MCPInstall

tres-recon-gaps

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.

Installs
49
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/anthropics/claude-plugins-community --skill tres-recon-gaps
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads tres-recon-gaps automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

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.

FAQ

What does the tres-recon-gaps skill do?

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.

How do I install tres-recon-gaps?

Run npx skills add https://github.com/anthropics/claude-plugins-community --skill tres-recon-gaps in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/tres-recon-gaps/ (personal) or .claude/skills/tres-recon-gaps/ (project).

Which AI agents can use tres-recon-gaps?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is tres-recon-gaps safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains tres-recon-gaps?

It is published by anthropics in anthropics/claude-plugins-community. It has 49 recorded installs.

More from anthropics/claude-plugins-community

View all →

eli5

anthropics/claude-plugins-community

Explain a topic like I'm a 5 year old. Use when the user types /eli5 or asks for a dead-simple picture explainer of how something works.

1.9K installs

html-plan

anthropics/claude-plugins-community

Write an implementation plan as one interactive HTML page - a tree of claims (why › what › how › where), each proved by one exhibit (UI mockup, state machine, call stack, schema or code), with the decisions the user has to make placed on the claim they change. Use when the user types /html-plan, or asks for a plan, RFC or design before building something that touches more than a couple of files.

Frontend & Design112 installs

quickdesign

anthropics/claude-plugins-community

Use the quickdesign CLI to generate AI media — UGC promo videos, image edits, product creatives, video upscales — through Seedance, Kling, Sora2, Nano Banana, and GPT Image. Invoke this skill whenever the user asks for a talking-avatar video, multi-segment ad / promo / explainer, image edit (object swap, angle change, state change), product photoshoot, or video upscale via QuickDesign.

Media & Creative66 installs

tres-cost-basis

anthropics/claude-plugins-community

Manage cost basis calculation in TRES Finance: check status, view/change strategy (FIFO, LIFO, AVG, MAXGAINS, MAXLOSSES, FIFOIMPAIRMENT), trigger recalculation, review financial issues, manage reevaluations/impairments, set bulk fiat prices, configure spec-ID lot disposal rules, view per-asset cost basis results, and export cost basis reports. Trigger this skill whenever the user asks about cost basis, gains/losses, realized gains, unrealized gains, COGS, inventory lots, tax lots, cost basis strategy, reevaluation, impairment, fiat value override, spec-ID rules, financial issues (negative balance, missing fiat), or anything related to how their crypto assets are costed. Also trigger when the user says "calculate cost basis", "what is my cost basis strategy", "show me financial issues", "create a reevaluation", "run cost basis", "change strategy to LIFO", or similar.

tres-asset-balance-validation

anthropics/claude-plugins-community

Validate wallet balances in TRES Finance against DeBank and generate a discrepancy report. Use this skill whenever the user asks to validate, verify, cross-check, or audit their TRES balances against on-chain data or DeBank. Also trigger when the user asks if their balances are correct or wants to see discrepancies. Only EVM-compatible wallets are supported.

Security51 installs

tres-report-advisor

anthropics/claude-plugins-community

Recommend the right TRES Finance report for any user question. Trigger this skill whenever a user asks which report to use, what report contains certain data, how to get specific information out of TRES, or compares two reports. Also trigger when the user describes a goal (e.g. "month-end close", "auditor needs proof", "tax filing", "reconciliation") without naming a specific report. Trigger phrases include "which report", "what report", "how do I export", "where can I find", "I need a report for", "what's the difference between", "best report for", "auditor asked for", or any question about getting data out of TRES Finance.

Docs & Writing50 installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs