Agent skill

should-i-quit-or-push

Get an honest read on whether to quit or keep going on a project, job, hobby, or goal that's become a slog — distinguishing a dip worth pushing through from a dead end worth leaving. Use when asked should I quit this, is it time to give up on, push through or walk away, or I don't know if I should keep going. Produces a diagnosis of whether you're in a temporary dip or a genuine dead end, the sunk-cost and identity traps clouding the call, honest signals pointing each way, and a clear push / pivot / quit recommendation — because both quitting too early and quitting too late are expensive.

mohitagw158561,255★ · 1 repos on radarProfile →
claude-codecursorMIT
Install
npx skills add mohitagw15856/pm-claude-skills --skill should-i-quit-or-push --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/should-i-quit-or-push/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

# Should I Quit or Push Every worthwhile thing has a slog in the middle — a dip where it stops being fun and isn't yet paying off. Push through the dip and you win; but push through a genuine dead end and you waste years. The whole skill is telling them apart, past the sunk-cost fog and the "I'm not a quitter" identity story. This gives an honest read and a real recommendation, not just "follow your heart." ## What This Skill Produces - **Dip or dead end?** — the core diagnosis: is this a temporary hard patch that gets better if you push, or a structural dead end that won't? - **The traps clouding it** — sunk cost ("I've put so much in"), identity ("quitting means I failed"), and fear-of-the-unknown, named so they stop distorting the call - **Signals each way** — the honest indicators pointing toward push vs. toward quit - **The recommendation** — push through / pivot (change the approach, not the goal) / quit — with the reasoning - **A face-saving exit or a re-commitment** — depending on the call, how to actually do it ## Required Inputs Ask for these if not provided: - **The thing** — the project, job, hobby, relationship, or goal - **Why it's hard now** — what's making you consi

What's inside
Steps it walks through
  1. What This Skill Produces
  2. Required Inputs
  3. Framework: Dip vs. Dead End
  4. Output Format
  5. The thing: [project/job/goal] · considering quitting because [x]
  6. Quality Checks
  7. Anti-Patterns
  8. Example Trigger Phrases
More from pm-claude-skills
All skills →
About this skill
What does the should-i-quit-or-push skill do?

Get an honest read on whether to quit or keep going on a project, job, hobby, or goal that's become a slog — distinguishing a dip worth pushing through from a dead end worth leaving. Use when asked should I quit this, is it time to give up on, push through or walk away, or I don't know if I should keep going. Produces a diagnosis of whether you're in a temporary dip or a genuine dead end, the sunk-cost and identity traps clouding the call, honest signals pointing each way, and a clear push / pivot / quit recommendation — because both quitting too early and quitting too late are expensive.

How do I install it?

Run `npx skills add mohitagw15856/pm-claude-skills --skill should-i-quit-or-push --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