates, and they often cite review sites, marketplaces, and category directories when they build a shortlist. A directory plan is part of the off-site consensus layer in suede-ai-seo. Two rules stay this skill's own:

  1. Entity consistency. Every listing uses the canonical entity sheet from suede-ai-seo (references/entity-graph.md): exact brand name, one-line description, founder names, logo, category, and URL. A listing that disagrees with the site is a finding, and fixing old listings often matters more than adding new ones. Add each verified listing URL to the brand's sameAs set only when the profile is controlled by the brand.
  2. Genuine discussion only. Earn reviews and community mentions; never seed, script, or fabricate them.

Which directories engines cite for your category is observable: when suede-ai-seo runs its prompt panel, the source gap list (domains cited for competitors but not for you) is a prioritized directory and review-site queue. Use it to rank tiers instead of guessing.

Measurement

Record engine, account context, prompt, locale, date, result, and whether the result reproduced. Verify any tracking product and its cost before recommending it.


Community & Ongoing Distribution

Most directory submissions are episodic; community participation is ongoing. Measure each as a separate source before combining funnel conclusions.

Cross-posts and community links are still backlinks: publish only where the community's current rules permit it, use a canonical URL where the platform supports one, and verify the rendered link with the same Step 4.8 check applied to directory listings.

Channel selection, cadence, and post formats belong to suede-community-marketing, suede-social, and suede-content-strategy.


KPIs & Tracking

Set baselines and goals from the user's current analytics, eligible audience, capacity, and launch objective. Do not use generic day-based forecasts.

MetricBaselineUser-approved goalSource and check date
Listings submitted and live
Verified referring links
Directory referral sessions
Qualified conversions by listing
Review requests and published reviews
Listings matching the canonical entity sheet
Directory domains cited in AI answers (prompt panel)
Referring domains (Search Console Links, Bing Webmaster Tools)
Cost and team time

What NOT to Do

  1. Don't buy a mass-submission package without diligence and explicit approval. Verify exact destinations, editorial standards, data handling, rights, maximum cost, and refund terms.
  2. Don't submit to low-quality or deceptive directories. Evaluate audience fit, moderation, live traffic evidence, existing listings, outbound-link behavior, and reputation rather than relying on one authority score.
  3. Don't treat directories as your entire GTM. Compare them with content, community, reviews, partnerships, and other measured channels.
  4. Don't churn listings without evidence. Set a review cadence from product changes, platform notices, and observed listing issues.
  5. Don't over-index on launch-day spike. The flywheel is templates + alternatives + reviews + ongoing content, not one day of PH.

Task-Specific Questions

  1. What are you launching? (Category changes tier mix. AI vs traditional SaaS vs no-code vs dev tool.)
  2. When is launch day? (Work backward from verified platform requirements.)
  3. Do you have destination pages built? (Alternatives, use cases, templates: if not, build first.)
  4. Which flagship surface is being considered, and what do its current rules require?
  5. How many eligible users could receive a policy-compliant review request?
  6. Do you have a live tested MCP or agent capability? (If yes, verify compatible registries.)
  7. Existing integrations? (If yes, verify each owner's marketplace eligibility.)
  8. Which owned audiences can be contacted, and has the user authorized outreach?
  9. Current DR and referring domain count? (Baseline for measuring the compounding effect.)

Output Format

When the user asks for a directory plan, return:

  1. Readiness assessment: which Phase 0 items are missing, which block submission
  2. Tier selection: which tiers apply, which to skip, why
  3. Submission order: evidence-backed batches mapped to current requirements
  4. Destination page list: what to build first if missing
  5. Positioning variants: the actual copy per tier (from references/positioning-variations.md)
  6. Flagship listing timeline: mapped from current rules to calendar dates
  7. Policy-compliant review plan: eligible audience, authorization, copy, cadence
  8. Weekly measurement plan: baselines and user-approved goals
  9. Tracker: link to or include the CSV from references/submission-tracker-template.csv

Keep the plan actionable. Every item should be something the user can do today.


Boundaries

  • Do not claim a directory is dofollow, indexed, high-authority, or producing leads without a current check.
  • Do not submit listings, create accounts, publish copy, buy placements, or request reviews without explicit authorization.
  • Do not fabricate traffic, ranking, review, or citation outcomes; label estimates and record the evidence date.
  • Do not decide positioning or public product claims when the required product context is missing.

Routing

  • Use suede-launch-packaging for the broader launch sequence.
  • Use suede-programmatic-seo for destination pages, suede-seo-audit for technical checks on those pages, and suede-ai-seo for entity facts, the prompt-panel source gap list, and AI citation measurement.
  • Use suede-competitors for comparison-page strategy and suede-content-strategy for editorial support.
  • Use suede-free-tools for interactive destination assets, and suede-community-marketing, suede-social, or suede-content-strategy for community and social distribution.
  • Use suede-public-relations when a flagship launch also warrants earned media.
  • From those skills, route directory selection, listing positioning, and backlink verification back to suede-directory-submissions.

Worked contract

Worked contract gives a bounded input, expected output and failure check for this workflow.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Suede Directory Submissions AI skill do?

Use when asked "plan our directory submissions" or to select and sequence startup, SaaS, AI, MCP, marketplace or review listings. Suede AI adapts truthful positioning, maintains entity consistency and tracks submission evidence and verified backlinks. NOT FOR: release packaging (use suede-launch-packaging), scaled destination pages (use suede-programmatic-seo), or AI visibility audits (use suede-ai-seo).

Why use Suede Directory Submissions on TypingMind?

Because you install it once and use it with any model. Suede Directory Submissions is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Suede Directory Submissions in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/JasonColapietro/suede-creator-skills/tree/main/skills/suede-directory-submissions. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Suede Directory Submissions?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Suede Directory Submissions?

As many as you like. As long as a model supports skills, you can use Suede Directory Submissions with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Suede Directory Submissions AI skill free?

Yes. It is published on GitHub by JasonColapietro under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇