find-consulting-opportunities
Skill0 starsChanged 3 months agoMITView on GitHub
Discover evidence-backed consulting, fractional, advisory, coaching, implementation, and buyer-signal opportunities that are not ordinary job postings.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/job-agent.mdcCursor rule
- answer-questionsSkill
- claim-checkSkill
- daily-briefSkill
- find-broad-jobsSkill
- find-jobsSkill
- record-outcomeSkill
- refresh-candidate-brandSkill
- research-target-personSkill
- review-search-performanceSkill
- score-fitSkill
- setup-profileSkill
- tailor-resumeSkill
- write-cover-letterSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Use this skill when the candidate wants revenue opportunities beyond conventional employment.
- Distinctive: line 27
Every opportunity must include:
- Distinctive: line 35
Never invent a person's name, title, email, phone number, budget, or business pain.
- Very specific: line 39
Read candidate/MASTER_PROFILE.md, candidate/OPPORTUNITY_TRACKS.json, and candidate/SEARCH_PREFERENCES.md.
- Distinctive: line 40
Search public sources for current evidence.
- Very specific: line 48
Use the normalized target_person_roles as a research order, not as proof that a specific person is correct.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
find-consulting-opportunities
Use this skill when the candidate wants revenue opportunities beyond conventional employment.
Goal
Find organizations with a verifiable current signal that maps to one of the candidate's opportunity tracks, then produce a normalized research lead. Do not infer a need from industry stereotypes alone.
Good source signals
- a company explicitly announcing an AI, automation, CRM, digital-transformation, or growth initiative;
- a company posting several related implementation roles that indicate an active program;
- a public request for an advisor, fractional executive, trainer, workshop leader, product builder, or automation implementer;
- a project marketplace listing;
- a company publicly describing a manual workflow, integration gap, lead-response problem, or growth-system problem;
- a warm/referral signal provided by the user.
Required evidence
Every opportunity must include:
- company or organization;
- source and source URL when available;
- dated/current evidence whenever possible;
- the exact signal that makes the opportunity relevant;
- the best matching candidate opportunity lane;
- likely role categories that own the problem.
Never invent a person's name, title, email, phone number, budget, or business pain.
Workflow
- Read
candidate/MASTER_PROFILE.md,candidate/OPPORTUNITY_TRACKS.json, andcandidate/SEARCH_PREFERENCES.md. - Search public sources for current evidence.
- Save raw research records using
templates/CONSULTING_OPPORTUNITY_TEMPLATE.jsonas the contract. - Normalize them with
scripts/opportunity_model.pyor equivalent tool invocation. - Generate a brief with
scripts/opportunity_brief.py. - Present opportunities for human review before any contact or application.
Person targeting
Use the normalized target_person_roles as a research order, not as proof that a specific person is correct.
Examples:
- AI transformation -> Chief AI Officer, CIO, CTO, COO, transformation leader.
- AI product build -> CTO, VP Engineering, Head of Product, founder.
- Growth / CRM / automation -> CMO, CRO, VP Growth, RevOps leader, founder.
- Fractional advisory -> founder/CEO, president, COO, operating partner.
- Coworking / PropTech -> owner, CEO, COO, CMO, VP Sales.
Outreach boundary
The skill may prepare a factual draft after the user selects a lead. It must not mass-send messages or fabricate personalization.
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.

