Check wiki consistency

    1

    Cross-check wiki pages for conflicting claims, validate internal links, and maintain a semantic topic index.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Check wiki consistency

    Example session with this skill installed

    Run a wiki consistency check. Reconcile any new answers in QUESTIONS.md and update the index.

    • Read your context and instructions
    • Compiled the check wiki consistency

    I have completed the wiki consistency sweep. I processed 14 pages, resolved 2 conflicting claims regarding the database connection pool defaults, and updated the index.

    Wiki Consistency Report

    TaskResultDetails
    Answer Sweep1 ResolvedApplied answer for Q-042 to 2023-11-12-auth-flow.md.
    Schema Validation3 FixedCorrected date format in frontmatter for 2 pages; fixed 1 broken link.
    Discrepancy Check1 FiledConflict found between [[2023-10-01-api-specs]] and [[2023-12-05-v2-migration]].
    Index UpdateSuccessRebuilt wiki/INDEX.md with 14 active pages across 4 topics.

    Resolved Discrepancies

    • File: pages/2023-11-10-db-config.md
    • Change: Updated max_connections default from 20 to 50 to match src/config/db.json.
    • Note: Left breadcrumb in page body regarding the sync with the current codebase.

    New Questions Filed

    Q-045: Discrepancy between API V1 support end-date. pages/2023-08-01-roadmap.md says Q4, but pages/2023-12-05-v2-migration.md implies Q1 next year. Checked milestones.json but dates are ambiguous.

    Next steps

    1. Review the new Q-045 entry in wiki/QUESTIONS.md and provide the correct sunset date.
    2. Verify the updated related: frontmatter in pages/2023-11-12-auth-flow.md.
    3. Commit the changes to the wiki/ directory to sync the index.

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

    About this skill

    Internal documentation often rots faster than code. This skill acts as a consistency layer for your markdown-based project wiki, identifying conflicting claims across different pages and ensuring all metadata, links, and indexes stay synchronized. It prevents the common "stale info" problem by cross-referencing wiki content against your actual codebase and existing decision logs.

    What it does

    • Discrepancy detection scans for conflicting claims about subsystems, flags, or bugs across multiple pages.
    • Automated resolution verifies current facts against the codebase or MCPs to update outdated wiki entries.
    • Link & schema validation ensures frontmatter follows conventions and all internal [[wikilinks]] resolve, including archived pages.
    • Question management files unresolved conflicts into a tracking file for human intervention when automated logic isn't enough.
    • Index regeneration rebuilds the master index by topic and date to reflect all recent content changes.

    How it works

    1. Answer sweep reads recently answered questions and propagates those changes to the relevant pages.
    2. Cluster & cross-check groups pages by semantic similarity to find logic or factual contradictions.
    3. Source verification checks the codebase to settle discrepancies and leaves a trail of what was changed.
    4. Index reconciliation updates the main index and topic headers based on the final state of the files.

    Frameworks & tools

    This skill is designed for Markdown-based wikis using frontmatter (YAML). It expects a specific structure including wiki/pages/, wiki/archive/, and tracking files like INDEX.md and QUESTIONS.md.

    Why this beats prompting it yourself

    Generic prompts often miss circular link errors or subtle contradictions across files that aren't currently in the active context window. This skill enforces a strict multi-pass process that ensures no page is skipped and every conflict is either fixed or filed for human review.

    Use cases

    • Auditing a project wiki after a major architectural shift to catch stale documentation.
    • Syncing a developer handbook where multiple pages describe the same shared services.
    • Cleaning up internal documentation by archiving dead links and fixing broken frontmatter.

    Known limitations

    Requires a specific directory structure (wiki/pages/, wiki/INDEX.md, wiki/QUESTIONS.md). Date-based filenames must follow the YYYY-MM-DD-kebab-case.md format.

    Requires specific wiki directory structure and naming conventions. Relies on wiki/QUESTIONS.md for human-in-the-loop conflict resolution.

    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

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 20 days ago

    • Free with an Agensi account

    Permissions

    Read Files
    Write Files
    Terminal / Shell
    Listed20 days ago

    What's inside

    Frequently Asked Questions

    This skill identifies contradictory statements across multiple files, validates that all internal wikilinks and YAML frontmatter are valid, and automatically updates your master INDEX.md to reflect the latest content.

    It is designed for any AI agent that supports file-system access and Markdown processing, provided your wiki follows the YYYY-MM-DD-filename.md naming convention and uses a central 'wiki/pages/' directory.

    When the skill finds conflicting information it can't verify against the codebase, it logs the discrepancy in a 'QUESTIONS.md' file for your review rather than making an unverified guess.

    You will receive the core logic for the multi-pass consistency checks, the schema for the INDEX.md and QUESTIONS.md files, and the configuration instructions to point the skill at your local directory.

    While the skill specializes in internal consistency, it can be configured to cross-reference your source code to verify if documentation about specific flags or subsystems matches the current implementation.

    New in Technical Documentation