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

shadow-presales

Skill1 starsChanged yesterdayMITView on GitHub

Enterprise IT Solutions & Commercial Pre-Sales. Use when analyzing RFP/TOR/KAK, scoring Bid/No-Bid, sizing 3-scenario workload capacity (conservative/expected/stress), modeling 3-5 yr TCO/NPV, or building Provider RAB/BoQ under Perpres 46/2025 (distinct from PPK HPS).

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-presales, evaluates a tender (KAK/TOR/RFP), decides Bid/No-Bid, designs solution …

    line 8
  2. Very specific:

    Never derive server specs solely from raw DAU guesses.

    line 20
  3. Very specific:

    Always produce 3 scenarios: conservative, expected, and stress, plus sensitivity sweeps.

    line 22

≈ “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-presales — Enterprise Solution & Commercial Engineering

Use this skill whenever the Monarch invokes /shadow-presales, evaluates a tender (KAK/TOR/RFP), decides Bid/No-Bid, designs solution options, models infrastructure capacity, or constructs commercial RAB/BoQ and multi-year TCO proposals.

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

  • methodologies/CAPACITY-TCO-AND-TENDER-METHODOLOGY.md — Requirements decomposition, tender intelligence, workload service-demand capacity engineering, 3–5 yr TCO/NPV/sensitivity, and Perpres Nomor 46 Tahun 2025 procurement compliance.
  • playbooks/ENGAGEMENT-PLAYBOOK-AND-TEMPLATES.md — Bid/No-Bid Scorecard, Solution Options MCDA, Assumption Register, Price Evidence Register, TCO Workbook, and Contract Exclusion Register.

1. Execution Contract (No Guessing, No Unauthorized Determinations)

  1. Context & Bid/No-Bid Gate: Identify sector (GOVERNMENT_SPBE, BUMN, BANKING, FINTECH, GENERAL_ENTERPRISE), separate Mandatory vs Desirable tender criteria, log ambiguities in a Clarification Register (Aanwijzing), and run a Bid/No-Bid Scorecard before committing proposal effort.
  2. Workload Capacity Engineering (3 Scenarios):
    • Never derive server specs solely from raw DAU guesses.
    • Require explicit CPU service demand ($D_{\text{cpu}}$) per workload class (read, write, report, batch), utilization ceiling, process RAM profile (base + concurrency * per_req_mem + cache + OS headroom), and configurable DB index/WAL ratios (db_index_overhead_pct, db_wal_headroom_pct) logged in the Assumption Register.
    • Always produce 3 scenarios: conservative, expected, and stress, plus sensitivity sweeps.
  3. FinOps, 3–5 Year TCO & Commercial Modeling:
    • Model CAPEX + recurring multi-year OPEX (cloud/hosting, licensing, FX sensitivity, annual renewal uplift, VAPT/audit, support, contingency), NPV, and Commercial Margin / Milestone Cashflow (Man-Month utilization, overhead, PPN).
  4. Indonesian Procurement Boundary (Perpres 46 Tahun 2025):
    • Strictly separate Provider Commercial Estimate (RAB / BoQ) from Official HPS (Harga Perkiraan Sendiri) which may ONLY be established by an authorized PPK / PA / KPA.
    • Validate PDN / TKDN priority (Pasal 66) and minimum 40% domestic UMKK allocation (Perpres 46/2025), citing price evidence sources (e-Katalog, vendor quotes, SSH/SBU).

2. Deterministic Calculator & Verification Gate

python "shadow-presales/scripts/presales_commercial_engine.py" --self-test
python "shadow-presales/scripts/presales_commercial_engine.py" --size-capacity path/to/workload.json
python "shadow-presales/scripts/presales_commercial_engine.py" --model-tco path/to/commercial.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.