Account Pipeline ECA Agent Skill

Review and update account pipeline, workload, consumption, delivery, and engineer-note context using Sales Cloud, SPA, and relevant…

Context cost
4.7k tokensestimated from the bundle, loaded when it triggers
Bundle
2 files · 18.7 kBtext throughout, nothing executable
Licence
not declarednone named by its author
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Review and update account pipeline, workload, consumption, delivery, and engineer-note context using Sales Cloud, SPA, and relevant Outlook email and calendar evidence. Use when an account review should be completed from those sources.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

productivity

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md17.0 kB · preview
--- name: account-pipeline-eca ---
6# Account Pipeline ECA
7
8Use the account name as the primary selector. This is a Sales Cloud and SPA-first alternative for account review; do not require access to other internal pipeline or engagement applications. Never update a record until the account identity and target opportunity or workload are unambiguous.
9
10## Workflow
11
121. Confirm the requested scope: review-only, proposed changes, or apply updates. Treat an unspecified request as **review and propose**; do not write to Sales Cloud or other live systems without explicit authorization.
132. Start Sales Cloud opportunity discovery at https://eeho.fa.us2.oraclecloud.com/fscmUI/redwood/cx-sales/application/container/opportunities/opportunities-list. Search the account name and disambiguate duplicates using global ultimate, territory, opportunity name, owner, and opportunity number. Remove inherited keyword, status, probability, close-date, or record-set filters that could omit account opportunities, unless the user explicitly asks for that scope.
143. Open each returned opportunity from its Sales Cloud result. Treat https://eeho.fa.us2.oraclecloud.com/fscmUI/redwood/cx-sales/application/container/opportunities/opportunities-detail?id=<opportunity-record-id>&puid=<opportunity-id>&view=foldout as the opportunity main page. Use the exact id and puid returned by Sales Cloud; do not guess either value. Use the edit route only when an approved workflow requires it.
15 - When the opportunity's **Details** view exposes a **Customer 360** link, use it to open the registry-specific SPA customer view. Prefer this routed link over a SPA **My Accounts** text search when the latter returns a stale or mismatched row. From Customer 360, open the applicable UCM plan, then **Plan Details**. Treat displayed registry and plan identifiers as record-specific; never reuse them for a different account.
164. For every material opportunity, review the current engineer note, sales stage, status, probability, account, amount, close date, revenue type, product or booking lines, workload labels, team, and activity history. Record the latest material activity date and summarize the current technical milestone, blocker, owner, and next step. Flag stale activity or a missing current engineer note as a follow-up risk.
175. Capture all available Sales Cloud product or booking-line information, including Universal Credits multicloud product type, amount, order number, contract or order reference, and new versus existing-commit context. Do not infer a product, booking, workload, or delivery status from an opportunity amount alone. If separate workload rows, consumption start, ramp, delivery owner, or SE hours are not exposed, report them as [VERIFY] rather than inventing equivalents.
186. For each material opportunity, use SPA at https://spa.oracle.com/, then navigate through **Customer 360 → OCI Consumption**. Do not treat the Customer 360 landing page as the SPA review. In the plan list, select **All Products** when necessary to expose every plan for the customer and inventory every returned plan, including active and terminated plans. Open **Plan Details** for each active UCM plan. Record active-line and projected status, projected overage month, start and end dates, committed credits, consumed amount, order number, contract ID, and most recent data date when available. For terminated plans, record status, term, and whether any current action remains. Do not open the SPA **Workloads** tab unless the user explicitly requests it.
197. When SPA returns a UCM plan for the same account or registry ID, record it as a **working association — [VERIFY]**. Confirm an opportunity-to-plan relationship only when the booked Sales Cloud line and SPA Plan Details share an order number or contract ID. Do not infer linkage from a matching amount, timing, account, or product alone. Distinguish customer-wide plan inventory from opportunity linkage: a plan can be valid for the account without being confirmed against the opportunity under review. If identifiers are unavailable, request confirmation from the booking, Sales Ops, or SPA plan owner.
208. When preparing or updating an Engineer Note, gather relevant Outlook context. Search the accessible mailbox across folders for the account name and aliases, opportunity ID, workload or project terms, and material stakeholders. Search the Outlook calendar for matching meetings and retrieve selected event details before relying on them. Use only evidence material to the opportunity; do not reproduce emails or unnecessary recipient details.
219. Reconcile Sales Cloud, SPA, email, and calendar evidence. Derive delivery and engagement context from dated Sales Cloud activities, Engineer Notes, opportunity team, product or booking lines, SPA plan details, and Outlook evidence. Record engagement owner, assigned engineers, milestones, service requests, heat or health, final readout, go-live, handoff, and detailed progress only when directly exposed by those sources; otherwise label the missing evidence [VERIFY] and identify the owner who can confirm it.
2210. Assess each workload or product-backed forecast using [references/pipeline-rules.md](references/pipeline-rules.md). Validate amount, consumption start, ramp months, status, and probability when the source exposes them. Treat missing fields, stale notes, blank workload labels, same-day close and consumption-start dates, missing ramps, and stage/probability mismatch as cleanup candidates. Keep booking forecasts and workload forecasts distinct.
2311. For a review, provide an account summary, recommended corrections, dependencies, and risks. Use source values for quarterly or annual consumption position, qualified-pipeline coverage, and forecast assumptions only where Sales Cloud or SPA exposes the required values. Otherwise state the limitation as [VERIFY]; do not calculate or imply a gap.
2412. For approved updates, edit only the smallest necessary set of live Sales Cloud records. Re-open the source record and verify persistence. State exactly what changed.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md2,447 words
Files2
Licencenot declared
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈70
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
4,605
on trigger
The instruction body and 1 supporting file, read only when the skill fires.
2.3%
of a 200k window
Ten skills this size would take about 23% of the window before you open a file.
050k100k150k200k context window

4.7k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

2 files, 18.7 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md17.0 kB
  • references/pipeline-rules.md1.7 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 2 files you can review in full before installing.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Account Pipeline ECA · 4.7k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/account-pipeline-eca/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/account-pipeline-eca" ] && { [ ! -e .claude/skills/account-pipeline-eca ] || { mv .claude/skills/account-pipeline-eca "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/account-pipeline-eca" .claude/skills/ && echo "Installed .claude/skills/account-pipeline-eca"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add oraclecodexcellent/account-pipeline-eca

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/account-pipeline-eca/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/account-pipeline-eca/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/account-pipeline-eca" ] && { [ ! -e ~/.claude/skills/account-pipeline-eca ] || { mv ~/.claude/skills/account-pipeline-eca "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/account-pipeline-eca" ~/.claude/skills/ && echo "Installed ~/.claude/skills/account-pipeline-eca" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/account-pipeline-eca/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referenceoraclecodexcellent/account-pipeline-eca

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

OR
OracleCodexcellent

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill