Agent skill

Good Enough Detector

by mohitagw15856 in mohitagw15856/pm-claude-skills

Tell you when to stop polishing and ship — the point where more effort stops adding real value.

MITAuto-check passed

Install Good Enough Detector

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill good-enough-detector -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills good-enough-detector --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/good-enough-detector .claude/skills/good-enough-detector && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
good-enough-detector
GitHub stars
1.4k
Token cost
~1k tokens
SKILL.md length
527 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Tell you when to stop polishing and ship — the point where more effort stops adding real value.

  • Works in 5 steps: Define the actual bar. What does this… → Check it against the bar. Does it… → Test for diminishing returns. Are the… → …
  • Asked is this good enough
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: Find The Bar, Check… and Output Format, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Good Enough Detector is an agent skill from mohitagw15856/pm-claude-skills. 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…

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked is this good enough
  • Should I keep working on this
  • I keep tweaking this and cant let go

Example prompts

  • “/good-enough-detector”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Define the actual bar. What does this genuinely need to accomplish for its purpose? Judge against that, not perfection.
  2. Check it against the bar. Does it already clear it? Often the answer is yes and the person just can't see it.
  3. Test for diminishing returns. Are the recent changes real improvements a user would notice, or just movement? If it's movement, you're done.
  4. Separate fixes from polish. List what genuinely still needs doing (real gaps) vs. what's perfectionism (things no one will notice).
  5. Give the verdict — and the cost. Ship / one pass / keep going, plus what continuing to polish is costing you elsewhere, so shipping feels…

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Good Enough Detector loads about 1k tokens when it runs. Until then it costs about 145 tokens; SKILL.md has 527 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~145
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 527 words, ~1,027 tokens.

Download SKILL.mdSave it as .claude/skills/good-enough-detector/SKILL.md (or your agent's skills folder).
name
good-enough-detector
description
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.

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 audience — who it's for and what it needs to do (sets the real bar)
  • How long you've been polishing — a clue to diminishing returns
  • What you're still tweaking — the changes you keep making

Framework: Find The Bar, Check The Returns

  1. Define the actual bar. What does this genuinely need to accomplish for its purpose? Judge against that, not perfection.
  2. Check it against the bar. Does it already clear it? Often the answer is yes and the person just can't see it.
  3. Test for diminishing returns. Are the recent changes real improvements a user would notice, or just movement? If it's movement, you're done.
  4. Separate fixes from polish. List what genuinely still needs doing (real gaps) vs. what's perfectionism (things no one will notice).
  5. Give the verdict — and the cost. Ship / one pass / keep going, plus what continuing to polish is costing you elsewhere, so shipping feels justified.
Show full SKILL.md (190 more words)Show less

Output Format

Judging: [the thing] · for [purpose] · polishing for [time]

The real bar: [what good-enough means here]. Clears it? [yes / almost / no]. Diminishing returns? [your recent tweaks are improving it / just moving it around]. Still genuinely needs: [real fixes] · Just perfectionism (skip): [things no one will notice]. Verdict: [🚢 ship it / one focused pass then ship / not there yet — because X]. Polishing more is costing you: [what else isn't getting done].

Quality Checks

  • Defines the real bar for the purpose, not perfection
  • Checks whether it already clears that bar
  • Tests for diminishing returns
  • Separates genuine fixes from perfectionist polish
  • Gives a clear ship/pass/keep-going verdict
  • Names the cost of continuing to polish

Anti-Patterns

  • Encouraging more polish on something already good enough.
  • Judging against an imagined perfect version.
  • No clear verdict — leaving the person still tweaking.
  • Ignoring the opportunity cost of not shipping.

Example Trigger Phrases

  • "Is this good enough to send, or should I keep working on it?"
  • "I keep tweaking this presentation and can't let go."
  • "When do I stop polishing this?"
  • "Am I done, or does this still need work?"
  • "Help me ship this — I think I'm just perfectionist-ing now."

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/good-enough-detector of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Good Enough Detector next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Good Enough Detector compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Good Enough Detector this skillmohitagw15856/pm-claude-skills1.4k—~1kAutomated safety check: PassMIT
Shipsimstudioai/sim30k—~4.2kAutomated safety check: PassApache-2.0
Ship Itvectorize-io/hindsight48k—~1.9kAutomated safety check: PassMIT
Ship Workflowgarrytan/gstack136k—~20kAutomated safety check: NotesMIT
Shipmillionco/react-doctor15k—~716Automated safety check: PassCustom licence
Impeccable Design Polishnexu-io/open-design100k—~735Automated safety check: PassApache-2.0

Similar skills

  • Ship

    simstudioai/sim

    Commit, push, and open a PR to staging in one shot — runs the cleanup pass and, when migrations changed, the db-migrate safety review first

    30k GitHub stars~4.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Ship It

    vectorize-io/hindsight

    Take a PR from review to merged — run the repo's code-review skill on it in a loop (review, fix, re-review) until nothing is left to fix, applying ALL fixes on the PR branch, wait for CI green, then…

    48k GitHub stars~1.9k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Ship Workflow

    garrytan/gstack

    Takes finished code to a pull request: merges the base branch, runs tests, reviews the diff, bumps VERSION, updates the CHANGELOG, commits, pushes and opens the PR.

    136k GitHub stars~20k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Ship

    millionco/react-doctor

    Take the current branch from done-coding to merge-ready in one pass — review the diff against AGENTS.md, deslop, commit and push, open a PR using rule-validate's PR copy, then babysit until mergeable.

    15k GitHub stars~716 tokensUpdated today
    DevelopmentAuto-check passed
  • Impeccable Design Polish

    nexu-io/open-design

    Follow-up design polish skill inspired by Impeccable. An agent skill from nexu-io/open-design.

    100k GitHub stars~735 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Shipping Artifacts

    phuryn/pm-skills

    The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping.

    27k GitHub stars~2.2k tokensUpdated yesterday
    Testing & QAAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Good Enough Detector

What does Good Enough Detector do?

Tell you when to stop polishing and ship — the point where more effort stops adding real value. Good Enough Detector is an agent skill from mohitagw15856/pm-claude-skills. Tell you when to stop polishing and ship — the point where more effort stops adding real value.

When should I use Good Enough Detector?

Good Enough Detector fits situations like: asked is this good enough; should I keep working on this; I keep tweaking this and cant let go.

How do I install Good Enough Detector in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill good-enough-detector -a claude-code`. Or copy the skill folder (skills/good-enough-detector in mohitagw15856/pm-claude-skills) into .claude/skills/good-enough-detector in your project. Claude Code loads it when a task matches its description.

How do I install Good Enough Detector in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill good-enough-detector -a codex`. Or copy the skill folder (skills/good-enough-detector in mohitagw15856/pm-claude-skills) into .agents/skills/good-enough-detector in your project. Codex loads it when a task matches its description.

Can I use Good Enough Detector in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill good-enough-detector -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/good-enough-detector, .gemini/skills/good-enough-detector, .github/skills/good-enough-detector and .opencode/skills/good-enough-detector in your project.

What does Good Enough Detector need to run?

SKILL.md names no scripts, command-line tools or credentials: Good Enough Detector is instructions for the agent only.

Does Good Enough Detector access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Good Enough Detector safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Good Enough Detector use?

Good Enough Detector is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Good Enough Detector use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Good Enough Detector?

Skills that share tags, products or a category with Good Enough Detector: Ship (simstudioai/sim, 30k stars), Ship It (vectorize-io/hindsight, 48k stars), Ship Workflow (garrytan/gstack, 136k stars) and Ship (millionco/react-doctor, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Good Enough Detector?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.