icp-reality-check
Skill5 starsChanged 4 months agoMITView on GitHub
Compares your stated ICP against actual closed-won and closed-lost customers. Use when you are about to write new targeting or messaging, or when the customers you actually close look nothing like the ICP on the slide.
In this repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ad-to-landing-promise-matchSkill
- b2b-audience-signal-auditSkill
- cold-outbound-sequence-reviewSkill
- competitor-lead-angle-reviewSkill
- crm-lead-source-quality-auditSkill
- discovery-call-gap-analysisSkill
- disqualification-reason-minerSkill
- email-nurture-sequence-reviewSkill
- form-friction-finderSkill
- ghosted-after-the-demoSkill
- google-ads-lead-quality-auditSkill
- landing-page-qualification-reviewSkill
- lead-magnet-offer-fitSkill
- lead-scoring-sanity-checkSkill
- lead-to-opportunity-drop-off-reviewSkill
- linkedin-ads-lead-quality-auditSkill
- meeting-prep-five-minutesSkill
- meta-ads-lead-quality-auditSkill
- objection-cheat-sheetSkill
- pipeline-hygiene-auditSkill
- proposal-win-loss-reviewSkill
- sales-follow-up-speed-auditSkill
- scale-readiness-check-lead-genSkill
- sdr-handoff-brief-generatorSkill
- spam-folder-checkSkill
- weekly-b2b-lead-gen-readoutSkill
- what-to-say-to-this-companySkill
- won-deal-to-case-studySkill
- write-the-follow-upSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 11 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use the shared quality bar in ../references/output-standard.md and ../references/skill-design-principles.md when those files are available.
- Distinctive: line 16
Do not use this skill for broad lead-generation advice without source, CRM, sales or qualification evidence.
- Distinctive: line 24
If an input is missing, continue with a clearly marked assumption instead of inventing data.
- Distinctive: line 28
Write the stated ICP as a short profile: company type, buyer role, pain, budget, urgency and exclusion rules.
- Distinctive: line 37
Use this table when the user provides CRM or sales outcome data:
- Distinctive: line 51
If the data does not connect to revenue, pipeline, qualified leads or conversion quality, label the recommendation as a hypothesis.
- Distinctive: line 52
If platform metrics and downstream data disagree, trust the downstream source for business quality and platform data for delivery mechanics.
- Distinctive: line 53
If the issue could be tracking, offer, audience, page or follow-up, do not collapse it into one cause without evidence.
- Distinctive: line 54
Do not recommend more budget until lead quality, follow-up and tracking confidence are separated.
- Distinctive: line 76
Do not make changes to live campaigns, pages, tags, containers, CRM fields or customer messages.
- Distinctive: line 77
Do not claim performance impact without evidence.
- Distinctive: line 79
Keep recommendations practical for a performance operator, founder or owner with a real advertising problem.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Icp Reality Check
Use the shared quality bar in ../references/output-standard.md and ../references/skill-design-principles.md when those files are available.
Use this skill when
- the user shares lead source, CRM stage, sales note, form, landing page or campaign data tied to icp reality check.
- the next decision could change targeting, qualification, scoring, follow-up, sales handoff or budget.
- lead volume looks acceptable but SQL, opportunity, closed-won, rejection or response-speed data raises doubt.
Do not use this skill for broad lead-generation advice without source, CRM, sales or qualification evidence. Use it when a real B2B lead quality decision is on the table.
Required input
- business model, ICP, offer, ACV or deal value range, sales cycle and main conversion goal.
- ad, landing page, lead form, CRM, call note, email or campaign data relevant to this diagnostic.
- time window, traffic source, lead volume and downstream outcomes where available.
- what decision the user is trying to make next: create, fix, scale, pause, brief sales or investigate.
- If an input is missing, continue with a clearly marked assumption instead of inventing data.
Analysis workflow
- Write the stated ICP as a short profile: company type, buyer role, pain, budget, urgency and exclusion rules.
- Build a comparison table for closed-won, closed-lost, disqualified and no-show leads by source, company size, role, industry, use case and deal value.
- Identify ICP drift: segments that produce cheap leads but weak SQL/opportunity/closed-won rates.
- Find ICP blind spots: segments with low lead volume but high sales acceptance or deal value.
- Separate targeting problems from offer, page, qualification and follow-up problems before recommending a change.
- Return an ICP action: keep, narrow, split into segments, exclude, or collect more data.
Diagnostic rubric
Use this table when the user provides CRM or sales outcome data:
| Segment | Lead volume | SQL rate | Opportunity rate | Closed-won rate | Rejection pattern | ICP verdict |
| Company size / role / industry / use case | Count and source mix | Percent or missing-data marker | Percent or missing-data marker | Percent or missing-data marker | Sales reason, no-show pattern or lost reason | Keep / narrow / split / exclude / collect more data |
Then summarize:
- ICP drift: segments that create leads but weak pipeline.
- ICP blind spot: segments with low volume but strong downstream quality.
- ICP change: the one targeting or qualification change worth testing first.
Decision rules
- If the data does not connect to revenue, pipeline, qualified leads or conversion quality, label the recommendation as a hypothesis.
- If platform metrics and downstream data disagree, trust the downstream source for business quality and platform data for delivery mechanics.
- If the issue could be tracking, offer, audience, page or follow-up, do not collapse it into one cause without evidence.
- Do not recommend more budget until lead quality, follow-up and tracking confidence are separated.
Output format
| Finding | Evidence | Lead quality impact | Recommended action | Confidence |
| Specific diagnostic claim | Data, screenshot, report, note or missing-data marker | Business or signal consequence | Smallest useful next step and owner | High / Medium / Low |
End with:
Decision:fix / test / monitor / ask for data / do not act yetApproval needed:yes/no and what would change if approvedMissing data:only the inputs that would materially change the recommendation
Practical example
User: "Here are CRM stages, source data and sales notes for icp reality check. What should we change before the next campaign move?"
Assistant should: put the stated ICP next to closed-won and closed-lost reality, name where they diverge, and stop at a corrected ICP the owner can sign off.
Guardrails
- Do not make changes to live campaigns, pages, tags, containers, CRM fields or customer messages.
- Do not claim performance impact without evidence.
- Mark missing data clearly.
- Keep recommendations practical for a performance operator, founder or owner with a real advertising problem.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

