SkillVaultskills Browse all 1,000+ skills

Reliability · Version 1.3.0 · Reviewed 2026-08-02

Capacity Planning Agent

Reduce production risk in load projection and headroom planning with evidence, explicit trade-offs, and a verification plan.

4 method steps 6 documented failure modes 5 diagnostic checks 7 quality gates

Translates traffic projections into concrete compute, storage, and connection requirements with headroom.

₹199 one-time

Get this skill archive

Install in your AI coding tool

SkillVault packages this skill in the open Agent Skills format for five leading coding tools, with a raw SKILL.md fallback for every other compatible IDE or agent.

See the complete graphical installation and usage guide

What this skill helps you do

  • Load projection
  • Headroom planning
  • Bottleneck identification

How Capacity Planning Agent works

You provide

Prompts, model versions, evaluation data, and failures

It inspects

Failure class and context sufficiency for load projection

It decides

A headroom planning change with one variable moved

You verify

Pass rate per case class against a pinned baseline

What it checks first

Capacity Planning Skill translates traffic projections into concrete compute, storage, and connection requirements with headroom. Use it when the work involves Load projection, Headroom planning, Bottleneck identification.

  1. Whether the failure is systematic across a class of inputs or random, which separates a capability gap from a sampling issue.
  2. Whether evaluation data overlaps training or prompt-development data, which invalidates the measurement.
  3. Token distribution of inputs and outputs, since cost and latency are driven by the tail, not the mean.
  4. Whether the system has a defined behavior for low confidence, or always produces an answer.
  5. Version pinning across model, prompt, retrieval, and tools, because an unpinned component makes regressions unattributable.

Failure modes it recognizes

  • Silent quality regression after a provider updates a model behind an unversioned alias.
  • Evaluation overfitting where the prompt was tuned on the same examples used to score it.
  • Cost and latency dominated by a small number of very long inputs that were never in the test set.
  • Tool-calling loops where the model retries a failing tool without a bounded attempt budget.
  • Confident fabrication when context is insufficient because no refusal path was defined.
  • Distribution shift where production inputs diverge from the evaluation set over time.

Answers it will reject

  • Judging quality by reading a few outputs, which cannot detect a regression of a few percent.
  • Using a larger model to fix a problem caused by missing context, paying more for the same failure.
  • Fine-tuning before exhausting prompting and retrieval, which is slower to iterate and harder to reverse.
  • Using an LLM judge without validating the judge against human labels on the same rubric.

Decision rules it applies

  • Establish a labeled evaluation set and a baseline before changing anything; without a baseline there is no improvement, only change.
  • Pin every version and change one component at a time.
  • Define and test the refusal path explicitly; a system that cannot say "I do not know" will fabricate.
  • Budget latency and cost on p95 token counts, not averages.

Evidence it asks for

  • Score per input class (easy, hard, adversarial, no-answer) so aggregate scores cannot hide a broken class.
  • Log model version, prompt version, and retrieval version on every request for regression attribution.
  • Track p50 and p95 tokens and cost per successful task, not per call.

The method inside

  1. Define the measured baseline and user-visible target for load projection.
  2. Attribute the dominant cost or latency mechanism affecting headroom planning.
  3. Rank bottleneck identification changes by expected impact, confidence, effort, and regression risk.
  4. Validate under representative load and retain guardrail metrics that detect a shifted bottleneck.

Deliverables

  • Load projection assessment
  • Headroom planning decision and action plan
  • Bottleneck identification verification checklist

Evidence requirements

  • User-visible symptoms and SLO impact
  • Timeline, telemetry, deploys, and dependency state
  • Current mitigations and operational constraints

Quality gates

  • Every material claim traces to supplied evidence or is labeled as a hypothesis.
  • The response follows the declared deliverable contract.
  • No execution, access, measurement, or verification is invented.
  • Secrets and personal data are redacted rather than repeated.
  • The user receives a concrete independent verification step.
  • The relevant failure modes in this domain were considered rather than only the reported symptom.
  • No listed anti-pattern was recommended as a solution.

Example task

Input

We expect 10x traffic during a product launch next month. What breaks first, and what should we size for?

Expected output

Your connection pool caps effective concurrency well before CPU saturates, so the database becomes the limit at roughly 3x, not 10x. Size against the pool and the slowest query under contention rather than against CPU headroom, because the CPU number will look healthy throughout the failure...

Boundaries and compatibility

Ideal for

  • Load projection: produce a decision or artifact grounded in supplied evidence.
  • Headroom planning: produce a decision or artifact grounded in supplied evidence.
  • Bottleneck identification: produce a decision or artifact grounded in supplied evidence.

Out of scope

  • Replacing incident command authority
  • Calling a trigger the root cause without a causal chain

Agent compatibility

  • GitHub Copilot Agent Skills
  • Cursor Agent Skills
  • Claude Code Skills
  • OpenAI Codex Skills
  • JetBrains Junie Skills

Tool policy: Advisory by default. No tools are assumed. If the host provides tools, use read-only evidence gathering unless the user explicitly approves a scoped write or execution action.