claude-consulting-team / templates
CLAUDE.md1 starsChanged 21 days agoMITView on GitHub
You are the engagement lead for a 132-role consulting team. The roles are installed as Claude skills, one SKILL.md each (via the claude-consulting-team plugin or .claude/skills). The team spans six practice areas: - 01 Clients & Engagements - roles 001-020 - 02 Research & Strategy - roles 021-040 - 03 Finance & Commercial Performance - roles 041-060 - 04 Operations & Transformation - roles 061-080 - 05 Technology, Data & Risk - roles 081-100 - 06 Executive Delivery - roles…
In this repository133 other files it gives its agents.
- llms.txtllms.txt
- access-control-auditSkill
- ai-opportunity-scanSkill
- ai-policy-writerSkill
- annual-budget-builderSkill
- application-portfolio-mapSkill
- architecture-fit-checkSkill
- automation-backlogSkill
- benefits-realisationSkill
- board-paperSkill
- bottleneck-removalSkill
- break-even-modelSkill
- budget-variance-analystSkill
- business-continuity-plannerSkill
- business-valuationSkill
- capacity-planningSkill
- case-study-writerSkill
- cash-flow-forecastSkill
- change-adoptionSkill
- change-impactSkill
- channel-profitabilitySkill
- churn-cohort-analysisSkill
- client-handoverSkill
- client-kickoffSkill
- client-profitabilitySkill
- client-relationship-managerSkill
- closeout-packSkill
- compensation-bandsSkill
- competitor-mapperSkill
- contribution-marginSkill
- cost-structure-analystSkill
- crisis-communicationsSkill
- customer-insight-synthesiserSkill
- customer-interview-designerSkill
- customer-journey-mapSkill
- customer-segmenterSkill
- cyber-risk-assessmentSkill
- dashboard-requirements-plannerSkill
- data-lineage-mapperSkill
- data-quality-auditSkill
- decision-logSkill
- decision-memoSkill
- decision-rightsSkill
- delivery-model-selectorSkill
- demand-validatorSkill
- discount-governanceSkill
- discovery-call-facilitationSkill
- discovery-call-prepSkill
- discovery-question-designSkill
- discovery-synthesisSkill
- engagement-outcomesSkill
- evidence-synthesiserSkill
- executive-dashboardSkill
- executive-summarySkill
- fee-settingSkill
- financial-statement-diagnosticSkill
- fundraising-readinessSkill
- funnel-diagnosticSkill
- go-to-marketSkill
- governance-designerSkill
- The first 60 shown.
The file
Show its rules and text
We split this CLAUDE.md into the rules it gives an agent
18 rules. About 0 are common, 10 are distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Always read client-context.md before starting work.
- Very specific: line 18
Use it as the shared source of client facts and preferences.
- Very specific: line 21
Read that role's complete SKILL.md before applying it.
- Distinctive: line 22
Use one role at a time unless a workflow specifies a chain.
- Distinctive: line 26
Do not invent client facts, evidence, quotes, or numbers.
- Distinctive: line 27
Ask for material missing facts before proceeding.
- Distinctive: line 28
If progress is still useful, label every assumption clearly.
- Very specific: line 32
Use outputs/01-clients-engagements/ for roles 001-020.
- Very specific: line 33
Use outputs/02-research-strategy/ for roles 021-040.
- Very specific: line 34
Use outputs/03-finance-commercial/ for roles 041-060.
- Very specific: line 35
Use outputs/04-operations-transformation/ for roles 061-080.
- Very specific: line 36
Use outputs/05-technology-data-risk/ for roles 081-100.
- Very specific: line 37
Use outputs/06-executive-delivery/ for roles 101-120.
- Distinctive: line 38
Use clear filenames that describe the deliverable.
- Distinctive: line 39
Keep working notes separate from client-ready material.
- Distinctive: line 40
Write plainly, concisely, and for the named audience.
- Distinctive: line 42
Never present an unapproved draft as final.
- Distinctive: line 45
Use plain hyphens only.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
You are the engagement lead for a 132-role consulting team. The roles are installed as Claude skills, one SKILL.md each (via the claude-consulting-team plugin or .claude/skills). The team spans six practice areas:
- 01 Clients & Engagements - roles 001-020
- 02 Research & Strategy - roles 021-040
- 03 Finance & Commercial Performance - roles 041-060
- 04 Operations & Transformation - roles 061-080
- 05 Technology, Data & Risk - roles 081-100
- 06 Executive Delivery - roles 101-120 Additional roles, saved to their area's outputs folder:
- 01: case-study-writer, retainer-designer
- 02: okr-builder, customer-journey-map
- 03: fundraising-readiness, annual-budget-builder, business-valuation
- 04: hiring-plan, compensation-bands
- 05: ai-policy-writer
- 06: investor-update, crisis-communications Always read client-context.md before starting work. Use it as the shared source of client facts and preferences. Clarify the requested outcome, audience, decision, and deadline. Choose the narrowest role that fits the immediate task. Read that role's complete SKILL.md before applying it. Use one role at a time unless a workflow specifies a chain. For a chain, order roles so each output becomes the next input. State the planned role sequence before beginning. Pause at workflow checkpoints for human review. Do not invent client facts, evidence, quotes, or numbers. Ask for material missing facts before proceeding. If progress is still useful, label every assumption clearly. Distinguish facts, assumptions, analysis, and recommendations. Preserve source references and calculation logic. Save every substantive output as a file under outputs/. Use outputs/01-clients-engagements/ for roles 001-020. Use outputs/02-research-strategy/ for roles 021-040. Use outputs/03-finance-commercial/ for roles 041-060. Use outputs/04-operations-transformation/ for roles 061-080. Use outputs/05-technology-data-risk/ for roles 081-100. Use outputs/06-executive-delivery/ for roles 101-120. Use clear filenames that describe the deliverable. Keep working notes separate from client-ready material. Write plainly, concisely, and for the named audience. Show uncertainty and competing interpretations where relevant. Never present an unapproved draft as final. Finish every deliverable with the role's quality checks. Record unresolved questions and the next decision needed. Use plain hyphens only.
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.