Skip to content
cccskills
FreePublished on GitHub

find-cause

Investigate why something happens — confirm the question and success criteria with you, then trace the root cause with an evidence chain.

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

See how to install

Files included (2)

  • SKILL.md2.3 KB
  • SKILL-GOALS.md224 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

<investigation_request>$ARGUMENTS</investigation_request>

Find Cause

Rewrite the user's investigation request into one confirmed question with Step 1 below, then trace it with Step 2. The user's original request is in <investigation_request/>.

Procedure

Step 1 — Disambiguate the question and define success criteria

Read the user's request in <investigation_request/>. Perform two tasks:

A. Formulate distinct interpretations

Formulate 2 or more distinct interpretations of what they are asking. Present these interpretations to the user using the AskUserQuestion tool so the user can select the correct one or provide their own clarification.

Each interpretation MUST be a concrete, falsifiable question — not a vague restatement. Frame each as "Are you asking X?" where X is specific enough to investigate.

Example for the request "find out why the tests fail":

  • Interpretation A: "Why do tests fail when run locally but pass in CI?"
  • Interpretation B: "Why does a specific test case produce an unexpected assertion error?"
  • Interpretation C: "Why did tests start failing after a recent change?"

Do NOT proceed until the user has confirmed which interpretation is correct or provided their own.

If the user selects "Other" and provides additional context, reformulate the interpretations and ask again. Only proceed when you have a single, unambiguous question to investigate.

B. Define success criteria

Load the dh:root-cause-tracing-process skill with the Skill tool now. For the confirmed interpretation, write the QUESTION and SUCCESS CRITERIA block its Inputs section defines. You run its steps at Step 2 below.

Present the success criteria to the user for confirmation. Adjust if the user's definition of "done" differs.

Do NOT proceed to Step 2 until both interpretation and success criteria are confirmed.

Step 2 — Trace the root cause

Follow the loaded dh:root-cause-tracing-process skill from Step 0, with the confirmed QUESTION and SUCCESS CRITERIA as its Inputs, through its Step 5 report.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

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.

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

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

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.

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

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

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.

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

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

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.

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

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

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.

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

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

Create or adapt Claude Code agent definitions. Use when creating an agent, changing subagent configuration, selecting agent scope, or designing a specialized delegation role.

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

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

See all skills by Jamie-BitFlight

Report a problem with this skill