agentsclimarketplace

Blog engine

Skill dranshrad/groundledger/skills/blog-engine

Groundledger: MIT agent skills for Claude Code, Cursor & Cowork — grounded blog SEO/AEO, PROBE site SEO, SAFE paid media, SPARK editorial, SNAP social, ORBIT discovery

Install
npx -y skills add dranshrad/groundledger --skill blog-engine

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 12 days oldThe repository was created 12 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Groundledger long-form skill: CLEAR rubric, claim ledgers, adversarial Q-tests, grounding law (no fabricated stats), YMYL, Ship Scan, Cite Surface Audit, Freshness Drift, Graph Runner, Locale Lattice, Release Latch. Use for blog drafts, rewrites, SEO audits, citation checks, clusters, multilingual plans, or publish readiness on Claude Code, Cursor, or Cowork.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

6.8 KB, ~1.7k tokens by cl100k_base, as published. Nobody here has run it

Blog Engine (CLEAR Editorial System)

Groundledger long-form skill for grounded, publish-ready articles.

Ship rule: CLEAR ≥ 85, claim ledger clean, Q-tests pass, residual risk accepted, Grounding Law satisfied, and (when requested) Ship Scan + Release Latch green.

Grounding Law: references/grounding.md — binding.

Modes

ModeGoal
draftNew article from JTBD + Spine Picker
improveRewrite under a diff contract
scoreCLEAR + ledger + residual risks
briefCompetitive teardown + evidence plan
horizonHorizon Brief — 90-day intent + surface bets
spineSpine Picker — form from JTBD + competitive gaps
mapReader-journey outline
verifyClaim audit (Claim Probe+)
cite-probe5 AI-style extractability questions
cite-surfaceCite Surface Audit — full citation readiness
ship-scanShip Scan — SEO + extractability checklist
collisionJob Collision Map — overlapping URL jobs
clusterIntent-pure graph
graph-runGraph Runner — plan → spoke briefs → ship order
freshnessFreshness Drift — refresh/consolidate/prune
mirrorMirror Markup — schema from visible truth
localeLocale Lattice — translate/localize/hreflang plan
frameFrame & Tone Kit — visual/chart/TTS briefs
signal-bridgeSignal Bridge — CWV/GSC/GA adapter checklist
releaseRelease Latch — packaging before handoff
adaptChannel packs (prefer social-cast atomize for depth)
ymylYMYL intensifier
calendarCadence + update triggers

Default for a bare topic: draft after one JTBD question.

CLEAR rubric (100)

See references/clear-rubric.md: Claim 25 · Lexical 15 · Entity 15 · Answer 25 · Reader-job 20. Ship at ≥ 85.

Core draft artifacts

Every draft / improve emits: article, claim ledger, adversarial Q-test, residual risks, CLEAR scorecard. Templates: references/artifacts.md.

Draft pipeline (summary)

  1. Lock JTBD · 2. Intent purity · 3. Evidence plan · 4. Spine Picker + journey map · 5. Write extractable answers · 6. Stress tests · 7. Deliver or block.

Full craft: references/craft.md · forms: references/forms.md · evidence: references/evidence.md.

Stress tests (blocking)

#TestPass
1Claim ledgerNo blocked material rows
2Contradiction huntNo internal conflicts
3Q-test5/5 extractable
4CLEAR≥ 85
5YMYLIntensifier green if triggered
6AccessibilityAlt, links, heading order

Extended modes (quick contracts)

Horizon Brief (horizon)

90-day plan: ICP jobs, surface bets, hub/spoke candidates, evidence gaps, KPI per asset. Hand production to draft / graph-run.

Spine Picker (spine)

Pick form from references/forms.md using JTBD + competitor spine gaps. Output: chosen form + rejected forms + why.

Ship Scan (ship-scan)

Owned SEO + extractability checklist (titles, meta, headings, links, OG, schema mirror, extractable opens). See references/ship-scan.md. Separate from CLEAR.

Job Collision Map (collision)

Given a corpus (paths or titles+jobs), flag overlapping JTBDs. Recommend merge, differentiate, or prune.

Cite Surface Audit (cite-surface)

Full citation readiness beyond cite-probe: entity stability, passage inventory, crawler access notes, structure for extraction. references/cite-surface.md.

Claim Probe+ (verify)

Per claim: support status, confidence (high/med/low), echo risk (same claim repeated without new evidence), fix action.

Freshness Drift (freshness)

From traffic/export deltas or stale dates: classify refresh / consolidate / prune; attach update triggers. references/freshness.md.

Graph Runner (graph-run)

Cluster plan → ordered spoke briefs → ship sequence with dependencies. Reject duplicate jobs.

Mirror Markup (mirror)

Emit JSON-LD only mirroring visible content (BlogPosting/Article, Person/Organization, BreadcrumbList). No invisible FAQ games.

Locale Lattice (locale)

Plan locales, adaptation depth (translate vs cultural), hreflang pairs, parity checklist. references/locale-lattice.md.

Frame & Tone Kit (frame)

Tool-agnostic briefs: hero brief, chart-from-ledger, optional TTS narration brief. references/frame-tone.md.

Signal Bridge (signal-bridge)

Checklist for plugging CWV, Search Console, analytics, keyword exports — no vendor lock-in. references/signal-bridge.md.

Release Latch (release)

Pre-handoff: required artifacts present, links resolve policy, hero/social image notes, review.md summary. references/release-latch.md.

YMYL

See references/ymyl.md.

Works with (sister tools)

Progressive disclosure

FileWhen
grounding.mdAnti-hallucination (always)
clear-rubric.mdScoring
artifacts.mdLedgers / Q-tests
evidence.mdSourcing
craft.mdProse / a11y
forms.mdSpines
ship-scan.mdSEO checklist
cite-surface.mdCitation audit
freshness.mdDecay
locale-lattice.mdi18n
frame-tone.mdMedia briefs
signal-bridge.mdAnalytics adapters
release-latch.mdPackaging
ymyl.mdHigh-stakes

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.