查找技能

View recorded output tokens, cache-read tokens, response counts, and available mode attribution for a Claude Code session. In other agent environments, find the native usage report where supported, without treating observed usage as proof of savings.

中文简介正在准备中。当前显示英语简介。

• Checking recorded token usage for the current session
• Reviewing response counts and mode attribution
• Aggregating recorded output across sessions

Find LLM workflows in a codebase and label them by the job they perform, so Caveman Cloud can separate spending by workflow. Present a labeling proposal for approval, apply focused code changes, and check an affected execution path.

中文简介正在准备中。当前显示英语简介。

• Breaking down LLM spending by job
• Inventorying LLM use in APIs, scheduled jobs, and scripts
• Separating evaluation spending from other workflows

Connect an application's LLM calls through the Caveman Cloud gateway to measure usage and cost without changing request content. The skill updates connection settings and verifies the integration with one small, real provider request.

中文简介正在准备中。当前显示英语简介。

• Start measuring an LLM application's usage and cost
• Route existing LLM calls through the gateway
• Verify a connection with a real request

Delegate code lookup, small edits, and diff reviews to three specialized subagents. Their compact, structured results help conserve the main agent's context, with guidance on when to delegate and when to keep work in the main conversation.

中文简介正在准备中。当前显示英语简介。

• Locating definitions and callers
• Making a focused edit across one or two files
• Reviewing a diff for bugs

Locate relevant code in an unfamiliar repository or after a direct search fails. This read-only explorer returns a short list of file paths, verified line ranges, and relevance notes for another agent to use.

中文简介正在准备中。当前显示英语简介。

• Find starting points in an unfamiliar codebase
• Locate logic spread across multiple files
• Investigate after a direct search fails

Build a narrowly scoped feature or integration using existing repository structures. Define observable acceptance criteria and non-goals, complete the working path across relevant layers, and stop when focused checks confirm the requested outcome.

中文简介正在准备中。当前显示英语简介。

• Building a feature within a clear scope
• Adding integrations using existing structures
• Defining acceptance criteria and non-goals

Restructure code through extraction, consolidation, or responsibility moves while preserving its behavior. Establish checks before editing, repeat them afterward, and keep intermediate versions buildable and testable without mixing in feature changes.

中文简介正在准备中。当前显示英语简介。

• Extracting code while preserving behavior
• Consolidating duplicate processing
• Moving responsibilities between modules

Evaluate Caveman optimization observations by selecting a specific code change with operator approval. Compare the original and changed versions on identical inputs, checking both task quality and resource usage before deciding whether to keep the change.

中文简介正在准备中。当前显示英语简介。

• Inspecting a Caveman observation report
• Comparing token or byte usage before and after a change
• Checking whether an optimization preserves quality

Review Caveman Cloud spending, latency, errors, and potential improvements using current reports and traces, or individual execution records. Produce findings tied to time windows and trace IDs, while keeping measured costs, estimated opportunities, and verified savings separate.

中文简介正在准备中。当前显示英语简介。

• Understanding which workflows drive LLM spending
• Investigating slow responses and errors
• Reviewing measured costs and verified savings separately

Fix bugs and small behavior changes by tracing the cause and editing the smallest responsible part of the code. Preserve surrounding behavior and existing user changes, then run focused checks to confirm the fix and guard against recurrence.

中文简介正在准备中。当前显示英语简介。

• Fixing a bug without changing surrounding behavior
• Making a small, targeted behavior change
• Adding a test to prevent a specific bug from returning

Turn a Caveman token-usage report into specific edits to instruction files, repeated context, and memory. Review each proposed change before approval, then measure the result and distinguish confirmed file reductions from less certain session-level effects.

中文简介正在准备中。当前显示英语简介。

• Trimming a large CLAUDE.md file
• Moving repeatedly pasted context into cavemem
• Reviewing duplicate rules and broken memory links

Plan and implement migrations for data, APIs, configuration, and dependencies while preserving existing data and compatibility. Define rollback steps, check old and new behavior, and handle retries and partial failures during staged transitions.

中文简介正在准备中。当前显示英语简介。

• Migrate data while preserving existing records
• Roll out changes while old and new versions coexist
• Prepare rollback steps before a migration

Compress memory files and task lists into shorter wording to reduce input tokens. Keeps code and document structure intact, saves a readable backup separately, and sends the text to the configured model provider.

中文简介正在准备中。当前显示英语简介。

• Shortening CLAUDE.md to reduce input tokens
• Compressing task lists and preference files
• Keeping readable backups of compressed files

Investigate unclear failures, intermittent behavior, and performance regressions before changing code. Separate symptoms from assumptions, trace how failures arise, and rank possible causes by evidence and ease of testing, then report the cause and supporting proof.

中文简介正在准备中。当前显示英语简介。

• Investigating a failure with an unknown cause
• Diagnosing intermittent behavior
• Finding the cause of a performance regression

Review Caveman Cloud experiment states, evaluation results, and safety checks to recommend a supported next action. Identify missing or failing evidence and explain execution blocks; the current agent interface reads experiment data without changing its lifecycle state.

中文简介正在准备中。当前显示英语简介。

• Reviewing whether an experiment is ready to start
• Checking whether evidence supports experiment approval
• Assessing cancellation or rollback options

Make agent replies shorter and easier to scan by putting answers first and removing filler. Preserves technical details, exact commands, numbers, and essential conditions while keeping the user's chosen language.

中文简介正在准备中。当前显示英语简介。

• Reading concise replies in a terminal
• Getting conclusions before explanations
• Reducing wording while keeping technical details

Rewrite agent replies in Classical Chinese, a compact historical writing style, while keeping code and technical identifiers unchanged. Use it to shorten on-screen text and avoid repeated explanations, with ordinary prose when clarity requires it.

中文简介正在准备中。当前显示英语简介。

• Reading technical replies in Classical Chinese
• Reducing the amount of text on screen
• Keeping commands and error messages in their original form

Compress agent replies into short phrases while preserving technical details, negations, numbers, and exact commands. Use it to reduce repeated explanations and keep chat responses brief until you explicitly turn the mode off.

中文简介正在准备中。当前显示英语简介。

• Keeping technical replies brief
• Removing repeated explanations
• Maintaining concise replies throughout a session

Look up commands for concise response modes, commit messages, review comments, and Markdown compression. The reference also explains how to check the current mode, return to normal responses, and configure startup defaults.

中文简介正在准备中。当前显示英语简介。

• Look up response mode commands
• Check commands for commits and reviews
• Find how to turn a mode off

Verify that existing work meets its acceptance conditions using the smallest sufficient set of checks. Reuse results that still match the repository state, report outcomes precisely, and stop once the evidence is complete without adding unrelated work.

中文简介正在准备中。当前显示英语简介。

• Checking completed work against acceptance conditions
• Running focused checks for specific requirements
• Reusing verification results that remain current

Create short commit messages using Conventional Commits, a format that labels the type of change. Emphasize intent, keep the subject concise, and include explanatory text when breaking changes, security fixes, data migrations, or reversions require context.

中文简介正在准备中。当前显示英语简介。

• Writing a commit message for code changes
• Standardizing commit message format
• Documenting breaking changes and migration steps

Review code changes and produce concise comments ready to paste into a pull request. Each finding includes its location, the problem, and a concrete fix, with fuller explanations for security issues, architectural disagreements, or authors who need context.

中文简介正在准备中。当前显示英语简介。

• Reviewing a pull request
• Shortening lengthy review comments
• Pairing findings with concrete fixes

Optional design-improvement pass for when you have spare usage to drain. Finds the shallowest modules in the code the spec touches, researches a deeper design, and proposes refactors that shrink interfaces and hide decisions — behavior held constant, tests green before and after. Proposes §I/§V/§T edits, never silent rewrites. Triggers when the user says "deepen this", "improve the design", "this module feels shallow", "pull complexity down", "use spare budget on the codebase", or invokes /ck:deepen. Leans on the codebase-design skill's deep-module vocabulary when present.

中文简介正在准备中。当前显示原文说明。

Read-only drift detector. Diffs SPEC.md against current code and reports violations grouped by severity. Writes nothing — suggests remedies via the spec or build skills but never invokes them. Triggers when the user asks to check drift, audit the spec, verify invariants, or ask whether code still matches the spec. Phrasings: "check drift", "audit the spec", "does the code still match §V", "check invariants", "spec vs code".

中文简介正在准备中。当前显示原文说明。