Last 20 Percent
by juliusbrussee8470b263d825No license162 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 2 months ago
Finds and finishes the last 20% of a built solution — the experiential layer agents skip: what the output actually reads like, which pages or screens should exist, first-run and empty states, opinionated defaults, the golden path. Use when planning any build so the magic gets specced as concretely as the plumbing, before calling any build "done", when a solution works but feels like a demo, or when the user says "last 20%", "finish this", "make it actually good", "is this actually done", or "why does this feel flat".
Only the file list is public. File contents are available once the skill is installed in a workspace.
| Path | Size | Type |
|---|---|---|
| references/last-20-catalog.md | 6.6 KB | text/markdown |
| SKILL.md | 8.2 KB | text/markdown |
Source and attribution
Source:juliusbrussee/skillsinskills/last-20-percentat commit8470b26
License: No license
Content belongs to its original authors. SourceWeft indexes it from a public repository.
More from juliusbrussee/skills
Junior To Senior
juliusbrussee
Adversarially reviews agent-written plans and rewrites them into a scoped, research-grounded senior version.
Interface Kit
juliusbrussee
Authoritative guide for implementing stunning, accessible, performant UI. Synthesizes design engineering philosophy, accessibility standards, animation principles, spatial design, typography, color systems, and component craft into a single actionable reference. Complements the design-system skill (which covers DESIGN.md spec writing) by covering the HOW of implementation. Trigger phrases: "build UI", "create component", "landing page", "make it look good", "frontend", "design", "polish UI", "implement design", "make it beautiful", "UI implementation", "component styling", "animation", "accessibility"
Grill Me
juliusbrussee
Runs a calibrated one-question-at-a-time interview to stress-test a plan, design, idea, or decision.
Deslopify
juliusbrussee
Scans and rewrites text to remove statistical fingerprints of AI writing, then re-scans until clean.
Caveman
juliusbrussee
Switches the agent into an ultra-compressed caveman-style reply mode to cut token usage while keeping technical accuracy.
More in Productivity & Workflow
Dd Meeting Prep
anthropics
Prepares question lists, benchmarks and red flags for due diligence meetings such as management presentations and expert calls.
Dd Checklist
anthropics
Builds and tracks sector-tailored due diligence checklists with workstreams, status tracking and red flag escalation.
Deal Tracker
anthropics
Tracks live M&A deals with milestones, deadlines, action items and weekly pipeline reviews.
Client Review
anthropics
Prepares client review meetings with portfolio performance, allocation analysis, talking points, and action items.
Morning Note
anthropics
Drafts concise morning meeting notes on overnight developments, trade ideas and key events for coverage stocks.
Notion Spec To Implementation
openai
Turns Notion specs into implementation plans, linked tasks, and progress updates inside Notion.