agentleFS
bookchaowalitbookchaowalit/platform-agent-skills/project-management/SKILL.md

project-management

Skill0 starsChanged 8 days agoApache-2.0View on GitHub

Run the Project Manager / Delivery Manager role for Solo Empire projects and client engagements — charter and authority, linked baseline (scope, schedule, cost, quality) with tolerances, WBS and resourcing, milestones and phase gates, RAID, a rated status report on a fixed cadence, change control against the baseline, external-party and vendor tracking, and closeout with final variance and lessons. Use when starting, planning, tracking, reporting on, escalating, re-baselining, or closing a project or engagement. Not for what to build or KPIs (product-management), backlog ordering and story acceptance (product-owner), requirements detail (business-analysis), or estimating effort (ai-native-estimation).

24 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 22 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep a bounded project on its approved baseline, make its status honest and visible, and close it with evidence.

    line 8
  2. Distinctive:

    Keep the evidence trail complete for outsourced and client work: decisions, approvals, minutes, and acceptance records with dates.

    line 63
  3. Distinctive:

    Do not duplicate other roles' artifacts.

    line 65

“Common” is measured: kept by at least 6 in 10 of the 22 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Project Management

Keep a bounded project on its approved baseline, make its status honest and visible, and close it with evidence.

Workflow

  1. Establish context: the owner and sponsor, client or internal, contract or SOW, the system's docpack, and the live task source. Open or create the control record from architecture-docs templates/positions/project-delivery-manager/project-control-record.md; it links every detailed artifact below rather than copying them.
  2. Initiate: write templates/sdlc/project-charter.md (objective, scope, authority, sponsor, constraints) and get it approved. Client work starts from templates/roles/engagement-delivery/engagement-kickoff.md.
  3. Plan the baseline:
    • scope from the BA requirements baseline (business-analysis);
    • WBS and resources with templates/sdlc/wbs-and-resource-plan.md;
    • effort and dates from ai-native-estimation (ranges, critical path, wait time);
    • milestones, gates, and RAID with templates/development-cycle/delivery-plan-and-raid.md;
    • cadence and audiences with templates/sdlc/communication-plan.md. Set a tolerance per dimension (scope, schedule, cost, quality). Mark dates that are not approved [ต้องยืนยัน].
  4. Track: on the stated cadence, update forecast against baseline, the RAID items rated high or due soon, and the milestone table. Outsourced or vendor work goes in templates/sdlc/external-parties/ (milestone and deliverable tracker, delay and dependency log).
  5. Report status with templates/roles/engagement-delivery/delivery-status-review.md and add a row to the control record. Rate with the written rule: green inside tolerance, amber outside with a recovery plan, red outside without one or when a sponsor decision is needed. Every decision needed has an owner and a date.
  6. Change control: any change to scope, schedule, or cost beyond tolerance needs a change record (templates/roles/engagement-delivery/delivery-change-record.md, or the BA change-request.md for requirements) and an approval before the baseline moves. Then update the RTM, plan, and estimate.
  7. Gates: run each phase gate with templates/sdlc/phase-gate-record.md; readiness and acceptance use the engagement-delivery readiness-review.md and acceptance-plan.md. Record minutes with templates/sdlc/meeting-minutes.md.
  8. Close: accepted deliverables, final variance against baseline, handoff (final-handoff.md), lessons learned, estimate calibration back to ai-native-estimation, and open items moved to the backlog with a new owner.

Decision rules

  • Report what is true. Never show green to avoid a hard conversation; a missed date or a blocked item is amber or red until recovered.
  • The baseline moves only through an approved change. Silent re-planning is a defect.
  • Spending, contract scope, external messages, delay notices to clients, and vendor escalation are owner decisions; draft them, do not send them.
  • Keep the evidence trail complete for outsourced and client work: decisions, approvals, minutes, and acceptance records with dates.
  • Do not duplicate other roles' artifacts. Link the BA baseline, the PO backlog and acceptance record, the SA design, and the QA evidence.

Handoff

Report the control record version, baseline versions and approvers, the current rating per dimension with variance, high RAID items with owners, open change records, next gate and its readiness, decisions needed with owner and date, and closeout status when the project ends.

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.