teachskillofskills-ai/digitalmarketingpro-techshu/check
Claude Code and agent skill by teachskillofskills-ai/digitalmarketingpro-techshu
- community
Checking that the SKILL.md file is still in the repository.
Run the unified pre-publish quality gate on marketing content — wraps scripts/eval-runner.py to score hallucination risk, claim substantiation (with --evidence), brand-voice fit (with --brand), structure (with --schema), content quality, and readability, plus a C2PA provenance check for AI assets in EU-targeted campaigns; returns a composite score with a PASS / WARN / BLOCKED decision and per-issue fix suggestions. Reports only — it never edits the content. Triggers on \"/digital-marketing-pro:check\", \"is this safe to publish\", \"run a hallucination check on this draft\", \"validate this copy against the brand voice\", \"pre-publish quality gate\". Resolves the active brand profile automatically; pairs with /digital-marketing-pro:c2pa-metadata to fix missing manifests.
Install
npx vskill@latest install teachskillofskills-ai/digitalmarketingpro-techshu/checkSKILL.md
The same SKILL.md was published earlier as indranilbanerjee/digital-marketing-pro/check.
/digital-marketing-pro:check — Unified Pre-Publish Quality Gate
This skill is the canonical pre-publish gate for marketing content. It wraps the evaluation suite (scripts/eval-runner.py) and produces a single pass/fail decision with actionable issues.
Context efficiency
Heavy skill. Grep before Read any referenced file, then Read only matched ranges with offset + limit. List the brand's workspace at ~/.claude-marketing/brands/{slug}/ (or $CLAUDE_PLUGIN_DATA/digital-marketing-pro/brands/{slug}/ when that env var is set) before opening files. On re-invocation mid-session, skip files already in context.
Use this skill before publishing any marketing content — blog posts, ad copy, emails, social posts, landing pages, press releases, or any branded copy.
Why this skill exists
An earlier version shipped a global PreToolUse hook that auto-ran a hallucination + brand-compliance check on every Write/Edit operation in every project. That hook was removed because it fired globally across all plugins and projects (Slack writes, GitHub PRs, code edits — all of it), causing friction in non-marketing work.
/digital-marketing-pro:check replaces that automatic gate with an explicit user-invoked gate. The work is the same; the trigger is intentional.
What the check evaluates
The check delegates to scripts/eval-runner.py (the master eval orchestrator) which calls four sibling scripts:
| Dimension | Script | What it checks | |
|---|---|---|---|
| Hallucination | hallucination-detector.py | Unattributed statistics, placeholder URLs (example.com / your-site.com), unsupported superlatives ("best", "#1", "leading"), fabricated citations | |
| Claims | claim-verifier.py (when --evidence provided) | Cross-checks specific claims against a user-provided evidence file | |
| Brand voice | brand-voice-scorer.py (when --brand provided) | Scores content against the active brand's voice profile (formality, energy, humor, authority, prefer/avoid words) | |
| Structure | output-validator.py (when --schema provided) | Validates content matches expected schema (blog_post, email, ad_copy, social_post, landing_page, press_release, content_brief, campaign_plan) | |
| C2PA provenance (compliance) | embed-c2pa.py (presence check) | When the brand's target_markets include an EU/EEA jurisdiction AND an accompanying asset is AI-generated: verifies a C2PA provenance manifest is present and valid. Missing or invalid manifest → CRITICAL / BLOCKED (EU AI Act Article 50, applies from 2 Aug 2026) |
Plus content quality and readability scoring (always run).
Subcommands and modes
Default (run-quick)
Runs the quick eval: hallucination detection + content quality + readability. Fast (~2 seconds), zero external dependencies. Use this for routine checks.
Full eval (run-full)
Runs all 6 dimensions: hallucination + claims (if evidence provided) + brand voice (if brand provided) + structure (if schema provided) + content quality + readability. Use before publishing anything client-facing or external.
Compliance-focused (run-compliance)
Runs hallucination + claims + brand voice + structure. Best for regulated industries (healthcare, financial services, alcohol, cannabis, gambling) where claim substantiation and brand-voice fidelity matter most.
With evidence file
When the content makes specific claims you want to substantiate, provide a JSON evidence file:
The check will extract every claim from the content and flag any that don't match an evidence entry.
With schema validation
Validates the content matches the structural requirements of the named schema. Available schemas: blog_post, email, ad_copy, social_post, landing_page, press_release, content_brief, campaign_plan. Use --schema list to see all schemas with their requirements.
With brand voice check
Scores the content against the brand voice profile at ~/.claude-marketing/brands/acme/profile.json. Reports per-dimension breakdown (formality, energy, humor, authority) plus deviation from prefer/avoid word lists.
Output format
The check returns a unified report:
If any CRITICAL issue is found, decision = BLOCKED and the user is asked to fix before publishing.
AI-tell scans (advisory section, never scored)
Alongside the eval-runner scorers, run both tell scans and report them as a single ADVISORY section of the check output:
- Tier 1 (surface) — LLM-favored vocabulary, significance markers, soft-adverb clusters, connective and participial openers, em-dash density, ungrounded one-liners. Report the overall LOW/MODERATE/HIGH rating and the flagged sentences with their suggested fix. Significance markers are reported with
"fix": "Delete this sentence; do not reword it."— pass that through verbatim, because rewording is the wrong remedy. - Tier 2 (structure) — the overall OK/NOTE/ATTENTION band plus each NOTE/ATTENTION finding with its spans (moralizing, section symmetry, parallel headings, specificity, stance, paragraph evenness, entity development). For
entity_development, always carry through that the fix is to develop an existing specific, never to delete specifics.
This whole section NEVER affects the PASS/WARN/BLOCKED decision. Both scripts keep their thresholds inside themselves, deliberately outside the eval config, because these are editorial judgment calls for a human editor, not publish gates — and because a detector proxy has a real false-positive rate on genuinely human writing. (The one place a tell scan does gate is the content-engine's humanize_passed, and only on the two tells precise enough to gate on: significance_marker and soft_adverb_cluster. llm_favored_word was dropped from that set on 2026-08-15 after it was measured firing only on prose published before ChatGPT existed and never on model prose. That gate is a density floor — measured, it fails no published human writing and catches no unedited model prose — so never report a pass as evidence that a piece reads human.) Both scans measure visible text only; neither can see, and neither has any relationship to, any statistical watermark.
EU AI Act Article 50 — C2PA provenance gate
The check gains a compliance dimension for AI-generated assets in EU-targeted campaigns. It fires when both conditions hold:
- The active (or
--brand) profile'starget_marketsinclude any EU/EEA jurisdiction, and - An accompanying asset is declared AI-generated — either the file metadata says so, or the
--evidenceJSON declaresai_generated: truefor it.
When both hold, the gate runs a C2PA manifest presence check on the asset via embed-c2pa.py (presence/verify mode — it does not modify the asset). A missing or invalid C2PA provenance manifest is a CRITICAL issue → decision = BLOCKED. Article 50 applies from 2 Aug 2026 (penalty up to EUR 15M or 3% of global turnover). To embed a compliant manifest, run /digital-marketing-pro:c2pa-metadata.
If embed-c2pa.py is not present in the script inventory or the asset cannot be resolved, surface the dimension as SKIPPED with a warning (never silently PASS an EU AI-asset check).
How the skill operates
The skill follows this flow:
- Resolve the input. If the user passed a file path, read it. If they passed inline content, use it.
- Resolve options. If
--brandnot specified, attempt to load from active brand at~/.claude-marketing/brands/_active-brand.json. If--schemanot specified, infer from content type if obvious (blog markdown →blog_post, etc.) or skip structure check. - Build the eval-runner command. Choose action:
run-quick(default),run-full(with--full),run-compliance(with--compliance). - Execute via Bash.
`` python "${CLAUDE_PLUGIN_ROOT}/scripts/eval-runner.py" --action run-quick --file <input> [--brand <slug>] [--evidence <path>] [--schema <name>] ``
- Parse the JSON output. Extract composite score, grade, dimension scores, alerts, auto-reject decision.
- Format for the user. Present the human-readable report shown above. Lead with the decision (PASS / WARN / BLOCKED).
- If BLOCKED, refuse to recommend publishing. Always require the user to address CRITICAL issues before they proceed.
Scripts called
scripts/eval-runner.py— master orchestratorscripts/hallucination-detector.py— invoked by eval-runnerscripts/claim-verifier.py— invoked by eval-runner if--evidenceprovidedscripts/brand-voice-scorer.py— invoked by eval-runner if--brandprovidedscripts/output-validator.py— invoked by eval-runner if--schemaprovidedscripts/content-scorer.py— invoked by eval-runnerscripts/readability-analyzer.py— invoked by eval-runnerscripts/embed-c2pa.py— presence/verify check for the EU AI Act Article 50 C2PA gate (only when an EU-targeted brand has an AI-generated asset)
All scripts use stdlib only (except brand-voice-scorer which optionally uses nltk). No external API calls, no internet required.
Examples
Example 1: Quick check on a draft
Example 2: Full eval with brand + evidence + schema
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/check/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/teachskillofskills-ai/digitalmarketingpro-techshu/check)