Agent skill

Recap

by davepoon in davepoon/buildwithclaude

Triggered by "monthly recap", "how did I do this month", "spending summary", "financial review", "weekly recap", "quarterly review", "year in review"

MITAuto-check passed

Install Recap

skills CLI
$ npx skills add davepoon/buildwithclaude --skill recap -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install davepoon/buildwithclaude recap --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/davepoon/buildwithclaude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/cashflow/skills/recap .claude/skills/recap && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
recap
GitHub stars
3.6k
Used in
1 other repo
Token cost
~550 tokens
SKILL.md length
233 words
Files
1
Skills in repo
245
Repo updated
First seen
Licence
MIT

At a glance

Triggered by "monthly recap", "how did I do this month", "spending summary", "financial review", "weekly recap", "quarterly review", "year in review"

  • Works in 6 steps: Determine the period. Parse $ARGUMENTS… → Fetch summary data. Call the query MCP… → Fetch year-ago comparison. For anything… → …
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Recap is an agent skill from davepoon/buildwithclaude. Triggered by "monthly recap", "how did I do this month", "spending summary", "financial review", "weekly recap", "quarterly review", "year in review"

Its SKILL.md is about 550 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw. The licence is MIT.

Example prompts

  • “monthly recap”
  • “how did I do this month”
  • “spending summary”
  • “/recap”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Determine the period. Parse $ARGUMENTS for the time span
  2. Fetch summary data. Call the query MCP tool with compare: "prior_period"
  3. Fetch year-ago comparison. For anything other than year-over-year, also fetch the same period from a year ago to account for seasonality
  4. Fetch recurring bills. Call the query MCP tool
  5. Synthesize a narrative recap covering
  6. Tone: Stick to the facts. Report what happened without judgement — no "great job" or "you need to cut back." Just clear, plain-language…

What it can do on your machine

Read from SKILL.md and the folder at commit 10bfc43. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Recap loads about 550 tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 233 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~550

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from davepoon/buildwithclaude at commit 10bfc43, republished under its MIT licence (© davepoon). 233 words, ~550 tokens.

Download SKILL.mdSave it as .claude/skills/recap/SKILL.md (or your agent's skills folder).
name
recap
description
Triggered by "monthly recap", "how did I do this month", "spending summary", "financial review", "weekly recap", "quarterly review", "year in review"

Financial Recap

Generate a narrative financial review for any time period.

Workflow

  1. Determine the period. Parse $ARGUMENTS for the time span:

    • "this week", "last week" → weekly
    • "this month", "january", "jan 2025", "2025-01" → monthly (default if no argument)
    • "this quarter", "Q1", "Q1 2025" → quarterly
    • "this year", "2025", "year in review" → yearly
    • Any explicit date range works too
  2. Fetch summary data. Call the query MCP tool with compare: "prior_period":

    json
    { "period": "<detected_period>", "compare": "prior_period", "include": ["ratios", "anomalies", "accounts"] }

    (Use start/end if a specific date range was requested.)

  3. Fetch year-ago comparison. For anything other than year-over-year, also fetch the same period from a year ago to account for seasonality:

    json
    { "start": "<same_period_last_year_start>", "end": "<same_period_last_year_end>", "include": ["ratios"] }

    For example, if reviewing February 2026, also fetch February 2025.

  4. Fetch recurring bills. Call the query MCP tool:

    json
    { "recurring": true }
  5. Synthesize a narrative recap covering:

    • Headline numbers: total income, total expenses, net cash flow, savings rate
    • vs. prior period: changes from the immediately preceding period (last week, last month, etc.)
    • vs. same period last year: seasonal context — note whether changes are normal for this time of year or unusual (skip this section for year-over-year recaps)
    • Anomalies: unusual transactions or spending spikes
    • Recurring bills: new, changed, or cancelled subscriptions/bills
    • Key ratios: any ratios returned in the summary (e.g. expense-to-income)
    • Account balances: current balances and changes
  6. 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.

© davepoon, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/cashflow/skills/recap of davepoon/buildwithclaude.

Open the folder on GitHubat commit 10bfc43

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in davepoon/buildwithclaude, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Recap next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Recap compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Recap this skilldavepoon/buildwithclaude3.6k1 repos~550Automated safety check: PassMIT
Session Recaprohitg00/agentmemory29k—~510Automated safety check: PassApache-2.0
Monthly Closing Statementssickn33/agentic-awesome-skills47k1 repos~6.2kAutomated safety check: PassMIT
Monthly Review and Planningballred/obsidian-claude-pkm1.9k—~1.4kAutomated safety check: PassMIT
Recipe Copy Sheet For New Monthgoogleworkspace/cli31k—~251Automated safety check: PassApache-2.0
Visual RecapBuilderIO/skills4.5k—~8.4kAutomated safety check: NotesMIT

Similar skills

  • Session Recap

    rohitg00/agentmemory

    Summarizes recent agent sessions for the current project by date, with each session's title, status, observation count and top highlights from memory.

    29k GitHub stars~510 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Monthly Closing Statements

    sickn33/agentic-awesome-skills

    Monthly closing register: period dates, cash/bank/party/inventory/TDS reconciliation flags, profit, receivables, payables, working capital, open adjustments and reviewer.

    47k GitHub starsUsed in 1 repo~6.2k tokens
    Business, Finance & HRAuto-check passed
  • Monthly Review and Planning

    ballred/obsidian-claude-pkm

    Runs a monthly review in an Obsidian vault: rolls up weekly reviews, checks quarterly milestones against yearly goals and sets next month's focus.

    1.9k GitHub stars~1.4k tokensUpdated 7 mo ago
    Knowledge ManagementAuto-check passed
  • Duplicate a Google Sheets template tab for a new month of tracking.

    31k GitHub stars~251 tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Visual Recap

    BuilderIO/skills

    Turn a PR, branch, commit, or git diff into an interactive visual recap with diagrams, file maps, API/schema summaries, annotated diffs, and focused review notes.

    4.5k GitHub stars~8.4k tokensUpdated today
    DevelopmentAuto-check: notes
  • Recap

    sharpdeveye/maestro

    Quick summary of the last session — commands run, files changed, and what to do next.

    592 GitHub stars~591 tokensUpdated 5 mo ago
    MobileAuto-check passed

More from davepoon/buildwithclaude

All 245 skills in this repo
  • Qwen Vision

    davepoon/buildwithclaude

    A skill your agent uses when the user asks to "analyze video", "watch this video", "what happens in this video", "describe this clip", "review this footage", "classify these videos", "compare…

    3.6k GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed
  • Hard Predict Future

    davepoon/buildwithclaude

    Activate this agent for any future-oriented question that requires deep quantitative analysis, historical precedents, and structured scenario planning.

    3.6k GitHub starsUsed in 1 repo~4.2k tokens
    Auto-check passed
  • iOS Hig Design Guide

    davepoon/buildwithclaude

    Build, update, and apply iOS design specifications using Apple Human Interface Guidelines (HIG) source data.

    3.6k GitHub stars~735 tokensUpdated yesterday
    Auto-check passed
  • Video Downloader

    davepoon/buildwithclaude

    Download YouTube videos with customizable quality and format options.

    3.6k GitHub starsUsed in 1 repo~871 tokens
    Auto-check passed
  • Atlas Cloud Media

    davepoon/buildwithclaude

    Discover Atlas Cloud image and video models, inspect their live schemas, and submit one confirmed media generation request with bounded GET polling.

    3.6k GitHub stars~852 tokensUpdated yesterday
    Auto-check passed
  • Slack Gif Creator

    davepoon/buildwithclaude

    Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives.

    3.6k GitHub starsUsed in 12 repos~4.3k tokens
    Auto-check passed

Questions about Recap

What does Recap do?

Triggered by "monthly recap", "how did I do this month", "spending summary", "financial review", "weekly recap", "quarterly review", "year in review". Recap is an agent skill from davepoon/buildwithclaude.

How do I install Recap in Claude Code?

Run `npx skills add davepoon/buildwithclaude --skill recap -a claude-code`. Or copy the skill folder (plugins/cashflow/skills/recap in davepoon/buildwithclaude) into .claude/skills/recap in your project. Claude Code loads it when a task matches its description.

How do I install Recap in Codex?

Run `npx skills add davepoon/buildwithclaude --skill recap -a codex`. Or copy the skill folder (plugins/cashflow/skills/recap in davepoon/buildwithclaude) into .agents/skills/recap in your project. Codex loads it when a task matches its description.

Can I use Recap in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add davepoon/buildwithclaude --skill recap -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/recap, .gemini/skills/recap, .github/skills/recap and .opencode/skills/recap in your project.

What does Recap need to run?

SKILL.md names no scripts, command-line tools or credentials: Recap is instructions for the agent only.

Does Recap access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Recap safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Recap use?

Recap is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Recap use?

About 550 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Recap?

Skills that share tags, products or a category with Recap: Session Recap (rohitg00/agentmemory, 29k stars), Monthly Closing Statements (sickn33/agentic-awesome-skills, 47k stars), Monthly Review and Planning (ballred/obsidian-claude-pkm, 1.9k stars) and Recipe Copy Sheet For New Month (googleworkspace/cli, 31k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Recap?

davepoon (a GitHub user) maintains it in davepoon/buildwithclaude, which has 3,604 GitHub stars. The repository holds 245 skills in this directory. The repository was last updated on October 6, 2026.

Source: davepoon/buildwithclaude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.