More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Localization Placeholder & Tag QA Checker

    1

    Check localization CSVs for broken placeholders, tags, numbers, URLs, glossary terms and repeated-string mismatches before release.

    Free

    2 usesSecurity scanned
    Localization Placeholder & Tag QA Checker

    Localization Placeholder & Tag QA Checker

    Example session with this skill installed

    Use Localization Placeholder & Consistency QA Pack on the authorized segments.csv, glossary.csv and policy.json files in this working folder. Write a fresh packet to ./localization-qa-packet, summarize all BLOCK and REVIEW items, and do not translate or overwrite any source file.

    • Read your context and instructions
    • Compiled the localization placeholder
    • Generated the data export

    Localization QA result

    Status: BLOCK
    Run ID: 24ee3711edb2b2be49be

    The deterministic review processed 2 supplied segments. One segment is blocked and one requires owner review. Resolve the BLOCK finding before release; send the REVIEW item to the localization owner.

    SegmentFileLocaleDecisionReason codes
    s1app.jsonfr-FRBLOCKNUMBER_MISMATCH; PLACEHOLDER_MISMATCH
    s2app.jsonfr-FRREVIEWURL_MISMATCH

    Packet created

    • result.json
    • segment-findings.csv
    • placeholder-mismatches.csv
    • glossary-findings.csv
    • issues.jsonl
    • LOCALIZATION_QA.md
    • evidence-receipt.json

    Next steps

    1. Restore the supplied source placeholder and confirm the intended numeric token in segment s1.
    2. Ask the localization owner to review the literal URL difference in segment s2.
    3. Rerun into a new empty output directory and compare the new evidence receipt.

    Scope

    These checks are structural. They do not translate text or judge meaning, fluency, spelling or locale grammar. Number and URL comparisons use the literal tokens supplied in the input files.

    segment-findings.csv

    CSV · data export

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    A translated string can look correct while silently dropping a placeholder, changing a tag or disagreeing with the same source text elsewhere. This local checker reviews supplied localization CSVs and separates placeholder, glossary and consistency findings into a deterministic release-review packet. It does not translate text or judge linguistic quality.

    What it does

    This downloadable local package checks authorized software-localization CSV files for placeholder, tag, number, URL, glossary and repeated-string consistency before release.

    It includes an installable Python CLI, a local stdio MCP adapter and a companion Agent Skill. One run creates result.json, segment-findings.csv, placeholder-mismatches.csv, glossary-findings.csv, issues.jsonl, LOCALIZATION_QA.md and evidence-receipt.json.

    Why it is reliable

    • Deterministic checks with fixed schemas and rules.
    • Rejects unsafe paths and malformed inputs.
    • Never overwrites an existing packet.
    • Escapes formula-active CSV cells.
    • Binds inputs and outputs with SHA-256.

    Best for

    • Localization freelancers, software teams and agencies checking translated UI strings.
    • Teams that need reproducible QA evidence before release.
    • Agencies preparing a reviewable client handoff.

    Requirements

    Windows 11 and Python 3.11–3.14. Optional mcp==2.2.0 for the local MCP adapter.

    Limitations

    It does not translate, judge linguistic correctness, spell-check, validate locale grammar, write back to CAT tools or approve a release. Processing stays local; no API key, login, upload, telemetry or live external action is included.

    Does not translate text, judge linguistic correctness, spell-check, validate locale grammar, write back to CAT tools or approve a release. Requires buyer-supplied local CSV and JSON inputs. No external APIs, accounts or live network checks.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 2 months ago

    • Free with an Agensi account

    Requires

    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    **/segments.csv
    **/glossary.csv
    **/policy.json
    **/localization-qa-packet/**

    Reads only operator-selected CSV and JSON inputs under a declared working directory and writes a new result packet. No network access, credential access or environment-variable collection.

    Listed2 months ago

    What's inside

    Frequently Asked Questions

    This tool automates the detection of technical errors in localized CSV files, such as mismatched placeholders, broken URLs, and inconsistent glossary terms that often lead to software crashes or UI breaks. It solves the manual burden of verifying that translated strings maintain the functional integrity of the original code.

    The package includes a local MCP (Model Context Protocol) adapter, making it compatible with AI agents like Claude Desktop and other MCP-enabled environments. It also functions as a standalone Python CLI for teams who prefer manual terminal execution or scripted workflows.

    Your purchase includes the core Python CLI package, a companion Agent Skill configuration, and the local MCP adapter. You also receive a comprehensive set of output templates for generating QA evidence, including CSV findings and SHA-256 verified reports.

    No, this is a deterministic validation tool that runs entirely on your local Windows machine. It does not require an API key, performs no external telemetry, and does not send your sensitive translation data to any cloud service or LLM.

    This pack is designed for Windows 11 environments running Python 3.11 through 3.14. It is optimized for software localization workflows where strings are managed in structured CSV formats.

    The tool is strictly for quality assurance and consistency checking; it does not perform machine translation, spell-checking, or grammar correction. It identifies technical mismatches between source and target strings but does not modify your original files or write back to CAT tools.

    New in Translation & Localization