seo-directory-backlinks – Marketing & SEO skill for AI agents
Directory and backlink register: platform, domain, target URL, follow attribute, authority and spam scores, approval and NAP-match status. Use for SEO citation tracking.
Install the seo-directory-backlinks skill with one command
Pick the tool you use, copy the command and paste it in your terminal. The skill lands in that tool's skills folder and is ready in your next session.
Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://skill.dn1nguoi.com/z/seo-directory-backlinks-74887.tgz | tar xz -C ~/.claude/skills
Call it in Claude Code: /seo-directory-backlinks – then describe the task you want done.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/seo-directory-backlinks-74887.tgz | tar xz -C ~/.codex/skills
Call it in Codex: $seo-directory-backlinks – then describe the task you want done.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/seo-directory-backlinks-74887.tgz | tar xz -C ~/.hermes/skills
Call it in Hermes Agent: /seo-directory-backlinks – then describe the task you want done.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/seo-directory-backlinks-74887.tgz | tar xz -C ~/.deepcode/skills
Call it in DeepSeek: /seo-directory-backlinks – then describe the task you want done.
SKILL.md content
Supporting material availability
This catalog copy contains the inline guidance below, but does not include the following supporting paths. They are external prerequisites, not bundled files:
../../references/backlink-directory-master-list.md
Obtain the required material from the [declared upstream source](https://github.com/WHOISABHISHEKADHIKARI/sme-ops-system-builder), or from a user-provided installation of that source. Resolve each path relative to that installation, inspect its contents, and verify any applicable license and execution prerequisites. Do not run a command or claim a referenced procedure was followed until its required file exists. Do not fabricate the missing scripts or treat an unrelated file with the same name as equivalent. Independent steps fully documented here can proceed within the user’s authorized scope; report any dependent step as unavailable.
SEO Directories & Backlinks
What it is: the off-site citation and link plan - which directory or platform the
business belongs on, whether the listing is real and consistent, what the link is worth,
and which submissions to refuse.
Overview
Works out the smallest useful citation plan for the business in front of it, then builds
it only when asked. The default output is a short recommendation, not a submission list.
The citation tracker - CSV, SQL DDL, JSON Schema, Notion mapping - is produced on request,
from one field list so the four cannot drift apart.
Layer: Layer 3: Acquire. Fits: Growth stage. Table code: n/a.
The rule this table exists to enforce: a directory is a *citation*, and a citation is
only correct if it matches. NAP Match is therefore a control field with three values,
not a note, and a citation whose NAP does not match is a defect to fix rather than a
backlink to keep. Alongside it, Approval Days and Link Type are recorded because a
listing that was never approved and a nofollow link are two different facts, and a tracker
that cannot distinguish them reports success it did not get.
The second rule: the highest-value links are almost never directories. Chamber of
commerce, council directory, trade association, an industry blog and one genuine local
press mention beat two hundred generic submissions. Tier exists so the plan spends its
effort at the top.
When to Use This Skill
- where to list my business, business directories, citations
- backlinks, link building, off-page SEO
- NAP consistency, citation building, local citations
- "why is a competitor ranking and we are not"
- Industry and vertical directories for a specific sector
- refusing or auditing a list of "free high DA" submissions
- link profile, referring domains, anchor text, lost links
Do not use it for: the website's own structure (business-website-setup), the map profile
(gbp-local-seo-intent), paid advertising, or content marketing and guest posting, which
are editorial decisions rather than directory submissions.
How It Works
Follow the shared execution contract. The module-specific rules below define only domain fields, decisions, calculations, and safety constraints.
Step 1 - Identify intent
Read the request and pick the intent before asking anything.
- "where should we list" / "set up" / "build" -> artifacts wanted; go to Step 2.
- "review this list someone sent us" -> an audit of a supplied list; go to Step 2 and then
the vetting step.
- "our rankings dropped" / "fix" -> something was done; capture what, then Step 2.
- "audit" / "check" -> a check, not a build.
Ask only if this is the highest-value missing fact; otherwise proceed without an opener:
> Q: What is the business called, and what does one line of it actually do?
Step 2 - Ask only what is missing
Treat ambiguous replies as unanswered and ask which explicit option the user means. Record unknown values as Unknown; Unknown is not zero. A record must not be Done when a required check fails.
Skip anything already answered. Ask the rest one at a time, and stop as soon as the
remaining answers would not change the directory list.
- Business - Industry and sector, in the words a customer would use? / One location or
several? / Customers visit, or is it service-area?
- Current - Is the business already listed anywhere? / How many listings roughly? / Who
created them, and is there an account the business still controls?
- Goal - What is the aim - more calls, more enquiries, more site traffic, or visibility
in one specific market? / Is there a market or a country in scope?
- Capacity - How much time is there to spend on this per month? / Is anyone paid to do
it, or is it the founder on a Sunday?
- Risk - Has anyone offered paid placement, a "dofollow network" or a reciprocal-link
deal? / Has the site ever received a manual action or an algorithmic drop?
Never invent an answer. Domains, DR or DA scores, spam scores, approval times, listing
URLs, referring domain counts and rankings the user has not supplied or measured are
Unknown. A DA score is a third-party estimate, and it is never invented here.
Step 3 - Hold the internal context
module: seo-directory-backlinks
intent: null # set up | fix | review | report | import
scale: null # Starter | Growth | Scale, only if the answer changes it
areas:
"Business": null
"Current": null
"Goal": null
"Capacity": null
"Risk": null
requested_outputs: []
confirmed_facts: []
open_questions: []Step 4 - Recommend the smallest workflow
Build an already requested artifact without asking again. For advice-only requests, give a short recommendation and offer the relevant artifact.
Recommended approach: Fifteen to twenty real listings, not two hundred. Tier 0 the two
map platforms the business is eligible for, Tier 1 the high-authority review platforms and
the professional profile that fit the sector, then the genuinely local sources - chamber of
commerce, council directory, trade association, one industry blog, and one local press
angle. Everything submitted in one sitting, from one canonical NAP block, and re-checked
quarterly. Two or three vertical directories, no link networks.
Why this one: Fifteen real listings are a citation set Google can read and customers can
use. Two hundred junk listings are a footprint across domains Google has publicly actioned,
and a small local business cannot afford that risk for a marginal gain. The genuinely local
links are also the ones competitors skip, so the effort goes further there than on a
national directory.
Workflow: Canonical NAP block written once → Tier 0 platforms claimed → Tier 1 review
and professional profiles completed → Local chamber, council and trade association joined
→ Two or three vertical directories chosen by relevance → Tracking row created for each
with a review date → Quarterly re-check scheduled → Referring domains and anchor text
reviewed once a quarter → Anything with a mismatched NAP corrected or removed
Step 5 - Build only on request
Once the user asks for it, derive the fields from the confirmed context and emit the
requested artifacts. For machine-readable text, keep prose outside the data; for files,
provide a usable link. Report material validation failures or limitations separately.
**A selected Notion output is rendered by notion-manual-import, so route the
Notion step there.** When the user selects Notion, hand that step to
@notion-manual-import: it holds the CSV, the property
mapping, the import steps and the verification checklist, and it renders the Field
Reference below instead of defining a table of its own. Do not restate the mapping
here and do not improvise the import steps. Manual CSV and mapping outputs need no
connection. For requested workspace changes, follow the shared contract: verify actual
tool access and the target before writing. A user saying "connected" is not tool evidence.
Never ask for a Notion password or token.
Citation ID,Platform Name,Domain,Tier,Category,Directory Type,Target URL,Link Type,Follow Attribute,Domain Authority,Domain Rating,Spam Score,Listing Status,Submitted Date,Approved Date,Approval Days,NAP Match,Referral Traffic,Review Date,Owner,Status,Notes
,Example Chamber of Commerce,examplechamber.org,Tier 1,Local chamber of commerce,Member directory,https://example.com/,Nofollow,Nofollow,Unknown,Unknown,Unknown,Approved,2026-09-27,2026-10-02,5,Match,Unknown,2026-12-27,Unknown,Planned,Example row - replace every value before use.-- Engine assumption: PostgreSQL. For another engine use the engine's auto-increment
-- equivalent and keep the rest portable.
CREATE TABLE seo_citation (
citation_id BIGINT GENERATED BY DEFAULT AS IDENTITY PRIMARY KEY,
platform_name VARCHAR(255) NOT NULL,
domain VARCHAR(255),
tier VARCHAR(50) NOT NULL,
category VARCHAR(100) NOT NULL,
directory_type VARCHAR(100) NOT NULL,
target_url TEXT,
link_type VARCHAR(50) NOT NULL,
follo… (full content is in the download package)
Related skills
- seo-drift – Snapshot a site's SEO state and detect ranking, indexation, metadata, canonical, robots…
- seo-forensic-incident-response – Investigate sudden drops in organic traffic or rankings and run a structured forensic…
- seo-fundamentals – Core principles of SEO including E-E-A-T, Core Web Vitals, technical foundations…
- seo-geo – Optimize content for AI Overviews, ChatGPT, Perplexity, and other AI search systems. Use…
- seo-health-score-calculator – SEO Health Score Calculator. Use when working with audit findings and a disclosed…
- seo-hreflang – Hreflang and international SEO audit, validation, and generation. Detects common…
- seo-image-gen – Generate SEO-focused images such as OG cards, hero images, schema assets, product…
- seo-images – Image optimization analysis for SEO and performance. Checks alt text, file sizes…