「audit」の検索結果

Audit a spreadsheet for formula accuracy, errors, and common financial-model mistakes. Use for selected ranges, single sheets, or whole-workbook model checks including balance-sheet balance, cash tie-out, roll-forwards, and logic sanity.

日本語の概要は準備中です。原文の説明を表示しています。

General workflow for auditing ML CI failures, experiment regressions, training run failures, golden metric failures, and telemetry-backed ML work-product claims from local repositories, logs, metrics, configs, and artifacts. Use when Codex needs to decide whether an ML failure is a model/convergence issue, correctness bug, data/config issue, infrastructure/runtime issue, evaluation/gating policy issue, or unsupported claim, and produce structured evidence-backed outputs.

日本語の概要は準備中です。原文の説明を表示しています。

Detect and rewrite AI writing patterns to make content sound authentically human. Supports voice calibration from the author's own writing samples. Use when asked to humanize text, remove AI patterns, calibrate voice, audit content for AI detectability, or check if writing sounds like ChatGPT. Triggers: /humanize, /voice-calibrate, /audit-ai

日本語の概要は準備中です。原文の説明を表示しています。

Audit and repair Pharos documentation against the codebase. Use for documentation update passes, verified-doc drift, source-path/doc-sync failures, methodology/doc routing updates, or requests to verify docs without trusting existing prose.

日本語の概要は準備中です。原文の説明を表示しています。

Drain the Pharos Dependency Map coverage-audit queues into evidence-refreshed edges, reviewed target dispositions, or documented deferrals. Use monthly after weekly production dependency audits, after dependency coverage drops, or when reviewing adapter gaps, material unlinked slices, symbol leads, duplicate/split groups, or unverifiable published edges.

日本語の概要は準備中です。原文の説明を表示しています。

Use for a whole-corpus, read-only audit of tracked stablecoin static metadata and domain sidecars, especially after catalog changes or when factual or internal-consistency drift needs review.

日本語の概要は準備中です。原文の説明を表示しています。

TLS/SSL configuration audit. Tests protocol versions (SSLv2/3, TLS 1.0/1.1/1.2/1.3), cipher strength and ordering, certificate chain validation (intermediates, CT logs, OCSP stapling, pinning), known vulnerabilities (POODLE, BEAST, CRIME, Heartbleed, ROBOT, DROWN, Ticketbleed, GOLDENDOODLE), session management (ticket reuse, resumption, fixation), renegotiation attacks, TLS 1.3-specific issues (0-RTT replay, PSK modes, downgrade), HSTS deep analysis (preload, subdomains, bypass), and certificate revocation (CRL, OCSP responder, stapled response freshness). Compliance-mapped to PCI DSS 4.0 (full Section 4), NIST SP 800-52r2, and FedRAMP. Uses testssl.sh, sslscan, sslyze, openssl, nmap NSE scripts, and nuclei SSL templates. Multi-port scanning across 20+ TLS-bearing services.

日本語の概要は準備中です。原文の説明を表示しています。

Use when auditing GitHub Actions workflows for script injection vulnerabilities via unsanitized context expressions. Trigger on: "github actions injection", "workflow injection", "head_ref injection", "github context injection", "pwn request", "github.head_ref", "github.event.pull_request.title", "github.event.issue.body", pull_request_target workflows, run: steps interpolating GitHub context variables, CI/CD script injection, GitHub Actions security audit.

日本語の概要は準備中です。原文の説明を表示しています。

Canonical entry point for the full Gaia evidence verification pipeline. Invoke as /evidence-verification-pipeline or /ev-pipeline — both names trigger this skill. Use whenever you need to run the evidence phases end-to-end: collecting raw evidence from the data lake, verifying live GitHub star counts, running Phase 2B benchmark-source verification, running adversarial auditing for noise and URL errors, and checking link health via Firecrawl. Also use when someone says "run the evidence pipeline", "verify the evidence lake", "audit evidence", "run ev-pipeline", "full evidence check", "pipeline run", "prepare evidence for ingestion", or "refresh the data lake". This is the pre-ingestion step — run it before importing any evidence into the registry.

日本語の概要は準備中です。原文の説明を表示しています。

Audit organizational communications — channel effectiveness, message clarity, overload, and actionable improvement plans.

日本語の概要は準備中です。原文の説明を表示しています。

Marketing analytics and data-driven optimization for B2B SaaS campaigns. Use this skill when analyzing marketing performance, optimizing conversion rates, running A/B tests, conducting customer research, creating marketing dashboards, building attribution models, analyzing funnel metrics, or storytelling with data. Also triggers on: marketing ops, performance analytics, CRO, A/B testing, data storytelling, customer insights, tracking plan, event taxonomy, UTM taxonomy, GA4 audit, consent mode, instrumentation contract, sample size calculation, minimum detectable effect, test duration, not enough traffic to A/B test, statistical significance, Bayesian vs frequentist, sample ratio mismatch, experiment feasibility, martech stack, marketing tech stack audit, tool consolidation, build vs buy, vendor evaluation, shadow IT tools, ESP/CRM/platform migration, switching cost, cutover plan, suppression list migration, data portability, customer interviews, survey design, sampling frame, non-response bias, how many people should I interview, thematic saturation, voice of customer, jobs-to-be-done, buyer persona research, is this finding real, data enrichment, which enrichment provider should we buy, waterfall enrichment, contact data quality, match rate, our list data is bad, email verification, catch-all domain, accept-all, bounce rate from bad data, B2B data decay, how often should we re-verify contacts, ZoomInfo vs Apollo vs Clearbit evaluation, cost per usable record, where did this list come from, GDPR Article 14 notice, purchased list compliance, suppression screening, TAM list building, demand planning, marketing plan, how many leads do we need, what pipeline target should marketing carry, funnel model, top-down vs bottom-up plan, plan of record, annual marketing planning, quarterly planning, pipeline coverage we have to create, sales cycle lag, our leads cannot close this quarter, carry-in pipeline, scenario planning, conservative moderate aggressive forecast, stretch target, reforecast, re-forecast triggers, assumption register, capacity ceiling, addressable audience ceiling, marginal cost per lead, blended CPL is wrong, we missed plan and nobody knows why, AI policy for the marketing team, AI governance, AI acceptable use policy, which AI tools are we allowed to use, can I paste customer data into ChatGPT, shadow AI, AI use register, human review of AI output, when can we stop reviewing every AI draft, can the agent send on its own, the AI made a mistake now what, pull back AI autonomy, AI evals, our AI vendor changed the model, AI output went out wrong, prompt injection, can our AI read prospect replies safely, lethal trifecta, the AI leaked internal notes, turn off auto-generated ad assets, auto-applied recommendations, AI literacy training, EU AI Act Article 4, duplicate records in the CRM, dedupe before import, which value wins in a merge, CRM cleanup.

日本語の概要は準備中です。原文の説明を表示しています。

Visual design verification loop for matching a goal PNG to a live render. Use when the user shares a design mock / goal image and asks to match the UI to it, asks to "iterate on this design" or "match this 1:1", or calls out visual drift in a previous UI iteration. Provides histogram color sampling, shape inspection (radius/border/shadow/bg-mode/fill-vs-context), computed-style checking on the live render, snap, and side-by-side diff. After every UI change the assistant MUST snap the live render and Read the snap with the Read tool before reporting the change done — skipping that is the

日本語の概要は準備中です。原文の説明を表示しています。

Decide whether a Pulp test earns its place — before writing it, when reviewing one, or when sweeping a subsystem for low-value, duplicated, or mis-routed tests. Applies a four-question authoring gate, a junk-pattern list, a retention bar, and an evidence template for any deletion, and routes kept tests to the right lane (required gate, pr-fast, slow, nightly). Handles "should I add a test for this", "is this test useful", "audit these tests", "reduce test time", "which tests can go", and "move toward functional tests".

日本語の概要は準備中です。原文の説明を表示しています。

Reviews CLAP plugin implementations for spec compliance, thread safety, and correctness. Use when the user asks to review a CLAP plugin, audit a CLAP extension, or check whether their process() callback follows the CLAP threading model. Trigger on phrases like "review my CLAP plugin", "check CLAP extension", "is my CLAP process() safe", "audit my clap_plugin_t", or when you see clap_plugin_t, clap_process_t, or CLAP extension structs in the code.

日本語の概要は準備中です。原文の説明を表示しています。

Reviews VST3 plugin implementations for spec compliance, host compatibility, and correctness. Use when the user asks to review a VST3 plugin, check bus arrangements, audit parameter handling, or verify their process() callback is safe. Trigger on phrases like "review my VST3 plugin", "check VST3 bus arrangement", "is my VST3 process safe", "audit my IAudioProcessor", or when you see IComponent, IAudioProcessor, IEditController, ProcessData, or Vst:: namespaced types in the code.

日本語の概要は準備中です。原文の説明を表示しています。

Convert an existing prose, flat, or loosely organized mathematical proof into a source-mapped Lamport-style hierarchy without repairing or completing its mathematics. Use when a submitted proof needs a traceable hierarchical rendering before a forward Lamport audit or for clearer presentation. Do not use to invent a proof, certify validity, or restructure an already hierarchical proof merely to audit it.

日本語の概要は準備中です。原文の説明を表示しています。

Audit an existing mathematical, logical, algorithmic, or technical proof from its stated conclusion backward as a bounded AND/OR graph of exact obligations. Use to reconstruct conclusion dependencies, determine whether a proof-supplied route establishes the conclusion, or expose hidden assumptions, unmet side conditions, cycles, overly strong steps, or silent route switches. For a source-mapped Lamport rendering use convert-lamport, and for forward hierarchy, construct, and scope conformance use forward-lamport before this skill. This does not decide full theorem-level entailment by searching for a different proof; do not turn the audit into a linear reversed proof, exhaustive proof search, or replacement proof.

日本語の概要は準備中です。原文の説明を表示しています。

Audit an existing Lamport-style hierarchical mathematical proof forward for validity and whether its hierarchy, scope, dependencies, side conditions, and proof constructs discharge the stated theorem. Use when the central question concerns a top-down proof with numbered levels, subproofs, ASSUME/PROVE, SUFFICES, PICK, CASE, DEFINE, Q.E.D., or prose equivalents. For an ordinary proof that first needs source-preserving hierarchy, use convert-lamport; for conclusion-first AND/OR obligation reconstruction, use reverse-lamport. Do not use to generate or replace a proof, or to audit Lean, Coq, Isabelle, or other proof-assistant source.

日本語の概要は準備中です。原文の説明を表示しています。

Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.

日本語の概要は準備中です。原文の説明を表示しています。

Audit the game for security vulnerabilities: save tampering, cheat vectors, network exploits, data exposure, and input validation gaps. Produces a prioritised security report with remediation guidance. Run before any public release or multiplayer launch.

日本語の概要は準備中です。原文の説明を表示しています。

Audit GDD-specified content counts against implemented content. Identifies what's planned vs built.

日本語の概要は準備中です。原文の説明を表示しています。

Audits game assets for compliance with naming conventions, file size budgets, format standards, and pipeline requirements. Identifies orphaned assets, missing references, and standard violations.

日本語の概要は準備中です。原文の説明を表示しています。

Audit whether all score-deciding logic in sgl-eval is vendored from NeMo-Skills, or whether some has crept into SE code. Use when the user asks "are we vendoring enough", "review vendor coverage", "audit vendoring", "is our vendoring complete", or before a release.

日本語の概要は準備中です。原文の説明を表示しています。

Evaluate ENCODE experiment quality using standard metrics and audit flags. Use when the user asks about data quality, wants to filter for high-quality experiments, needs to interpret quality metrics (FRiP, NSC, RSC, NRF, IDR, TSS enrichment, fragment size), wants to understand ENCODE audit warnings, needs to compare quality across experiments, or is deciding whether data is usable for their analysis. Also use when the user mentions QC, quality control, or data filtering.

日本語の概要は準備中です。原文の説明を表示しています。