engagement-retention-content
Documents the content-and-return-loop engagement checks that matter for sites where value comes from repeated visits and content depth rather than a single…
Skill by AAX10
Chalk Labs
Need help deploying engagement-retention-content?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/aax10-engagement-retention-content
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: devops, writing, marketing, research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/engagement-retention-content
What's inside
- Skill name
engagement-retention-content- Description
- Documents the content-and-return-loop engagement checks that matter for sites where value comes from repeated visits and content depth rather than a single transaction — news/media publishers and community/social/forum platforms. Covers related-content discovery (grounded in Chartbeat's Engaged Time research), ad density, freshness, onboarding clarity for specialized systems, and return-trigger infrastructure. Implementation lives in the orchestrator's consolidated script; selected by the orchestrator's own read of the site's business model.
- License
- MIT
- Instructions
- 24 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- allowed-tools: must be a space-separated string
Files (1)
- SKILL.md
SKILL.md (first lines)
# Engagement: Retention & Content ## When to use Included when the orchestrator's own judgment (see `engagement-audit-orchestrator/SKILL.md` step 2) concludes the site's engagement model centers on repeat visits and content/community depth rather than a single transaction. `genre_signals` (`news`/`community`) are supporting evidence, not a standalone trigger. ## Implementation Every check below is implemented in `engagement-audit-orchestrator/scripts/run_audit.js` (`checkRelatedContentModule`, `checkAdDensity`, `checkFreshness`, `checkOnboardingHelp`, `checkReturnTriggers`), computed once as part of the single consolidated pass. ## Checks and their rationale 1. **Related-content / next-action modules.** Flags article pages with no related-content block after the main content. Cited against **Chartbeat's Engaged Time research**: near-identical pageview counts hid a 91%-vs-7% gap in real reader engagement across two articles — extending a session past the first page is the metric that matters, not raw traffic. 2. **Ad density (news genre).** Flags articles where ad-slot markers exceed half the count of paragraph blocks — a well-documented, fast-acting bounce driver on publisher sites. 3. **Freshness.** Flags a stale homepage/feed (newest dated JSON-LD item older than 48h) for sites scoring high on the `news` signal. 4. **Onboarding clarity for specialized systems.** Flags a displayed reputation/rank/karma system with no in-context explanation (tooltip, help link) reachable nearby — invisible friction for new users that veteran users and the site's own team will never notice on their own. 5. **Return-trigger infrastructure.** Flags the absence of any detectable notification mechanism as a low-severity, evidence-only opportunity — some sites intentionally rely on habitual direct visits instead, so this is framed as a suggestion, not a defect. ## Output Same finding-object shape as every other category.
From AAX10/Adobe-Round-3, MIT.
More from AAX10/Adobe-Round-3
- 0.526score
source-selection-auditor
AAX10
Evaluates whether an AI retriever can reliably select a page's primary factual content by measuring content density ratio, heading-to-answer locality, and…
SkillBFreshness: BClaude Code +9 - 0.525score
engagement-audit-orchestrator
AAX10
Entrypoint skill for the brand-engagement-audit marketplace.
SkillBFreshness: BClaude Code +9 - 0.525score
engagement-conversion-friction
AAX10
Documents the transaction-oriented engagement checks that matter for sites where the visit is meant to end in a discrete action — e-commerce checkout, SaaS…
SkillBFreshness: BClaude Code +9 - 0.525score
master-orchestrator
AAX10
Single entrypoint for the Brand AI Readiness Audit marketplace.
SkillBFreshness: BClaude Code +9 - 0.521score
A-Crawlability
adobe-hackathon-research
Audit a public website's crawlability — the first gate in the machine discovery pipeline.
SkillBFreshness: BClaude Code +9 - 0.521score
F-Non-Text-Lock-In
adobe-hackathon-research
Audit a public webpage for non-text lock-in — important facts trapped in images, PDFs, or video/canvas without readable text equivalents.
SkillBFreshness: BClaude Code +9 - 0.521score
C-Extractability
adobe-hackathon-research
Audit a public webpage's machine-readability — whether important facts can be correctly extracted by AI and machine readers.
SkillBFreshness: BClaude Code +9 - 0.520score
site-capture
AAX10
Documents the capture phase — fetching a target URL over plain HTTP (no browser automation), extracting HTML metadata and structured signals (JSON-LD, genre…
SkillBFreshness: BClaude Code +9 - 0.520score
engagement-local-trust-leads
AAX10
Documents the trust-and-lead-capture engagement signals that matter for local and professional-services businesses — dentists, clinics, law firms…
SkillBFreshness: BClaude Code +9 - 0.520score
engagement-technical-baseline
AAX10
Documents the business-model-agnostic engagement checks that apply to every audited site — response-time-based performance signal, static accessibility…
SkillBFreshness: BClaude Code +9 - 0.517score
mechanism-d-entity-graph
AAX10
Audits the JSON-LD structured data layer to ensure an organization has a connected entity graph, strong external identity anchors, and cross-modal consistency…
SkillBFreshness: BClaude Code +9 - 0.515score
Personalization Context Audit
AAX10
Audits websites for hyper-localization and persona context fragmentation that causes AI systems to drop sources.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 11, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/AAX10/Adobe-Round-3
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from AAX10
- 0.526score
source-selection-auditor
AAX10
Evaluates whether an AI retriever can reliably select a page's primary factual content by measuring content density ratio, heading-to-answer locality, and…
SkillBFreshness: BClaude Code +9 - 0.525score
engagement-audit-orchestrator
AAX10
Entrypoint skill for the brand-engagement-audit marketplace.
SkillBFreshness: BClaude Code +9 - 0.525score
engagement-conversion-friction
AAX10
Documents the transaction-oriented engagement checks that matter for sites where the visit is meant to end in a discrete action — e-commerce checkout, SaaS…
SkillBFreshness: BClaude Code +9 - 0.525score
master-orchestrator
AAX10
Single entrypoint for the Brand AI Readiness Audit marketplace.
SkillBFreshness: BClaude Code +9 - 0.520score
site-capture
AAX10
Documents the capture phase — fetching a target URL over plain HTTP (no browser automation), extracting HTML metadata and structured signals (JSON-LD, genre…
SkillBFreshness: BClaude Code +9 - 0.520score
engagement-technical-baseline
AAX10
Documents the business-model-agnostic engagement checks that apply to every audited site — response-time-based performance signal, static accessibility…
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get engagement-retention-content running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
engagement-retention-content skill. Agent Mart. https://agentmart.dev/skills/aax10-engagement-retention-content (last updated 2026-10-24)