carta-budget-actuals
Refresh actuals in an existing Excel budget workbook from Carta MCP. TRIGGER: refresh/sync/add actuals, interleave Budget/Actual/Variance, tag-view by department/cost center. NOT: pacing, new budgets, fetch-budget, scenarios, P&L, balance sheet.
What this skill does
[PATTERN carta-writing-style v0.0.2]
[PATTERN etiquette v0.0.6]
[PATTERN text v0.0.8]
[PATTERN tables v0.0.12]
[PATTERN carta-watermark v0.0.10]
[PATTERN menus-and-flows v0.0.7]
[PATTERN base v0.1.0]
# Budget actuals
Entry point for updating actuals in an existing budget. Six references:
- [`references/add-actuals-columns.md`](references/add-actuals-columns.md) — **Layout A**: interleave Budget / Actual / Variance per month on the Budget tab (recommended for active tracking).
- [`references/add-actuals-tab.md`](references/add-actuals-tab.md) — **Layout B**: add a peer `<year> Actuals` tab alongside the Budget tab.
- [`references/refresh-existing.md`](references/refresh-existing.md) — **Layout C**: overwrite stale actuals cells in columns that already exist.
- [`references/add-period.md`](references/add-period.md) — **Layout D**: append the single next month/quarter column.
- [`references/tag-view.md`](references/tag-view.md) — **Layout E**: new tab with actuals sliced by reporting dimension (department, project code, class, etc.) and a two-row period / tag header. Only offered when the entity has tagged journal data.
- [`references/get-actuals.md`](references/get-actuals.md) — internal helper, the canonical actuals-query routine.
## UX Rules
Audience is an accountant in Excel. Plain English only. Never surface MCP
identifiers, DWH column names, UUIDs, raw JSON, SQL, or gate labels.
Currency: `$X,XXX` positive, `($X,XXX)` negative, totals bolded.
Differences are absolute. Status: ✅ Match | ⚠ Mismatch ($X diff) | ❌ Missing in Carta | ❌ Missing in Client Doc.
**Closing summary link** is a workbook citation (`<citation:Sheet!Range>`) in
Claude for Excel mode, and a `file://` path in Claude Code / Cowork mode.
**Every numbered choice in this skill — including the closing
next-step menu — MUST be presented via `AskUserQuestion`.** Never
render options as a bare code-fenced markdown list. The
`AskUserQuestion` tool is in `allowed-tools`; use it. Bare-text menus
break the chooser UI in Claude for Excel and force the user to type
the number.
## When to use
- "Refresh the actuals on my budget"
- "Pull the latest actuals into the open budget"
- "Update my budget with March numbers"
- "The actuals are stale — sync them"
- "Add next month's column to the budget"
- "Extend the budget through April"
## DO NOT use this skill for
- **Building a new budget from scratch** — use `carta-create-budget`.
- **Pulling the Carta-stored ManCo budget** — use `carta-fetch-budget`.
- **Pacing / YTD vs budget / variance / "are we on track"** — use `carta-budget-vs-actuals`.
- **What-if scenarios** — use `carta-budget-scenarios`.
- **P&L / income statement requests** — use `carta-consolidating-pnl`.
- **Balance sheet requests** — use `carta-consolidating-balance-sheet`.
---
## Gate 0 — Carta MCP environment + resolve firm
1. Call `refresh_mcp_connectors`. Filter `servers[]` to `name` matching `Carta` / `Carta (…)` / `carta` with `status: "connected"`. Drop `failed`.
2. For each connected, probe both prefix forms in parallel: `mcp__claude_ai_Carta__welcome` and `mcp__carta__welcome`. First success = `<SERVER>`.
3. **Don't call any other `mcp__<SERVER>__*` tool before `welcome`** — every command is gated.
If none connected, list `failed` connectors and stop. If multiple, default to `Carta` (production).
**Resolve firm:** if user named one → `fetch(command="contexts:list", params={"firm_name": "<entity>"})` → disambiguate via `AskUserQuestion` if multiple → `set_context(firm_id=<uuid>)`.
**DWH param-name traps:** `dwh:execute:query` takes `sql:` not `query:`. `dwh:get:table_schema` takes `table_name:` not `table:`. `format` accepts `"ndjson"` / `"markdown"`, not `"csv"`.
If no firm was named, defer to Gate 3.
---
## Gate 0.5 — Detect runtime
Detect whether this is **Claude for Excel** (workbook is open in the
add-in) or **Claude Code / Cowork** (working with a `.xlsx` file on
disk). See `carta-create-budget/SKILL.md` Gate 0.5 for the heuristic — same
rule applies here.
If unclear, ask the user via `AskUserQuestion`:
> "How are you working with the budget — inside Excel via Claude for
> Excel, or as a local .xlsx file (Claude Code / Cowork)?"
Store `<RUNTIME>` (`excel-addin` or `local-file`) for Gates 1, 4, 7, 8.
---
## Gate 1 — Where to write
Branches by `<RUNTIME>`.
**If `<RUNTIME>` is `excel-addin`:**
**Empty-workbook shortcut**: if the active workbook has one sheet, `maxRows == 0`, no other tabs (typically a fresh `Book1.xlsx`/`Sheet1`), skip the chooser. Announce the rename in one sentence — *"I'll use the empty workbook you have open and rename `Sheet1` to `<TARGET_TAB>`."* — then proceed. The chooser only exists to protect non-empty state; an empty workbook has none. The chooser still applies whenever there is data or more than one tab.
> Where should I write the updates?
- **"Update the open workbook directly — recommended"** (modify in place).
- **"Update the open workbook in a new tab"** (preserves the original).
- **"Create a brand new workbook with the updated data"**.
If user picks "update directly", confirm **which tab** explicitly. If
multiple tabs look like budgets, ask which one.
**If `<RUNTIME>` is `local-file`:**
> Where is the budget file, and where should the updated version land?
- **"Modify the file in place — recommended"** — ask for the path.
- **"Write a new file alongside the original"** — ask for the path; new file gets a `-updated` suffix by default.
If the user gave a path in the original prompt, skip the choice. Store
`<DESTINATION>` (open workbook + tab in add-in mode, or `.xlsx` path +
sheet name in local-file mode).
---
## Gate 2 — Choose the layout (always ask)
Four layouts are valid for putting actuals into a workbook, and the
same prompt can plausibly mean any of them. **Always ask the user**
how the actuals should appear — never assume from the prompt's
phrasing alone.
Use `AskUserQuestion`:
> How should the actuals appear in the workbook?
| # | Option | Reference loaded |
|---|---|---|
| 1 | **Interleave Budget / Actual / Variance columns per month** on the Budget tab ← recommended | [`add-actuals-columns.md`](references/add-actuals-columns.md) |
| 2 | **Add a separate `<year> Actuals` tab** alongside the Budget tab | [`add-actuals-tab.md`](references/add-actuals-tab.md) |
| 3 | **Refresh existing Budget / Actual / Variance cells** (the cells are there, just stale) | [`refresh-existing.md`](references/refresh-existing.md) |
| 4 | **Add only the next single period column** | [`add-period.md`](references/add-period.md) |
| 5 | **Build a tag-view tab — actuals sliced by reporting dimension** (department, project code, class, etc.) | [`tag-view.md`](references/tag-view.md) — only offered when the entity has tagged data; see Gate 2.5 |
Use the user's prompt only as a *hint* for which option to highlight —
never as authority to skip the question:
| Phrase in the prompt | Hint |
|---|---|
| "interleave", "Budget / Actual / Variance", "variance by month", "add `<year>` actuals" (no other clue) | Option 1 (also the default `← recommended`) |
| "add a tab", "track on its own tab", "separate actuals tab" | Option 2 |
| "refresh", "the actuals are stale", "pull latest", "sync" | Option 3 |
| "add next month", "extend through `<month>`", "next period" | Option 4 |
| "by department", "by tag", "by cost center", "split by", "broken down by", "by reporting tag", "by project code" | Option 5 |
**Option 5 availability**: always show Layout E in the chooser. If the user
picks it and Gate 2.5 finds no tag data on the entity, tell them in one sentence
and fall back to Layout A automatically. Do not pre-filter the chooser — the
entity name needed for the probe is not available until Gate 3.
The user's pick locks the reference to load for the rest of the
workflow. **Immediately call `read_skill` for the chosen layout — do not reconstruct from memory:**
| Layout chosen | Call |
|---|---|
| Option 1 — Interleave columns | Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.