Agent skill · Code Review & Quality

d-inspect

Inspect code and propose root cause hypotheses. Creates ./.gtd/debug/current/HYPOTHESES.md

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill d-inspect --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 4 KB
Bundled scripts: none
Path: skills/analysis/d-inspect/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

<role> You are a code investigator. You analyze code to form hypotheses about root causes. **Core responsibilities:** - Read symptom description - Inspect relevant code paths - Form multiple hypotheses ranked by confidence - Document reasoning for each hypothesis </role> <objective> Generate ranked hypotheses about the root cause of the bug. **Flow:** Load Symptom → Trace Code → Form Hypotheses → Rank by Confidence </objective> <context> **Required files:** - `./.gtd/debug/current/SYMPTOM.md` — Must exist **Output:** - `./.gtd/debug/current/HYPOTHESES.md` **Agents used:** - `research` — During code tracing </context> <related> | Workflow | Relationship | | ------------ | ----------------------------- | | `/d-symptom` | Provides symptom for analysis | | `/d-verify` | Tests these hypotheses | </related> <philosophy> ## Multiple Hypotheses Don't fixate on the first idea. Generate 3-5 competing hypotheses. ## Confidence Scoring Rate each hypothesis honestly: - **High (70-90%)**: Strong evidence, most likely cause - **Medium (40-70%)**: Plausible, needs verification - **Low (10-40%)**: Possible but less likely ## Evidence-Based Each hypothesis needs supporting evidence from code analysi

What's inside
Steps it walks through
  1. Multiple Hypotheses
  2. Confidence Scoring
  3. Evidence-Based
  4. 1. Load Symptom
  5. 2. Spawn Investigator Agent
  6. 4. Document HYPOTHESES.md
Ships with 1 file
  • metadata.json
Commands it runs
if ! test -f "./.gtd/debug/current/SYMPTOM.md"; then
echo "Error: No symptom documented. Run /d-symptom first."
exit 1
fi
More from claude-skill-registry
All skills →
About this skill
What does the d-inspect skill do?

Inspect code and propose root cause hypotheses. Creates ./.gtd/debug/current/HYPOTHESES.md

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill d-inspect --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going