Results for “baseline”

Reconcile baseline-versioned files that the `create-baseline upgrade` CLI staged for LLM-assisted semantic merge. Use when the CLI prints "Open Claude Code and run /upgrade-project to reconcile". Reads the stage manifest at `.claude/state/upgrade/<ts>/manifest.json`, reasons through each pending file's three-way delta in main context, writes a reconciled LOCAL, then deletes the stage when every file lands. Supports `--dry-run` (preview the reconciled diff without writing) and a structured "needs-user-input" fallback when the conflict cannot be disambiguated automatically.

The English summary is being prepared. Showing the original description.

Generate or repair a project's .gitignore. Composes the baseline must-ignore set (the single source of truth in baseline-ignores.json) with optional gitignore.io enrichment, and merges add-only so existing entries are never lost. Use when a repo has no .gitignore, when the commit-leak guard reports a gap, or when onboarding a new stack. Trigger: "set up gitignore", "fix my gitignore", "ignore node_modules/secrets", "gitignore for <stack>".

The English summary is being prepared. Showing the original description.

Drift check between the baseline implementation on disk and the claims in `docs/init/seed.md` + cross-references in CLAUDE.md, README.md, and the rendered docs site. Verifies hook/agent/skill/command names + counts, settings.json wiring, project.json key presence, .mcp.json servers, vendored license files, and helper script presence. Exit 0 PASS / 1 FAIL — suitable for CI. Read-only; safe to invoke any time.

The English summary is being prepared. Showing the original description.

Use when the user asks to "map what our surfaces say today", "inventory our current messaging", or "find the gap between what we say and what we mean"; produces the narrative baseline — a surface-by-surface inventory of what every owned touchpoint (homepage, pricing, docs, decks, social bios, email footers) claims RIGHT NOW, each line labeled Measured / User-provided / Estimated, plus a per-surface gap read vs the intended message and the drift-baseline snapshot the Evaluate phase measures future drift against. Not for authoring the canon — use message-system-architect; not for scoring the surfaces or running the vetoes — use narrative-quality-auditor. 现状叙事盘点/各触点口径/意图差距/漂移基线

The English summary is being prepared. Showing the original description.

Diagnose MSBuild build performance bottlenecks using binary log analysis. Only activate in MSBuild/.NET build context. USE FOR: identifying why builds are slow by analyzing binlog performance summaries, detecting ResolveAssemblyReference (RAR) taking >5s, Roslyn analyzers consuming >30% of Csc time, single targets dominating >50% of build time, node utilization below 80%, excessive Copy tasks, NuGet restore running every build. Covers timeline analysis, Target/Task Performance Summary interpretation, and 7 common bottleneck categories. Use after build-perf-baseline has established measurements. DO NOT USE FOR: establishing initial baselines (use build-perf-baseline first), fixing incremental build issues (use incremental-build), parallelism tuning (use build-parallelism), non-MSBuild build systems. INVOKES: binlog MCP server tools (overview, errors, search, items, properties); falls back to dotnet msbuild binlog replay + grep/cat when the MCP is unavailable.

The English summary is being prepared. Showing the original description.

SEO drift monitoring: capture baselines of SEO-critical elements, detect changes, and track regressions over time. Git for SEO: baseline, diff, and track changes to your on-page SEO. Use when user says "SEO drift", "baseline", "track changes", "did anything break", "SEO regression", "compare SEO", "before and after", "monitor SEO changes", or "deployment check".

The English summary is being prepared. Showing the original description.

Add machine learning to an existing application through a structured workflow. The skill guides problem definition, data checks, separation from business logic, and training and evaluation of a simple initial model.

• Adding recommendations to an existing application
• Checking whether training data is ready
• Integrating a prediction model with fallback rules

Turn speedup requests into a measured optimization process with limits on time, cost, and variants. Compare each change against a baseline and correctness checks, then retain the fastest safe option with reproducible commands and measurements.

• Speeding up a slow operation using measured comparisons
• Comparing implementation variants under the same input conditions
• Evaluating latency, throughput, or cost per run

Train and evaluate models that estimate human poses from WiFi signals. Compare results against a model that always predicts the average pose, check for data leakage, and report measured improvements with clear evaluation conditions.

• Train a pose model using camera labels
• Evaluate pose estimation without a camera at inference
• Compare accuracy against an average-pose baseline

Compare saved benchmark runs over time to track win rate, response times, escalation rate, and LLM baseline costs. Review changes between the first and latest runs, with flags for declining win rates or rising average latency.

• Check performance trends before a release
• Review benchmark history after expanding the test corpus
• Track latency changes after an agent-booster upgrade

Run a prepared set of test cases to check agent-booster success rates and routing decisions. Optionally compare results with Gemini or Claude models, then save detailed measurements and summaries as JSON records for later verification.

• Checking success rates before a release
• Verifying routing after adding test cases
• Checking performance claims against measurements

Test interface behavior in a real browser and save actions, checks, and screenshots in a replayable RVF session file. Use recorded sessions to repeat tests, investigate CI failures, and compare screenshots against an earlier baseline.

• Checking user flows in a real browser
• Recording a baseline before interface changes
• Comparing screenshots with a previous test run

Compare accessibility findings between two versions of a web page. Identify newly introduced and fixed issues, count existing findings, and report evidence and suggested fixes without editing application code.

• Check accessibility before committing local changes
• Compare a page against a branch baseline
• Confirm which accessibility issues a change fixed

Prepare a one-page briefing before a company's quarterly earnings report. Gather market estimates, rank key metrics, and outline optimistic, baseline, and pessimistic scenarios, including the developments that could influence the stock's reaction.

• Preparing a briefing before quarterly earnings
• Prioritizing company-specific metrics to watch
• Comparing optimistic, baseline, and pessimistic scenarios

Review source code for MCP, a protocol connecting AI applications to tools. Check authentication, input validation, unsafe execution, and other security risks, then report findings with file and line references and separate manual follow-ups.

• Reviewing an MCP server before release
• Checking authentication and validation on a network-exposed server
• Auditing tool code for unsafe execution paths

Create integration tests for .NET database access before migrating from Oracle to PostgreSQL. The tests record expected Oracle behavior with controlled test data and portable checks, providing a baseline for later migration validation.

• Recording Oracle behavior before migration
• Testing repository methods and stored procedure calls
• Checking empty strings, NULL inputs, and datetime precision

Audit Azure Storage settings for public containers, encryption, access permissions, network restrictions, and logging gaps. Use command-line checks and monitoring alerts to produce findings and remediation guidance across subscriptions.

• Auditing storage settings across Azure subscriptions
• Investigating publicly accessible blob containers
• Verifying encryption, network, and logging controls

Investigate malware that survives OS reinstallation by checking UEFI firmware, boot files, and Secure Boot settings. Use chipsec and supporting tools to compare trusted baselines, identify bootkit indicators, and document findings.

• Investigating reinfection after OS reinstallation
• Checking unexpected Secure Boot changes
• Comparing firmware against a trusted vendor baseline

Inspect Windows startup entries with Sysinternals Autoruns to find possible malware persistence, settings that let malware restart automatically. Review signatures, file locations, and changes from a clean baseline to identify entries that need investigation.

• Investigating suspicious startup entries on a Windows endpoint
• Comparing startup settings against a clean baseline
• Checking for remaining malware startup entries after cleanup

Improve prompts through test cases and baseline comparisons, measure how well AI answers use retrieved sources, and check agent configurations. Includes Python tools for prompt analysis, retrieval quality reports, and token estimates, with costs calculated from supplied rates.

• Compare prompt revisions against a baseline
• Measure answer quality against retrieved sources
• Check agent tool settings and loop risks

Add or update Handsontable performance tests for rendering and user interactions. The skill guides trace recording, measurement boundaries, baseline comparisons, and reports that help reviewers identify performance changes in pull requests.

• Add a performance test for a Handsontable feature
• Investigate filtering or sorting performance
• Compare performance changes in a pull request

Check running experiments, collect logs and result metrics, and summarize progress alongside baseline comparisons. It supports SSH servers, Vast.ai, and Modal, with optional Weights & Biases metrics and cost reporting for the supported compute services.

• Check whether remote experiments have finished
• Compare collected metrics with the matching baseline
• Investigate NaN values or diverging training runs

Compare two GEO audits, which assess a site's readiness for AI search visibility, and produce a monthly client report. Summarize score changes, crawler access, completed actions, newly discovered issues, and priorities for the following month.

• Prepare a monthly GEO progress report for a client
• Compare baseline and current audit scores
• Review completed actions and next month's priorities

Research key competitors and produce cited profiles, a comparison table, and implications for a product decision. Separate facts from inferences and assumptions, highlight evidence quality, and create a consistent baseline for later comparisons.

• Reviewing a product's positioning against competitors
• Informing roadmap priorities with competitive evidence
• Investigating a rival's strengths after lost deals