Analyze specific pytest failures using authoritative contracts and a cited product/test evidence chain. Use for failing test names or pytest output, distinguishing product, interface, oracle, and harness defects without automatically changing expectations or forcing an architectural redesign.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Read and follow Test Failure Mindset, including its Python standards route. It owns the investigation protocol; this skill applies it to each supplied failure. Reuse an existing evidence record instead of restarting completed investigation.
Read the complete relevant test, fixtures, setup/cleanup, stack trace, and product path. Preserve the failed revision and conditions; reproduce safely when permitted. Trace the product and test observation to their earliest demonstrated contract divergence.
For each candidate explanation, identify a discriminating observation and separate observed facts from unverified inference. Verify which requirement governs the expected behavior. A familiar mathematical, library, or API convention alone does not establish this product's contract.
Classify supported defects separately as product implementation, interface/architecture, test oracle, or harness/CI; several may coexist. For missing authority, report the intent decision. For missing execution, report unvalidated behavior rather than silently choosing a side.
Example: divide(10, 0) returning a sentinel versus raising an exception cannot be adjudicated
from the operation's name. A current approved sentinel contract makes a raising implementation
incorrect; an approved error contract makes a sentinel expectation incorrect. Without that
authority, report the ambiguity and the evidence or decision required.
TEST / REVISION / FAILURE:
CONTRACT / AUTHORITY / INVARIANTS:
EXPECTED / OBSERVED / REPRODUCTION LIMITS:
EVIDENCE CHAIN / FIRST DIVERGENCE:
SUPPORTED CAUSE / UNVERIFIED HYPOTHESES:
CORRECTION CATEGORY / RATIONALE:
PROPOSED CHANGE / PRESERVED BEHAVIOR:
VALIDATION: original fault -> intended failure; corrected behavior -> success
REMAINING UNCERTAINTY / NEXT OBSERVATION OR INTENT DECISION:
Do not manufacture cause from an assertion mismatch. Keep correction proposals distinct from work actually performed. When changing a test, explain the authoritative reason and show its relevant fault sensitivity; a collection or setup error does not establish regression protection. Use Comprehensive Test Review for the broader assessment.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Add automated documentation updater to any Claude skill. Creates a Python sync script that downloads upstream docs, processes markdown for AI consumption, and maintains local cache with configurable refresh. Collects template variables, then delegates implementation through 5-phase workflow. Use when adding auto-updating reference documentation to plugins or skills.
中文简介正在准备中。当前显示原文说明。
SAM-style feature initiation workflow — discovery through codebase analysis, architecture spec, task decomposition, validation, and context manifest. Use when a user asks to add a feature, plan a feature, or convert an idea into an executable SAM plan.
中文简介正在准备中。当前显示原文说明。
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
中文简介正在准备中。当前显示原文说明。
Browser automation for AI agents using the agent-browser CLI and Playwright. Use when navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, logging into sites, or automating any browser task. Triggers on "open a website", "fill out a form", "click a button", "scrape data", "test this web app", "automate browser actions", or any programmatic web interaction request.
中文简介正在准备中。当前显示原文说明。
Runs the description-drift experiment — spawns all Claude Code agents simultaneously to collect self-reported capabilities, then compares them against static frontmatter descriptions to reveal how reliable orchestrator routing based on descriptions actually is. Use when measuring description drift across the agent fleet, re-running the capability collection experiment, analyzing a specific agent's self-reported capabilities, or auditing whether frontmatter descriptions accurately reflect agent behavior.
中文简介正在准备中。当前显示原文说明。
Create or adapt Claude Code agent definitions. Use when creating an agent, changing subagent configuration, selecting agent scope, or designing a specialized delegation role.
中文简介正在准备中。当前显示原文说明。