semantic-draft-writer

semantic-draft-writer is a skill for Claude Code from siddiqss/semantic-seo-suite. It costs 105 tokens per session (1,347 once invoked), scanned A, original, MIT.

A writing skill that turns a semantic-SEO brief into a complete article draft. It checks the draft against the brand's approved facts and repairs or reports unsupported claims.

In plain words
What is it for?
Use it to write articles from briefs, create content for topic-map nodes, validate factual claims, and identify details needed before publication.
Why use it?
It reduces the risk of publishing invented details while still requiring the writer to add concrete examples and useful depth. If the supplied facts are too limited, it surfaces the missing information instead of filling gaps with vague text.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is python ../../scripts/validate_draft.py --draft <draft.md> \.

Part of the semantic-seo-suite plugin — 10 skills shipped together

Good fit Use it to write articles from briefs, create content for topic-map nodes, validate factual claims, and identify details needed before publication.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/siddiqss/semantic-seo-suite
agentmods
npx agentmods add skills/siddiqss/semantic-seo-suite/semantic-draft-writer

Made for: Claude Code.

Or install semantic-seo-suite, the plugin that ships this one along with the rest of its 10 skills.

Wrote 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.

agentmods badge for semantic-draft-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/siddiqss/semantic-seo-suite/semantic-draft-writer/github.svg)](https://agentmods.dev/skills/siddiqss/semantic-seo-suite/semantic-draft-writer)
Your own site
<a href="https://agentmods.dev/skills/siddiqss/semantic-seo-suite/semantic-draft-writer"><img src="https://agentmods.dev/badge/skills/siddiqss/semantic-seo-suite/semantic-draft-writer/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.

agentmods 80×15 button for semantic-draft-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/siddiqss/semantic-seo-suite/semantic-draft-writer"><img src="https://agentmods.dev/badge/skills/siddiqss/semantic-seo-suite/semantic-draft-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,347 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00105 $0.01347
Opus 5 $0.00053 $0.00674
Sonnet 5 $0.00021 $0.00269
Haiku 4.5 $0.00011 $0.00135

Measured 10d ago against content hash 0419f66bb4a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

semantic-draft-writer 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 10d 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.

skills/semantic-draft-writer/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

semantic-draft-writer

Turn a brief into publishable copy that is deep, specific, extractive, and — the part other tools skip — factually honest. "Passes the validator" is the floor, not the goal: the goal is a piece genuinely worth reading. The draft is done when it is fabrication-clean AND clears the quality bar (or its remaining gaps are explicitly surfaced).

Read first: ../../framework/semantic-writing-rules.md (especially the Craft & depth rules 22–28), ../../framework/macro-micro-semantics.md. Load the brief, the node, brands/<slug>/locked-facts.json, and entity-profile.json (for voice/audience).

Workflow

  1. Scope depth and surface fact gaps FIRST. Before writing, list the concrete specifics a strong piece needs — real examples, named entities, figures, a point of view — and check them against locked-facts.json + the brief. If the piece can only be written generically because the facts aren't there, that is a signal to ask the user for the missing specifics (real customer result, actual feature names, a workflow detail) rather than writing vague filler. Thin facts are the #1 cause of thin drafts.

  2. Front-matter first. Emit the required block (semantic-writing-rules.md): node_id, target_query, intent, entities_covered, internal_links, schema_type, locked_facts_used (start empty), sources (start empty).

  3. Draft for a reader, section by section along the brief's contextual vector. Lead a section with the extractive answer (rules 3–4) THEN go deep: mechanism, a concrete example (rule 23), a trade-off, a real point of view (rule 26). Do not turn every H2 into a tiny Q&A (rule 27) — vary the shape. Declarative, specific, filler-free.

  4. Honour the locks while writing:

    • State a brand fact ONLY if it exists in locked-facts.json; when you use one, add its key to locked_facts_used.
    • State an external factual number ONLY with a citation; add the URL to sources.
    • Where a figure would help but isn't grounded, write the honest version (mechanism/ range/"depends on…") — never invent one. Pull from the brief's do_not_fabricate.

Read the full file on GitHub · 92 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 92 lines · 105 tokens per session scan A 0419f66bb4a0

Subscribe to this mod's changes

semantic-draft-writer is a skill published in the GitHub repository siddiqss/semantic-seo-suite (9 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 1,347 once invoked, about $0.0005 per session on Opus 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 2026-08-31.