Agent skill

good-enough-detector

Tell you when to stop polishing and ship — the point where more effort stops adding real value. Use when asked is this good enough, should I keep working on this, when do I stop, or I keep tweaking this and can't let go. Produces a read on whether the thing already meets its actual bar, the diminishing-returns check (is more effort improving it or just moving it around), what genuinely still needs fixing vs what's perfectionism, and a clear ship / one-more-pass / keep-going verdict — freeing you from polishing things past the point anyone will notice.

mohitagw158561,255★ · 1 repos on radarProfile →
claude-codecursorMIT
Install
npx skills add mohitagw15856/pm-claude-skills --skill good-enough-detector --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 4 KB
Bundled scripts: none
Path: skills/good-enough-detector/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 1,277
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Good-Enough Detector Perfectionism disguises itself as diligence, but past a point, more effort just moves things around without making them better — and the cost is everything else you're not doing. This checks whether your thing already clears its *actual* bar (not an imagined perfect one), whether you've hit diminishing returns, and what genuinely still needs fixing versus what's just you unable to let go. Then it tells you: ship, one more pass, or keep going. ## What This Skill Produces - **The real bar** — what "good enough" actually means for this thing's purpose and audience (usually lower than your perfectionist bar) - **The diminishing-returns read** — whether more effort is still improving it or just rearranging it - **Genuine fixes vs. perfectionism** — the few things that truly still need doing, separated from the endless polish that no one will notice - **The verdict** — ship it / one focused pass then ship / genuinely not there yet, with why - **The cost of not shipping** — what continuing to polish is costing you elsewhere ## Required Inputs Ask for these if not provided: - **The thing** — what you're working on (paste it or describe it) - **Its purpose and audienc

What's inside
Steps it walks through
  1. What This Skill Produces
  2. Required Inputs
  3. Framework: Find The Bar, Check The Returns
  4. Output Format
  5. Judging: [the thing] · for [purpose] · polishing for [time]
  6. Quality Checks
  7. Anti-Patterns
  8. Example Trigger Phrases
More from pm-claude-skills
All skills →
About this skill
What does the good-enough-detector skill do?

Tell you when to stop polishing and ship — the point where more effort stops adding real value. Use when asked is this good enough, should I keep working on this, when do I stop, or I keep tweaking this and can't let go. Produces a read on whether the thing already meets its actual bar, the diminishing-returns check (is more effort improving it or just moving it around), what genuinely still needs fixing vs what's perfectionism, and a clear ship / one-more-pass / keep-going verdict — freeing you from polishing things past the point anyone will notice.

How do I install it?

Run `npx skills add mohitagw15856/pm-claude-skills --skill good-enough-detector --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From mohitagw15856/pm-claude-skills, a repository with 1,277 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going