agentleFS
anotbanotb/management-consulting-plugin/skills/engagement-setup/SKILL.md

engagement-setup

Skill62 starsChanged 12 days agoMITView on GitHub

Launch a consulting engagement with a focused kickoff, discovery plan, stakeholder assessment, and working arrangements. Use after award or when resetting an engagement that lacks shared scope, access, or decision authority.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Engagement Setup

Turn the agreed engagement into a shared problem definition, access to evidence, working ownership, and useful early progress. Preserve the contract, approved scope, existing work, and client's operating requirements. Do not replay sales qualification after award or impose enterprise governance on a small advisory task.

Use the brief, contract, known team, timeline, and available data. Draft supported portions while recording missing information. Ask only when a missing answer changes the scope or makes the plan unusable. Mark unknown stakeholder positions and proposed commitments rather than filling them with plausible names, dates, or attitudes.

Prepare the launch

Identify the outcome, decision-maker, scope boundaries, deliverables, success evidence, dependencies, and near-term decisions. Compare expectations with the agreement and make discrepancies visible. Separate contractual commitments from planning assumptions.

Map affected groups and decision roles. Use a power-interest matrix when it helps: high power/high interest = manage closely; high power/low interest = keep satisfied; low power/high interest = keep informed and hear their input; low power/low interest = monitor proportionately. Influence and interest do not establish support or opposition. Record stance from evidence and revisit it when information changes.

Design the kickoff around unresolved alignment and decisions. Move routine information into a proportionate pre-read if time permits. Select a duration and participants to fit the brief; a kickoff can be a short working session rather than a workshop. Identify the authority or representation required for decisions without treating absence as automatic evidence of disengagement.

For a charter, use project charter template. Adapt fields to the engagement; do not require every field to be finalized live or describe a charter as replacing the contract.

Design discovery

Tie each question to the decision it will inform. Choose data review, interviews, observation, working sessions, or a survey according to the evidence needed. Use discovery methods for requests, interviews, and synthesis.

Distinguish an interview report, an observed behavior, and a measured outcome. Several people reporting the same theme can justify further investigation but do not establish prevalence or causality. Test executive accounts against operating evidence without assuming either is always more accurate.

Prioritize evidence that could change the recommendation or unlock work. Track what was requested, supplied, tested, and still missing. Do not commission broad research or contact stakeholders merely because a template lists them; execute those actions within the user's authorization.

Establish working arrangements

For the work that needs coordination, set workstream ownership, deliverable handoffs, decision rights, access, document locations, version conventions, communication channels, and escalation. Reuse the client's systems and governance. Schedule only the ceremonies needed to make decisions or resolve dependencies.

Capture actual agreements separately from proposals. Protect sensitive stakeholder assessments and interview confidentiality under the engagement's rules; sanitize shared materials where appropriate. Do not promise anonymity or record a meeting without the applicable agreement and authorization.

Deliver

Produce the requested kickoff agenda, charter draft, discovery plan, interview guide, or launch pack. Check that it reflects the contract, identifies unresolved decisions, and makes the first useful work clear. Named actions need an owner and timing; when unconfirmed, use a proposed role and relative date. Report evidence gaps as work to resolve, not as invented findings.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.