client-red-flags
Spot a bad client before you sign — the warning signs of the projects that turn into unpaid, scope-creeping nightmares, and how to screen, price, or decline them
Install / Use
npx skills add mohitagw15856/pm-claude-skills --skill client-red-flagsInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of client-red-flags
client-red-flags scores 82/100 on our quality scale, 2920th of 4,658 Development & Engineering skills we index.
Its SKILL.md is 4.6 KB long, well organised into 9 sections and no code examples: a solid amount of guidance for an agent.
With 1,396 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated 8 days ago, so client-red-flags is actively maintained.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
client-red-flags compared with similar skills
All 4 of these similar skills score higher than client-red-flags; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| client-red-flags (this skill)by mohitagw15856 | 82 | 1.4k | 8d ago | SKILL.md |
| ai-job-searchby MadsLorentzen | 100 | 44.8k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 41.7k | 2d ago | CLAUDE.md |
| algorithmic-artby anthropics | 100 | 177.9k | 10d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 10d ago | SKILL.md |
Frequently asked questions
- How do I install client-red-flags?
- Run
npx skills add mohitagw15856/pm-claude-skills --skill client-red-flags. The install tabs above show the steps for each supported agent. - Which AI agents does client-red-flags work with?
- It is written for Cline, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is client-red-flags safe to use?
- It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is client-red-flags still maintained?
- The repository was last updated 8 days ago, so client-red-flags is actively maintained.
Skill content
View source on GitHubname: client-red-flags description: "Spot a bad client before you sign — the warning signs of the projects that turn into unpaid, scope-creeping nightmares, and how to screen, price, or decline them. Use when asked is this client a red flag, should I take this client, screening a difficult client, or how to avoid bad clients. Produces a read on the warning signs present (haggling, vagueness, disrespect, urgency, unrealistic expectations), what each predicts, screening questions to ask before committing, protective terms if you proceed anyway, and how to decline gracefully — so you avoid the clients who cost more than they pay."
Client Red Flags
Experienced freelancers know: the worst projects announce themselves early. The client who haggles hard before you start, can't describe what they want, disrespects your time, or needs it "yesterday" tends to become the one who scope-creeps, pays late, and drains your energy. This reads the warning signs, tells you what they predict, and helps you screen, protect, or walk — before you're trapped.
What This Skill Produces
- A red-flag read — the warning signs present in this prospect and what each tends to predict (aggressive haggling → payment/scope issues; vagueness → endless revisions; disrespect early → worse later; false urgency → chaos)
- Screening questions — what to ask before committing to surface the risks (budget, decision-maker, success definition, timeline realism)
- Protective terms — if you proceed, the contract/process safeguards (deposit, milestone payments, tight scope, kill fee) that reduce the risk
- A proceed / protect / decline call — a judgment based on the severity and your situation
- A graceful decline — how to say no professionally without burning the bridge
Required Inputs
Ask for these if not provided:
- The prospect — how they've behaved so far (messages, calls, the ask)
- The project — what they want, budget signals, timeline
- The signs — anything that's given you pause
- Your situation — how much you need the work (affects risk tolerance)
- Your terms — what protections you can put in place
Framework: Read The Signs, Screen, Protect Or Pass
- Recognize the classic flags. Aggressive pre-start haggling, vague or shifting requirements, disrespect for your time/expertise, unrealistic timelines/expectations, "this'll lead to more work" in lieu of pay, and reluctance to sign or deposit.
- Translate to prediction. Each flag tends to forecast a specific future problem — name it so the decision is informed, not just a bad feeling.
- Screen before committing. Ask about budget, who decides, what success looks like, and timeline — the answers reveal risk. A prospect who won't engage is itself a signal.
- Protect if you proceed. For borderline cases you still want, use a deposit, milestone payments, a tightly-scoped contract, and clear change/revision terms.
- Decline gracefully when warranted. Some clients cost more than they pay — say no professionally, briefly, without insult, and keep the door open.
- Weigh your reality. Desperation lowers standards; factor honestly how much you need the work, but know the true cost of a nightmare client.
Output Format
Client screen: [prospect behavior] · project [x]
Red flags present: [flag → what it predicts] (e.g. haggling hard → likely payment/scope trouble). Screen with: ["what's the budget?" · "who signs off?" · "what does success look like?" · "is that timeline firm?"]. If you proceed — protect: [deposit · milestone payments · tight scope · change/revision terms · kill fee]. Call: [take it / take it with protections / decline] — because [severity + your situation]. Graceful decline: "[brief, professional no]".
Quality Checks
- [ ] Identifies the specific red flags present
- [ ] Translates each into what it tends to predict
- [ ] Provides screening questions to surface risk before committing
- [ ] Offers protective terms for borderline cases
- [ ] Gives a clear proceed/protect/decline call
- [ ] Includes a graceful, professional decline
Anti-Patterns
- Ignoring early warning signs because you want the work.
- A vague bad feeling with no specific flag named.
- Proceeding with no protective terms on a risky client.
- Taking every client regardless of cost.
- Declining rudely and burning a bridge.
Example Trigger Phrases
- "Is this client a red flag? They're haggling before we've even started."
- "Should I take this project? Something feels off about the client."
- "How do I screen out bad clients?"
- "This prospect can't tell me what they want — should I be worried?"
- "Help me decline a client politely."
Related Skills
ai-job-search
44.8kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
41.7kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
