본문으로 건너뛰기
cccskills
무료GitHub에 공개

tres-recon-gaps

Inspect and resolve differences between ledger and on-chain balances in TRES Finance. View gaps by date and asset in an HTML dashboard with fiat values, then use copied prompts to create one-time adjustments or recurring gap-fill rules.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Query, display, and resolve reconciliation gaps from the TRES Finance MCP connector. Trigger this skill ONLY when the user explicitly requests to view or close reconciliation gaps — for example: "show me the reconciliation gaps", "close the recon gaps", "view gaps for today", "plug the reconciliation gaps for ETH", "fix the gaps for USDC and BTC". Do NOT trigger for general balance queries, transaction history, or ledger browsing. Covers the full workflow: confirming the target date, optionally filtering by asset, fetching gap data, enriching with fiat and on-chain balances, rendering an HTML dashboard where each gap row has copy-prompt buttons (Plug / Auto-fill) — clicking copies a ready-to-paste Claude prompt for that gap. The user pastes it in the chat and Claude executes the action. Ends with a data collect once the user is done.

설치 방법 보기

이럴 때 유용합니다

  • Review reconciliation gaps for a specific date
  • Filter balance differences to ETH or USDC
  • Create a one-time adjustment for a selected gap
  • Set up recurring gap fills and trigger a data refresh

포함된 파일(2)

  • SKILL.md10.0 KB
  • references/html-template-notes.md4.1 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

TRES Reconciliation Gaps Skill

End-to-end workflow for surfacing, analyzing, and resolving reconciliation gaps in TRES Finance.


Pre-flight: confirm date and asset scope

Before fetching any data, confirm two things with the user:

1. Target date

The reconciliation queries are scoped to a specific date (the endDate parameter).

  • If the user explicitly stated a date — use it.
  • If the user did not mention a date — assume today's date and inform them:

    "I'll fetch reconciliation gaps for today (YYYY-MM-DD). Let me know if you want a different date."

Use ISO format YYYY-MM-DD throughout.

2. Asset filter (optional)

  • If the user named specific assets (e.g. "for ETH and USDC", "just BTC") — note them. After fetching, filter the results to only those asset.symbol values before displaying.
  • If the user did not specify assets — fetch and display all gaps.

Step 1 — Fetch reconciliation gaps

Use the reconciliation query. Always pass the confirmed endDate. Fetch up to 200 at a time.

query GetReconciliationGaps($limit: Int, $offset: Int, $endDate: Date) {
  reconciliation(limit: $limit, offset: $offset, endDate: $endDate) {
    totalCount
    results {
      id
      amount
      calculatedBalance
      state
      status
      gap
      belongsTo {
        id
        name
        identifier
      }
      asset {
        key
        identifier
        symbol
        platform
      }
      pendingTransactionsCount
      pendingTransactionsTotalAmount
    }
  }
}

Variables: {"limit": 200, "offset": 0, "endDate": "<confirmed-date>"}

Note: gap = calculatedBalance − historicalBalance. Positive means the ledger has more than on-chain; negative means the ledger has less.

If the user requested specific assets, filter the results now: keep only rows where asset.symbol matches the requested symbols (case-insensitive).


Step 2 — Enrich with fiat values and on-chain balances

Take all IDs from the (filtered) Step 1 results and query assetBalance:

query GetAssetBalancesWithFiat($ids: [String], $limit: Int, $currency: String) {
  assetBalance(id_In: $ids, limit: $limit, currency: $currency, excludeUnderDelegation: true) {
    totalCount
    results {
      id
      calculatedBalance
      historicalBalance
      reconciliation
      fiatValue {
        value
        unitPrice
        fiatCurrency
      }
      belongsTo {
        id
        name
        identifier
      }
      asset {
        key
        symbol
        platform
        identifier
      }
    }
  }
}

Variables: {"currency": "usd", "ids": ["<id1>", "<id2>", ...], "limit": 200}

Important: id_In expects [String], not [ID].

Compute for each row:

fiatGap = reconciliation (token gap) × fiatValue.unitPrice

Step 3 — Display: always render the HTML dashboard

Always generate a standalone .html file as the primary output — do not fall back to an inline widget.

Read references/html-template-notes.md for the full visual spec (fonts, colors, layout, column widths, modal behavior, API call mechanism).

Key requirements for the generated file:

  • Dark financial dashboard aesthetic (spec in reference file)
  • Sticky header showing the target date and a refresh timestamp badge
  • 5 summary metric cards: net fiat gap, positive gap count, negative gap count, asset group count, pending tx count
  • If an asset filter was applied, show a visible filter badge in the toolbar (e.g. Filtered: ETH, USDC)
  • Search + direction filter + platform filter toolbar
  • Asset-grouped collapsible sections, sorted by absolute net fiat gap descending
  • Full column set per row — last column has two copy-prompt buttons: ↳ Plug (blue) and ⟳ Auto-fill (purple)
  • Clicking either button copies a ready-to-paste prompt to clipboard and shows a toast: "Prompt copied — paste it in the Claude chat to resolve this gap."
  • No HTTP requests — the HTML is a pure display interface; all mutations happen in Claude after the user pastes the prompt

After generating the file, present it to the user with present_files.


Step 4 — Actions (plug-once and auto-fill)

The user triggers actions by copying a prompt from the HTML dashboard and pasting it into the Claude chat. When Claude receives one of these prompts, execute the corresponding mutation immediately — no further confirmation needed (the user already chose the action in the dashboard).

One-time plug (createPlug)

mutation CreatePlug(
  $hash: String!
  $platform: Platform!
  $timestamp: DateTime!
  $belongsToId: ID!
  $assetId: ID!
  $assetIdentifier: String!
  $amount: Float!
  $direction: Direction!
  $thirdPartyIdentifier: String!
) {
  createPlug(
    hash: $hash
    platform: $platform
    timestamp: $timestamp
    belongsToId: $belongsToId
    assetId: $assetId
    assetIdentifier: $assetIdentifier
    amount: $amount
    direction: $direction
    thirdPartyIdentifier: $thirdPartyIdentifier
  ) {
    transaction { id identifier platform timestamp }
  }
}

Variable mapping:

FieldValue
hashplug_<assetId>_<walletId>_<timestamp_ms>
platformasset.platform
timestampnew Date().toISOString()
belongsToIdbelongsTo.id
assetIdasset.key
assetIdentifierasset.identifier (use "native" for native assets like ETH/AVAX)
amountMath.abs(gap)
directiongap > 0 ? "INFLOW" : "OUTFLOW"
thirdPartyIdentifierbelongsTo.identifier (wallet address)

Auto gap-fill rule (createReconciliationGapFillRule)

mutation CreateGapFillRule(
  $name: String!
  $assetId: String!
  $internalAccountId: Int!
  $interval: Interval!
  $startDate: Date!
  $endDate: Date!
) {
  createReconciliationGapFillRule(
    name: $name
    assetId: $assetId
    internalAccountId: $internalAccountId
    interval: $interval
    startDate: $startDate
    endDate: $endDate
  ) {
    success
    message
    ruleId
  }
}

Variable mapping:

FieldValue
nameUser-editable rule name (pre-filled: Auto gap-fill · <asset> · <wallet>)
assetIdasset.key
internalAccountIdparseInt(belongsTo.id) — must be Int!
intervalDAILY / WEEKLY / MONTHLY
startDateISO date string, e.g. "2026-04-07"
endDateISO date string (default: 2 years from today)

Step 5 — Run data collect after plugs are done

Once the user indicates they are finished adding plugs (e.g. "done", "that's all", "looks good"), run a data collect to sync the updated state.

Use the triggerDataCollect mutation (or equivalent — introspect with get_schema_summary if needed):

mutation TriggerDataCollect {
  triggerDataCollect {
    success
    message
  }
}

After it completes, inform the user:

"Data collect triggered — TRES will now sync the latest on-chain balances. The reconciliation gaps should update shortly."


Grouping and sorting logic

Default grouping: by asset symbol

  • Group all rows sharing the same asset.symbol into one group
  • Net fiat gap shown per group header
  • Sort groups by absolute net fiat gap descending
  • Sort rows within each group by absolute fiat gap descending

Alternative: group by wallet (if user requests it)

  • Group by belongsTo.identifier
  • Same sorting logic

Always order by fiat gap, not token gap.


Number formatting conventions

// Fiat values
≥ $1M  → "$X.XXXM"
≥ $1K  → "$X.XXK"
< $1K  → "$X.XX"

// Token quantities
≥ 1B   → "X.XXXB"
≥ 1M   → "X.XXXM"
≥ 1K   → "X.XXXK"
< 1K   → up to 6 significant figures, trim trailing zeros

// Signs
Positive gaps: "+" prefix
Negative gaps: "−" (minus sign, not hyphen)
No sign:       absolute values (on-chain bal, calculated bal)

Common edge cases

SituationHandling
unitPrice = 0Show "—" for fiat gap; token gap still displays
historicalBalance is negativeDisplay as-is; flag visually if extreme
pendingTransactionsCount > 0Show amber warning badge — pending txs may reduce the gap once confirmed
Very large token gaps with tiny fiat valueStill show; sort by fiat means they appear near bottom
gap field timeouts on large datasetsUse assetBalance.reconciliation field instead (same value, more reliable)
Asset filter yields zero rowsInform the user: "No gaps found for [assets] on [date]"

Key schema facts (verified)

  • reconciliation query — has endDate parameter; returns gap and basic balance fields
  • assetBalance query — returns historicalBalance, reconciliation (= gap), and fiatValue { value, unitPrice }; prefer for enriched data
  • assetBalance(id_In: [String]) — note [String] not [ID]
  • createPlug — belongsToId is ID!, assetId is ID! (pass the asset key string)
  • createReconciliationGapFillRule — internalAccountId is Int!; assetId is String!; interval is Interval! enum
  • Platform enum values: ETHEREUM, BASE, ARBITRUM, OPTIMISM, POLYGON, AVAX, AVALANCHE_P_CHAIN, MANTRA, etc.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

eli5

무료

Turn a topic into a simple HTML explainer with large pictures and few words. It is designed for readers with no prior knowledge who want a basic visual explanation of how something works.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Getting a visual introduction to an unfamiliar topic
  • Explaining how something works in simple terms
  • Requesting an explanation with fewer words
anthropics/claude-plugins-community4.7천2026년 10월 21일 업데이트

html-plan

무료

Create an interactive HTML implementation plan that connects proposed behavior to mockups, code, and data structures. Readers can explore details, choose options, edit schemas, and return comments before development starts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Reviewing a feature plan before development
  • Collecting decisions on implementation options
  • Connecting proposed behavior to code locations
anthropics/claude-plugins-community4.7천2026년 10월 21일 업데이트

Create talking-avatar ads, product images, and promotional videos through the quickdesign CLI. Use reference images for edits and compositions, maintain a consistent voice across video segments, and finish videos with captions or higher resolution.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Create a product ad with a talking avatar
  • Build a multi-segment explainer with a consistent voice
  • Edit product images using multiple references
anthropics/claude-plugins-community4.7천2026년 10월 21일 업데이트

Audit Playwright automated test code using context from TestDino. The skill guides a review that produces a local Markdown report, submits findings with a score, and lets you retrieve previously submitted audits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Requesting a TestDino audit of Playwright tests
  • Saving test audit findings in Markdown
  • Submitting a scored audit report
anthropics/claude-plugins-community4.7천2026년 10월 21일 업데이트

Check the TestDino connection and personal access token, then discover accessible organizations, projects, and available modules. Use the results to identify the correct projectId before starting project-specific work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Check the TestDino connection
  • Validate a personal access token
  • Find accessible organizations and projects
anthropics/claude-plugins-community4.7천2026년 10월 21일 업데이트

Manage manual test runs in TestDino, from finding or creating a run for a release to inspecting its cases and summary statistics. Assign individual cases and update results or elapsed time using recognizable run and case IDs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Finding manual test runs for a release
  • Creating a test run for a sprint
  • Inspecting cases and summary statistics
anthropics/claude-plugins-community4.7천2026년 10월 21일 업데이트

anthropics의 스킬 모두 보기

이 스킬의 문제 신고