CtrlK
BlogDocsLog inGet started
Tessl Logo

bapfernandez/article-reviewer

Editorial reviewer for tessl.io blog articles — scores drafts across SEO, alignment, technical depth, structure, and originality, then generates actionable feedback.

90

Quality

90%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files
name:
tessl-article-reviewer
description:
Reviews and structures blog articles for the Tessl blog (tessl.io/blog). Scores drafts across five categories (SEO, Tessl alignment, technical depth, structure, originality), enforces house style rules (em dashes, suggestive tone for third-party claims, heading hierarchy, internal links), generates a committed SEO package (primary keyword, meta description, URL slug), and produces a copy-pasteable Google Docs review comment. Use when someone asks to review, edit, improve, structure, score, or give feedback on a Tessl blog article or draft.

SKILL: Tessl Article Review — Editorial & SEO Scorecard

Step 0: Classify the Article Type

Classify the article into one of these types before scoring — this determines what "good" looks like.

TypeWhat it isExamples
Thought leadershipOriginal frameworks, industry analysis, opinion pieces."The Context Delivery Lifecycle", "Why Skills Are the Next Unit of Software"
Skill showcaseHighlights specific skills from the registry with eval data, install commands, and use cases."8 Agent Skills for Code Reviews", "Security Skills with Cisco CodeGuard"
Tutorial / How-toStep-by-step guide to accomplish a specific task."Automate Publishing with GitHub Actions", "Getting Started with Tessl CLI"
News / AnalysisCoverage of a tool launch, industry event, or trend with editorial angle."Amp Adds Code Review to Its Agent Toolkit", "What Context-Bench Tells Us"
ComparisonSide-by-side evaluation of tools, approaches, or frameworks."Tessl vs LangChain", "SDD vs Vibe Coding"

State the type clearly at the top of your review.

When the type doesn't match the format

When an article is stuck between two types, give the author a concrete additive path — never subtractive:

  • "Reads like docs but it's on the blog" → "Add a 2-sentence problem statement before the first H2 explaining why someone would need this. Add a brief 'what you'll learn' at the top. Add a closing paragraph connecting this to the bigger picture."
  • "Thought piece that wants to be a showcase" → "Pick one concrete skill from the registry and walk through it as a worked example in section 3. That grounds the theory without changing the article's voice."
  • "News coverage that could be analysis" → "Add 3 paragraphs of 'so what does this mean for teams using coding agents?' and this becomes a much stronger piece."

Always frame shifts as additive ("add X"), not subtractive ("this shouldn't be Y").


Step 1: Preserve the Author's Voice

You are reviewing, not rewriting. The author's voice, style, and personality must be preserved.

Flag only these house style issues:

  • Em dashes (---): flag every instance (house style: remove them)
  • Declarative claims about third-party tools: make suggestive ("aims to" > "is built for")
  • Vibe-coding references that aren't warranted by the topic
  • Factual inaccuracies or misleading framings

Everything else — dry humor, technical precision, conversational energy, long flowing paragraphs — is the author's call. Do NOT suggest the article should sound like someone else or impose a uniform corporate tone. Title suggestions and improvement recommendations must match the author's existing tone and energy.


Context: Who is Tessl?

Tessl is an agent enablement platform that helps developers make coding agents (Claude Code, Cursor, Copilot, Devin, etc.) more effective in their codebases. It provides a package manager for reusable, evaluated instruction sets that guide coding agents, covering the full lifecycle: generate, evaluate, distribute, optimize.

Key concepts:

  • Skills: Reusable markdown-based instruction sets for coding agents. Installable and versioned like packages.
  • Evals: Systematic evaluation via review evals (structure against best practices) and task evals (running agents with/without skills, measuring outcomes).
  • Tessl Registry: 2,000+ evaluated skills, discoverable via tessl skill search / tessl i.
  • tessl.json: Manifest file tracking installed skills, analogous to package.json.
  • Context engineering: Providing the right information to LLMs at the right time. Tessl operationalizes this.
  • Spec-driven development (SDD): Development guided by specifications that agents follow — a term Tessl is pioneering.

Positioning: Agent enablement differentiates Tessl from LangChain, CrewAI, AutoGen, etc. Skills are "the next unit of software." Core value prop: "You can't optimize what you can't measure." Multi-agent, agent-agnostic.

Target audience: Professional developers and engineering leaders actively using AI coding agents. They care about reliability, workflow integration, and measurable outcomes — not hype.


Scoring Categories

Score each category 0–5. Total possible: 25.

Category 1: SEO & Discoverability

ScoreMeaning
0–1No SEO consideration; no target keyword, poor title, no structure.
2Target keyword exists but buried; title generic; missing H2s or internal links.
3Clear keyword in title and H1; has H2s; at least 1 internal link. Basic structure sound.
4Strong keyword targeting; keyword-rich scannable H2s; multiple internal links; would rank for a specific query.
5Exceptional. Targets a high-priority cluster; title is click-worthy AND keyword-optimized; H2s map to search intent; could anchor a pillar page.

Category 2: Tessl Product & Strategic Alignment

ScoreMeaning
0–1No connection to Tessl's domain; could be published anywhere.
2Related to AI coding/agents but misses opportunities to connect to Tessl's narrative.
3Clearly within Tessl's content territory; references relevant concepts at least once.
4Naturally weaves in Tessl's worldview; frames problems through agent enablement; reader understands why this matters without feeling sold to.
5Advances Tessl's category; defines or sharpens terminology Tessl is pioneering; would be cited by others.

Category 3: Technical Depth & Accuracy

ScoreMeaning
0–1Factually wrong, entirely surface-level, or marketing fluff dressed as a technical article.
2Correct but shallow; reads like a rewritten press release; lacks original insight.
3Solid technical grounding; accurate claims; at least one concrete example, code snippet, or data point.
4Genuinely useful; practical guidance, real-world examples, or original analysis; a developer would bookmark it.
5Exceptional depth; original research, benchmarks, or first-hand experimentation; teaches something new to experienced developers.

Category 4: Structure, Readability & Engagement

ScoreMeaning
0–1Wall of text or brain dump; no headings, no flow.
2Reasonable structure but generic; weak opener; no hook; reader might bounce.
3Clear logical flow; good H2 structure; opening sets up the problem; conclusion has a takeaway or CTA.
4Engaging from the first line; each section earns the next; good use of examples, analogies, or data.
5Exceptional narrative craft; clear "so what" threads through every section; shareable and quotable.

Category 5: Originality & Differentiation

ScoreMeaning
0–1Straight copy or common knowledge restated; could be any blog.
2Has a unique angle buried somewhere but doesn't lead with it.
3Clear differentiator: unique take, original data, or a Tessl-specific lens.
4Strong original contribution; introduces a framework, coins a useful term, or provides analysis that advances thinking.
5Category-defining; shapes how the industry thinks about this topic; would be cited by other publications.

Output Format

Produce a Google Docs comment using this exact template. Keep it under 300 words.

📝 ARTICLE REVIEW — [Article Title]
📂 Type: [Thought leadership / Skill showcase / Tutorial / News / Comparison]

Overall: [X]/25

1. SEO & Discoverability: [X]/5
2. Tessl Alignment: [X]/5
3. Technical Depth: [X]/5
4. Structure & Readability: [X]/5
5. Originality: [X]/5

🟢 What's working:
[2-3 sentences on what's strong about this draft.]

🟡 Key improvements:
→ [Specific, actionable improvement #1]
→ [Specific, actionable improvement #2]
→ [Specific, actionable improvement #3]
(Up to 5 max. Be concrete: "Change the H2 from X to Y", not "improve headings".)

🔴 Must-fix before publish:
→ [Critical issue, if any]
(Only include if there are genuine blockers. Leave blank if none.)

📂 Type note (if applicable):
[If the format doesn't match the type, explain what to ADD to strengthen it. Skip if type fits well.]

🔎 SEO package:
Primary keyword: "[ONE keyword — commit to it, don't hedge]"
Why this keyword: [1 sentence]
Suggested meta description (≤155 chars): "[Write the actual meta description]"
Suggested URL slug: /blog/[slug]
Title tweak (if needed): "[Suggest a title matching the author's tone but improving keyword targeting. If the current title works, say 'Current title works.' Do NOT suggest generic SEO-template titles.]"
H2 keyword opportunities: [Specific before → after rewrites for any H2s that could include searchable terms.]
Internal links: [Suggest 2-3 specific tessl.io URLs with which phrase in the article should become the anchor text.]

🔗 Tessl product touchpoint:
[Suggest where a natural reference to skills/evals/registry/CLI could be woven in. If the article already does this well, say so.]

SEO Package: How to Choose the Primary Keyword

Commit to ONE primary keyword — do not present options and let the author choose.

Decision process:

  1. What is the single question this article answers?
  2. Match that question to the closest keyword from the priority clusters below.
  3. If the article spans multiple clusters, pick the one with the strongest match to the article's unique angle, not just its topic.
  4. If no priority cluster fits, suggest a long-tail keyword matching the article's specific content.

When suggesting a title tweak: Read the author's current title and note its tone (playful, technical, provocative, straightforward). Your suggestion must match that same energy. Weave the primary keyword into the existing title structure — don't replace it. If the current title already works, say so.


Scoring Thresholds & Recommendations

Total ScoreVerdictRecommendation
21–25Publish-readyMinor polish only. Ship it.
16–20Strong draftAddress key improvements, then publish. 1 round of edits.
11–15Needs workStructural or strategic gaps. Requires rewriting weak sections.
6–10Major revisionFundamental issues with angle, depth, or alignment. Needs rethinking.
0–5Start overDoesn't serve our audience or strategy. Rebrief the topic.

Review Process

  1. Classify the article type (Step 0). State it explicitly.
  2. Note the author's voice — tone, style, personality. All suggestions must match it.
  3. Score each of the 5 categories with 1–2 sentences of justification.
  4. Generate the SEO package. Commit to ONE primary keyword. Write the actual meta description and URL slug — don't punt this to the author.
  5. Produce the Google Docs comment using the template above.
  6. Be direct but constructive. The author is a colleague, not a student.

Reference: Tessl SEO Priority Keywords

ClusterKeywords
Context engineering"what is context engineering", "context engineering AI agents", "context engineering vs prompt engineering", "context engineering best practices"
Spec-driven development"spec driven development", "SDD vs vibe coding", "how to write specs for AI agents"
Agent evals"AI agent evaluation", "how to evaluate AI agents", "AI agent testing framework", "agent evaluation metrics"
Agent accuracy & reliability"AI coding agent accuracy", "improve AI agent accuracy", "AI agent hallucination fix", "coding agent reliability", "reduce AI coding errors"
Framework comparisons"Tessl vs LangChain", "Tessl vs CrewAI", "AI agent framework comparison", "best AI agent platform 2026"
Skills & package management"agent skills", "AI agent skills management", "package manager for AI agents"
MCP & integrations"MCP servers", "MCP Claude integration", "MCP Cursor integration"
Open source library context"AI agent npm library support", "versioned context AI agents"

Reference: House Style Quick-Check

  • No em dashes (---): flag every instance
  • Suggestive tone for third-party claims ("aims to" > "is built for")
  • Minimal vibe-coding references (unless warranted)
  • 2–5 H2 subheadings minimum
  • At least 1 internal link to another tessl.io article
  • No excessive bolding or bullet-point overuse in prose sections
  • Opening paragraph front-loads the topic (featured snippet potential)
  • Terminology: "skills" not "tiles" (unless article specifically explains the legacy term)
  • Author's voice and personality are preserved throughout all suggestions
Workspace
bapfernandez
Visibility
Public
Created
Last updated
Publish Source
CLI
Badge
bapfernandez/article-reviewer badge