agentleFS
RidhuanDEVRidhuanDEV/claude-skills/shadow-pmo/SKILL.md

shadow-pmo

Skill1 starsChanged yesterdayMITView on GitHub

Contractual IT Delivery & PMO Governance. Use when triaging client requests across contractual hierarchy (Contract/Addendum/KAK/SOW/FSD) as Defect vs Paid CR candidate, computing PERT + CPM + Monte Carlo (P50/P80/P90), EVM (CPI/SPI), or Laporan Proyek.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill whenever the Monarch invokes /shadow-pmo, evaluates a mid-project client request (Defect vs Paid CR), builds WBS & PERT/CPM …

    line 8
  2. Very specific:

    Never classify a client request as IN_SCOPE_DEFECT or PAID_CHANGE_REQUEST solely by comparing SRS text.

    line 19
  3. Very specific:

    Always evaluate against the full Contractual Hierarchy: Master Contract & Change Clauses -> Approved Addendum -> KAK / SOW -> Signed FSD / …

    line 20

≈ “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.

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

/shadow-pmo — Contractual & Delivery Governance

Use this skill whenever the Monarch invokes /shadow-pmo, evaluates a mid-project client request (Defect vs Paid CR), builds WBS & PERT/CPM schedules, runs P50/P80 schedule risk simulations, tracks Earned Value (CPI/SPI), or prepares Laporan Pendahuluan / Antara / Akhir and BAST acceptance packages.

Integrates with shadow-monarch/reference/CONSULTING-INTELLIGENCE-CORE.md and deep methodologies:

  • methodologies/CONTRACTUAL-GOVERNANCE-AND-SCHEDULE-RISK.md — Contractual document precedence, CR decision logic, PERT + Critical Path + Monte Carlo P50/P80/P90, and EVM math.
  • playbooks/PMO-DELIVERABLES-AND-CR-TEMPLATES.md — Scope Baseline Register, CR Decision Record, Schedule Impact Assessment, RAID Log, Earned Value Dashboard, and Acceptance Evidence Pack.

1. Execution Contract (No Unauthorized Legal Verdicts)

  1. Contractual Precedence Before CR Classification:
    • Never classify a client request as IN_SCOPE_DEFECT or PAID_CHANGE_REQUEST solely by comparing SRS text.
    • Always evaluate against the full Contractual Hierarchy: Master Contract & Change Clauses -> Approved Addendum -> KAK / SOW -> Signed FSD / SRS -> UAT Baseline & Warranty Clauses, plus implicit statutory/baseline obligations.
    • Any recommendation impacting commercial billing (PAID_CHANGE_REQUEST_CANDIDATE) MUST explicitly route through Change Control Board (CCB) / Contract Counsel / Authorized Client PPK or Sponsor (requires_human_approval: true).
  2. Schedule & Risk Engineering (PERT + CPM + Monte Carlo):
    • Compute activity expected duration $E = \frac{O + 4M + P}{6}$ and $\sigma = \frac{P - O}{6}$ across dependency DAGs.
    • Compute deterministic Critical Path (ES, EF, LS, LF, Total Float) AND run Monte Carlo simulation (fixed seed for reproducibility) to report realistic P50 / P80 / P90 completion dates rather than naive summed averages.
  3. Earned Value & Traceable Audit Trail:
    • Track PV, EV, AC, CPI = EV/AC, SPI = EV/PV, and EAC, plus an immutable CR Decision Record linking request -> baseline reference -> impact assessment -> CCB sign-off.

2. Deterministic PMO Governance Engine

python "shadow-pmo/scripts/pmo_governance_engine.py" --self-test
python "shadow-pmo/scripts/pmo_governance_engine.py" --analyze-schedule path/to/wbs_dag.json
python "shadow-pmo/scripts/pmo_governance_engine.py" --evaluate-cr path/to/cr_request.json

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.