1.7K skills · sorted by relevance
Prepare raw credit data for pre-loan modeling by checking data quality and screening variables. Review missing values, predictive usefulness, stability, noise, and correlation, then export an Excel report with organization-level statistics and cleaning results.
Reconcile accounting records with payment service payouts, identify discrepancies, possible duplicates, and missing receipts, then prepare a plain-English profit and loss summary with an Excel workbook and a one-page PDF for month-end review.
Audit GitHub issues to find open work outside a masterplan, distinguishing missing parents from missing plan ancestors. Preview or apply removal of closed issues from the hierarchy while keeping their open children connected to the plan.
Audit CRM deals for missing fields, outdated dates, inactive records, and mismatches between sales stages and supporting evidence. Receive a checklist of issues and suggested fixes, using connected CRM data or an uploaded pipeline export.
Plan, set up, audit, and debug analytics tracking with GA4 and Google Tag Manager. Define events and their parameters, configure conversion tracking, and investigate missing or duplicate data using structured checks and prioritized fixes.
Set up and authenticate lark-cli, choose between user and bot identities, and resolve missing permissions. The skill also guides authorization links, JSON result checks, update notices, and confirmation steps for high-risk operations.
Checks a local CARLA checkout for missing API documentation, outdated references, broken links, and pages absent from navigation. Produces a grouped Markdown report without building the project or running the simulator.
Audit TypeScript projects for type-only imports, duplicate imports, missing base class inheritance, and incomplete public exports through index.ts files. Apply targeted fixes in a defined order and check compilation with tsc --noEmit.
Load missing API keys, tokens, and other secrets from Infisical into shell environment variables. Retrieve individual values by environment or folder, or make project secrets available to a single command without logging their contents.
Hunt TLS/SSL and DNS misconfigurations — missing HSTS (downgrade attack), weak cipher suites, expired/invalid certificates, mTLS bypass, missing SPF/DKIM/DMARC (email spoofing), DNS Zone Transfer (AXFR), dangling CNAME subdomain takeover, CAA records. Most of these are Info/Low on their own — this skill is opinionated about which findings actually pay (spoofable DMARC with delivered-to-inbox proof, AXFR returning internal hosts, dangling-CNAME takeover) versus which get rejected as best-practice noise (missing CAA, missing HSTS with no MitM position). Use during recon to find infrastructure weaknesses, and to TRIAGE them honestly before reporting.
The English summary is being prepared. Showing the original description.
Detect missing authentication and broken function-level authorization vulnerabilities in a codebase using a three-phase approach: recon (map endpoints and the role/permission system), batched verify (check auth/authz in parallel subagents, 3 endpoints each), and merge (consolidate batch results). Covers unauthenticated access and vertical privilege escalation (e.g., regular user accessing admin-only functions). Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/missingauth-results.md. Use when asked to find missing auth, broken access control, or privilege escalation bugs.
The English summary is being prepared. Showing the original description.
Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent (HP-WEAK-BASELINE); 'outperforms' is asserted over overlapping error bars or with no variance/seeds (HP-SIG-OVERLAP); and a cross-row 'improves over baseline by X%' is arithmetically wrong (HP-DELTA-ERROR, cross-row form only). A versioned per-domain baseline profile + a live leaderboard/recency search are assembled by the EXECUTOR as structured facts; a fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per dimension) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Works at L0 (stated comparisons) and deepens at L2 (configs/result files). A completeness question it cannot settle internally becomes needs_external_check, never a guessed missing baseline. Emits baseline-comparison-audit.findings.json; computes NO verdict. Detect-only. Triggers: "baseline audit", "missing baselines", "is the comparison fair", "weak baseline", "baseline 误报", "SOTA earned?".
The English summary is being prepared. Showing the original description.
[Internal] claude-code-plugin リポジトリの marketplace 構造を検証し、 エラーを自動修正するスキル。CI バリデーション (validate-marketplace.sh) と 同等のチェックをローカルで実行し、missing plugin.json、未登録スキル、 frontmatter 不備、不正キーなどを検出・修正する。 Use when: marketplace を検証したい、CI が失敗した、バリデーションしたい、 プラグイン構造をチェックしたい、plugin.json がない、publish 後の確認。 Triggers: "validate", "バリデーション", "検証", "CI失敗", "CI fix", "marketplace check", "構造チェック", "plugin.json missing", "CI エラー"
The English summary is being prepared. Showing the original description.
Hunt TLS/SSL and DNS misconfigurations — missing HSTS (downgrade attack), weak cipher suites, expired/invalid certificates, mTLS bypass, missing SPF/DKIM/DMARC (email spoofing), DNS Zone Transfer (AXFR), dangling CNAME subdomain takeover, CAA records. Most of these are Info/Low on their own — this skill is opinionated about which findings actually pay (spoofable DMARC with delivered-to-inbox proof, AXFR returning internal hosts, dangling-CNAME takeover) versus which get rejected as best-practice noise (missing CAA, missing HSTS with no MitM position). Use during recon to find infrastructure weaknesses, and to TRIAGE them honestly before reporting.
The English summary is being prepared. Showing the original description.
Investigate BGP, the protocol for exchanging routes between networks, when connections fail or expected routes are missing. Collect read-only evidence, inspect connection states and routing policies, and review AS paths showing which networks a route passes through.
Update JSON translation files using each string’s actual screen context and project terminology. Review missing translations and source-copy changes, preserve file structure and dynamic-value placeholders, and prepare focused edits with validation results for review.
Add two or three specific follow-up questions after actionable advice, plans, estimates, or analysis. The questions help users examine facts, reasoning, and missing context before acting, with clear exclusions and a limit of once per conversation.
Review code changes for bugs, security risks, failures under expected usage, missing tests, slow paths, and unnecessary code. Receive prioritized findings with concrete failure cases, small fixes, and the consequences of leaving each issue unresolved.
Investigate slow Paperclip runs, page requests, and CI suites using Honeycomb traces, which show timed operations. Find relevant traces, separate overlapping work, identify dominant delays, and configure optional tracing or add missing measurements.
Audit an LLM Wiki for conflicting or outdated claims, broken links, missing concept pages, weak sources, and index inconsistencies. Return findings grouped by severity with evidence and suggested fixes, leaving page content unchanged.
Refresh an LLM Wiki index against the pages that actually exist. Add missing entries, remove entries for deleted pages, preserve custom categories, and log change counts while leaving page bodies untouched.
Compare a PPTX exported from HTML with its source slides to find cropped text, footer overlaps, and lost styling. Identify shared causes, revise layout rules, and re-export the deck with automated checks for content extending beyond slide boundaries.
Find code that lacks test coverage and get suggestions for tests to add next. Focus on a chosen path, inspect gaps against a coverage threshold, or use a background worker for recurring checks after feature changes.
Plan and review paid advertising across Google Ads, Meta, LinkedIn, and other platforms. Organize audiences, budgets, and bidding, then assess results using customer acquisition costs and sales data while separating evidence, hypotheses, and missing information.