plugins/cashflow/skills/recap/SKILL.md
Triggered by "monthly recap", "how did I do this month", "spending summary", "financial review", "weekly recap", "quarterly review", "year in review"
npx skillsauth add davepoon/buildwithclaude recapInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generate a narrative financial review for any time period.
Determine the period. Parse $ARGUMENTS for the time span:
Fetch summary data. Call the query MCP tool with compare: "prior_period":
{ "period": "<detected_period>", "compare": "prior_period", "include": ["ratios", "anomalies", "accounts"] }
(Use start/end if a specific date range was requested.)
Fetch year-ago comparison. For anything other than year-over-year, also fetch the same period from a year ago to account for seasonality:
{ "start": "<same_period_last_year_start>", "end": "<same_period_last_year_end>", "include": ["ratios"] }
For example, if reviewing February 2026, also fetch February 2025.
Fetch recurring bills. Call the query MCP tool:
{ "recurring": true }
Synthesize a narrative recap covering:
Tone: Stick to the facts. Report what happened without judgement — no "great job" or "you need to cut back." Just clear, plain-language observations. Skip categories with trivial amounts.
tools
Assesses the current state of the startup project and recommends what to focus on next. Use when there is a need or a question from the user to understand what the next steps are or what to focus on next.
data-ai
Use at the start of any conversation about a startup idea, product validation, founder strategy, or work inside a `startup/` workspace. Establishes file conventions, voice-input handling, subagent dispatch rules, and how to update each artifact safely. Activate before invoking any other startup-superpowers skill.
tools
Manages the founder's survey-based validation — crafting the right questions, deploying a survey to the internet, and analyzing results against hypotheses. Use when the founder wants to run a survey, create survey questions, validate hypotheses at scale, check how a survey is going, understand whether a survey is the right tool right now, or deploy a question set to get quantitative signal. Also bring this up if you believe that creating a survey to collect quantitative evidence may be useful at this point.
development
Guides the founder through designing and optionally building the simplest MVP or prototype that validates their current hypotheses. Use when the founder wants to build something to test assumptions, discusses what to build next, wants to interpret results from a live MVP, or is deciding whether the current approach is still right. Also use when a founder proposes something to build — the skill will check whether the proposed form is the simplest thing that generates honest signal.