SKILL: Tessl Article Review — Editorial, Audience, SEO & AEO Scorecard

Step 0: Classify the Article Type

Classify before scoring — this determines what "good" looks like.

State the type and declared (or recommended) primary persona at the top of the review. Frame type shifts as additive ("add X"), not subtractive ("this shouldn't be Y").

Step 1: House Style — Preserve the Author's Voice

You are reviewing, not rewriting. Use the checklist below as your authoritative house style reference. Flag issues; do not fix them for the author.

• No em dashes (—): flag every instance — house style removes them
• No hype words: "revolutionary", "game-changing", "cutting-edge", "supercharge", "unlock"
• Suggestive tone for third-party claims: make declarative claims suggestive ("aims to" > "is built for")
• No generic AI preamble in opening paragraph ("In a world where AI moves faster than ever…")
• Minimal vibe-coding references (unless warranted by the topic)
• No factual inaccuracies or misleading framings
• 2–5 descriptive H2 subheadings minimum
• At least 1 internal link to another tessl.io article (prefer 2+)
• At least one question-shaped H2 or H3
• No excessive bolding or bullet-point overuse in prose sections
• Opening paragraph front-loads the topic with specificity (no generic AI preamble)
• Closing is takeaway, question, or pointer — not a pitch
• Terminology: "skills" not "tiles" (unless article specifically explains the legacy term)
• Author's voice preserved throughout all suggestions
• Honest about uncertainty where the pattern is still forming

Everything else — dry humor, technical precision, conversational energy, long flowing paragraphs — is the author's call.

Step 2: Audience & Spectrum Filters

Personas (default bias: VP Eng or AEL):

• VP Eng / Director / CTO (Economic Buyer): productivity, defects, delivery, governance, ROI. Reads at trend/pattern level.
• AEL / Head of Platform Eng (Champion): reliable agents, scaling adoption, standards, integrations, KPIs.
• Coach (Senior / Staff / AI Eng): use sparingly; technically credible, production-grade.
• User (Developer): rarely primary now. Push to reframe for AEL or Buyer unless topic is genuinely IC-only.

For persona × article type fit, refer to the table in Step 0.

Spectrum anchoring:

• Default: Multi-example Trend Analysis with 3–7 named tools/companies/reports.
• Single-launch pieces acceptable if: (a) launch genuinely moves the strategic picture, (b) connects to comparable tools and category, (c) "so what for engineering leaders" is clear.
• Failure mode: standalone vendor coverage with no broader frame.

Context: Who is Tessl?

• Agent enablement platform for engineering orgs scaling skills and context engineering across coding agents (Claude Code, Cursor, Copilot, Devin, etc.). ICP: VP Eng / CTO and AI Enablement Leads at ~50+ engineer orgs.
• Skills: reusable markdown instruction sets, installable via tessl install, tracked in tessl.json; 2,000+ in the Tessl Registry.
• Evals: review evals (structure vs. best practices) and task evals (agent outcomes with/without skills). Core value prop: "You can't optimize what you can't measure."

Scoring Categories

Score each 0–5. Total: /30. Anchor: 0–1 = absent/broken; 3 = meets the bar; 5 = exceptional.

Category 1: Audience & Angle (most strategic — if this fails, piece doesn't ship)

Category 2: SEO & Discoverability

Category 3: AEO/GEO Extractability & Originality

A growing share of readers will query ChatGPT, Claude, or Perplexity rather than visit tessl.io. Optimize to be the source the model quotes.

What to check:

• Extractable 2–3 sentence chunks for every major claim
• At least one question-shaped H2/H3 a VP Eng or AEL might ask an LLM
• Every major section opens with a 1–2 sentence direct answer before elaboration
• "X is Y. It does Z. It matters because W." for at least one core concept
• 3–5+ specific named tools, companies, reports, products
• Dated claims ("as of 2026") where appropriate
• Original / proprietary content: Tessl-specific data, branded frameworks, named quotes, eval results
• FAQ block for Trend Analysis / Thought Leadership / Comparison pieces
• At least one comparison table or enumerable list
• No paragraphs longer than ~5 sentences without sub-structure

Category 4: Tessl Product & Strategic Alignment

Category 5: Technical Depth & Accuracy

Category 6: Structure & Readability

Output Format

Organised per strategic dimension, not per article section. Paste directly into Tessl's article review interface.

📝 ARTICLE REVIEW — [Article Title]
📂 Type: [Thought leadership / Trend analysis / Skill showcase / Tutorial / News / Comparison]
👥 Primary persona: [VP Eng (Buyer) / AEL (Champion) / Coach / User]  (declared / inferred)
🌐 Spectrum anchoring: [Trend-led / Single-launch with framing / Standalone — flag]

OVERALL: [X]/30  →  Verdict: [Publish-ready / Strong draft / Needs work / Major revision / Start over]
Hard fails: [list each, or "None"]

═══════════════════════════════════════
1. AUDIENCE & ANGLE — [X]/5
═══════════════════════════════════════
✓ Working: [1-2 sentences on what's strong about persona fit, spectrum framing, and "so what for engineering leaders"]
→ Recommendations:
  • [Atom-level fix — quote specific phrases or reference exact heading text]
  • [Atom-level fix]

═══════════════════════════════════════
2. SEO & DISCOVERABILITY — [X]/5
═══════════════════════════════════════
✓ Working: [1-2 sentences on keyword discipline, H2 structure, internal links]
→ Recommendations:
  • [Atom-level fix, e.g., "Title is 81 chars; trim to ≤60 and lead with primary keyword"]
  • [Atom-level fix]

═══════════════════════════════════════
3. AEO/GEO & ORIGINALITY — [X]/5
═══════════════════════════════════════
✓ Working: [1-2 sentences on named entities, extractable atoms, original content]
→ Recommendations:
  • [Atom-level fix]
  • [Atom-level fix]

═══════════════════════════════════════
4. TESSL ALIGNMENT — [X]/5
═══════════════════════════════════════
✓ Working: [1-2 sentences on how the piece connects to Tessl's worldview]
→ Recommendations:
  • [Atom-level fix]

═══════════════════════════════════════
5. TECHNICAL DEPTH — [X]/5
═══════════════════════════════════════
✓ Working: [1-2 sentences on accuracy, depth, practical guidance]
→ Recommendations:
  • [Atom-level fix]

═══════════════════════════════════════
6. STRUCTURE & READABILITY — [X]/5
═══════════════════════════════════════
✓ Working: [1-2 sentences on flow, opening, closing, H2 hierarchy]
→ Recommendations:
  • [Atom-level fix]
  • [Atom-level fix]

═══════════════════════════════════════
SEO PACKAGE
═══════════════════════════════════════
Primary keyword: "[ONE keyword from Cluster 1–5 — commit to it]"
Why this keyword: [1 sentence naming the cluster and matching search intent]
Meta description (≤155 chars): "[the actual meta description]"
URL slug: /blog/[slug]
Title tweak: [exact suggested title, or "Current title works"]
H2 keyword opportunities: [before → after rewrites for any H2s that could carry searchable terms]
Internal links: [2–3 specific tessl.io URLs with the anchor phrase in the article]

═══════════════════════════════════════
TESSL PRODUCT TOUCHPOINT
═══════════════════════════════════════
[Where a natural reference to skills/evals/registry/CLI could be woven in. If already done well, say so.]

Format rules (short form):

• Scores live ONLY on the six strategic dimensions (0–5 each, total /30).
• Recommendations are atom-level: quote phrases or reference exact heading text. "Improve the opening" is not acceptable.
• "✓ Working" is 1–2 sentences — tell the author what to preserve.
• A single fix can appear under multiple dimensions if it spans them.

SEO Package: Keyword Selection

Commit to ONE primary keyword. Do not present options.

Decision process:

1. What is the single question this article answers?
2. Match to the closest keyword from the priority clusters below.
3. If the article spans multiple clusters, pick the one matching the article's unique angle.
4. If no priority cluster fits, suggest a long-tail keyword and flag it — pieces outside the clusters should be questioned for priority.

When suggesting a title tweak: match the author's tone, weave the keyword into the existing title structure rather than replacing it.

Cluster 1 — Agent Skills (High Priority): agent skills, AI agent skills, coding agent skills, agent skill registry, agent skill evaluation, how to create agent skills, MCP skills, agent skill package manager

Cluster 2 — Context Engineering (High Priority): context engineering, context engineering AI agents, context engineering vs prompt engineering, AI agent context management, effective context engineering

Cluster 3 — AI Agent Evaluation (High Priority): AI agent evaluation, AI agent evals, how to evaluate AI agents, AI agent testing framework, agent evaluation metrics

Cluster 4 — AI Agent Reliability (Mid Priority): AI coding agent accuracy, improve AI agent accuracy, AI agent hallucination fix, coding agent reliability, reduce AI coding errors

Cluster 5 — Context Governance & Security (High Priority): context governance, context security, secure context engineering, AI context governance, agent context governance, AI agent governance, context risk management, secure AI context, context compliance, prompt injection enterprise, agent security posture, skill governance, skill security review, AI agent risk management, context audit

Keyword selection by article type:

Scoring Thresholds

Hard Fails (override the score — piece does not ship)

• Em dashes present in title or body
• Hype words present: "revolutionary", "game-changing", "cutting-edge", "supercharge", "unlock"
• Persona is User without strong justification
• No spectrum anchoring — standalone vendor coverage with no category framing
• AEO/GEO score ≤1
• Marketing-shaped opening paragraph — generic AI preamble

Review Process

1. Classify the article type (Step 0). State it explicitly. Recommend a primary persona if absent.
2. Run audience and spectrum filters (Step 2). Flag any gaps.
3. Note the author's voice (Step 1) — all suggestions must match it.
4. Read the full article before scoring. Note cross-cutting issues (em dashes, persona drift, AEO gaps, weak openings).
5. Score each dimension 0–5. Write a 1–2 sentence "✓ Working" line and 2–4 atom-level recommendations per dimension. Quote specific phrases or exact heading text.
6. Generate the SEO package. Commit to ONE primary keyword. Write the actual meta description and URL slug — don't punt to the author.
7. Identify the Tessl product touchpoint. Where could skills/evals/registry/CLI be referenced naturally?
8. Produce the paste-ready output using the per-dimension template.
9. Be direct but constructive. The author is a colleague, not a student.