editorial-surface
Skill16 starsChanged 5 months agoMITView on GitHub
Shape editorial and reading-first surfaces with strong hierarchy, readable measure, and disciplined media rhythm. Use for articles, guides, books, blog indexes, featured/recent cards, and other longform or text-heavy public surfaces.
In this repository94 other files it gives its agents.
- agent-friction-ledgerSkill
- agent-learning-layer-triageSkill
- agent-operations-contractSkill
- agents-best-practicesSkill
- agent-tool-contract-reviewSkill
- anti-slop-reviewSkill
- architecture-deepening-reviewSkill
- assumption-excavationSkill
- authorized-security-routerSkill
- book-to-skillSkill
- bounded-evaluationSkill
- bounded-growth-loopSkill
- bounded-orchestration-contractSkill
- brief-first-executionSkill
- browser-verificationSkill
- bug-evidence-protocolSkill
- codex-review-loopSkill
- compaction-survivalSkill
- complexity-optimizerSkill
- confidence-fragility-reviewSkill
- context-degradation-reviewSkill
- corporate-surfaceSkill
- delivery-baseline-auditSkill
- delivery-preflight-gateSkill
- design-critique-polishSkill
- designmd-brand-kitSkill
- design-register-bootstrapSkill
- diagnoseSkill
- doc-grounded-grillingSkill
- doc-to-lora-evaluatorSkill
- durable-context-maintenanceSkill
- dynamic-workflow-packetsSkill
- evidence-ledger-researchSkill
- filesystem-context-disciplineSkill
- fluid-interaction-reviewSkill
- frontend-product-builderSkill
- frontend-taste-layerSkill
- git-native-context-contractSkill
- goal-loop-designerSkill
- graph-guided-code-readingSkill
- handoffSkill
- happy-handoffSkill
- html-brief-artifactSkill
- html-diagram-artifactSkill
- hypothesis-diversificationSkill
- idea-to-ship-gatesSkill
- knowledge-base-enrichmentSkill
- lean-context-layoutSkill
- local-inference-tuningSkill
- loop-hardening-contractSkill
- loopops-protocolSkill
- loop-readiness-reviewSkill
- lottie-motion-builderSkill
- minimal-diff-builderSkill
- motion-review-gateSkill
- overengineering-reviewSkill
- personal-workspace-routerSkill
- phase-spec-executionSkill
- pipeline-readiness-gateSkill
- plan-to-issuesSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Treat reading experience as a product requirement, not decorative polish.
- Distinctive: line 15
Use this when the surface is text-first and the common failure mode is bad hierarchy, empty cards, oversized hero treatments, weak excerpt …
- Distinctive: line 55
not automatically adjacent to cover art if that creates a media wall.
- Distinctive: line 56
not after the entire article if it belongs near the core narrative.
- Distinctive: line 57
Verify desktop and mobile reading comfort before calling the change ready.
- Distinctive: line 72
Do not rewrite owner-approved article body unless explicitly asked.
- Distinctive: line 73
Do not turn editorial pages into generic marketing pages.
- Distinctive: line 74
Do not add decorative imagery to cover for weak hierarchy.
- Distinctive: line 75
Do not shrink content density so far that text-first surfaces become empty.
- Distinctive: line 76
Do not imitate Medium or Substack blindly when the project has its own identity.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Editorial Surface
Treat reading experience as a product requirement, not decorative polish.
Use this when the surface is text-first and the common failure mode is bad hierarchy, empty cards, oversized hero treatments, weak excerpt logic, or unreadable body rhythm.
Best Fit
- article pages;
- blog and writing indexes;
- guide pages;
- book and booklet landing sections;
- featured and recent content cards;
- mixed text/media editorial layouts.
Design Priorities
- title, deck, metadata, and body must read as one system;
- body measure and paragraph rhythm win over decorative hero treatment;
- cards should carry the right amount of information for their role;
- media should support reading, not interrupt it;
- text-only surfaces should still feel intentionally composed.
Workflow
- Identify the content role:
- index, featured card, recent card, article page, guide, or mixed editorial section.
- State the reading job:
- skim, choose, commit, or read deeply.
- Check the hierarchy:
- label/source/date;
- title;
- deck/excerpt;
- body;
- supporting media;
- actions and related links.
- Fix the common structural failures first:
- oversized title block;
- empty right side on text-only featured cards;
- recent cards with dead space instead of useful excerpt;
- metadata too faint to scan;
- body too light, narrow, or long-line;
- video or external resources placed without narrative rhythm.
- For mixed media, place media where it helps comprehension:
- not automatically adjacent to cover art if that creates a media wall;
- not after the entire article if it belongs near the core narrative.
- Verify desktop and mobile reading comfort before calling the change ready.
Output Shape
Return:
content rolereading jobhierarchy fixesexcerpt rulemedia placement ruledesktop/mobile reading checks
Guardrails
- Do not rewrite owner-approved article body unless explicitly asked.
- Do not turn editorial pages into generic marketing pages.
- Do not add decorative imagery to cover for weak hierarchy.
- Do not shrink content density so far that text-first surfaces become empty.
- Do not imitate Medium or Substack blindly when the project has its own identity.
Final Report
Include:
- the content role handled;
- the main hierarchy correction;
- the excerpt or media rule applied;
- desktop/mobile reading evidence;
- any remaining issue that still needs
anti-slop-revieworbrowser-verification.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

