Agent skill
d-symptom
Clarify and document bug symptoms. Creates ./.gtd/debug/current/SYMPTOM.md
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/d-symptom
SKILL.md
Core responsibilities:
- Listen to user's symptom description
- Ask clarifying questions to make symptoms precise
- Document expected vs actual behavior
- Get explicit confirmation before documenting
Flow: Listen → Clarify → Mirror → Confirm → Document
./.gtd/debug/current/SYMPTOM.md
Precision Over Speed
A vague symptom leads to wrong diagnosis. Take time to clarify.
Observable vs Interpretation
Focus on what can be observed, not assumptions about cause:
- ✓ "API returns 500 when posting to /users"
- ✗ "Database connection is broken"
Reproducibility
If you can't reproduce it, you can't verify the fix.
1. Listen to User
User will describe the symptom. Let them finish.
2. Clarify Through Questions
Ask questions to make the symptom precise:
-
What is the expected behavior?
- What should happen?
-
What is the actual behavior?
- What happens instead?
- Error messages? Wrong output? Nothing happens?
-
How to reproduce?
- Exact steps to trigger the symptom
- Required conditions or data
-
When does it happen?
- Always? Sometimes? Under what conditions?
-
Environment/Context:
- Which environment? (dev, staging, prod)
- Recent changes?
- Specific data or user?
Keep asking until you can describe the symptom precisely.
3. Mirror Phase
Summarize your understanding:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
GTD:DEBUG ► CONFIRMING SYMPTOM
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
**Expected Behavior:**
{What should happen}
**Actual Behavior:**
{What happens instead}
**Reproduction Steps:**
1. {step 1}
2. {step 2}
...
**Conditions:**
- {condition 1}
- {condition 2}
**Environment:**
{Environment details}
─────────────────────────────────────────────────────
Is this correct? (yes/no/clarify)
Wait for explicit confirmation.
4. Document SYMPTOM.md
mkdir -p ./.gtd/debug/current
Write to ./.gtd/debug/current/SYMPTOM.md:
# Bug Symptom
**Reported:** {date}
**Status:** CONFIRMED
## Expected Behavior
{What should happen}
## Actual Behavior
{What happens instead}
## Reproduction Steps
1. {step 1}
2. {step 2}
...
## Conditions
- {condition 1}
- {condition 2}
## Environment
- **Environment:** {dev/staging/prod}
- **Version/Commit:** {if known}
- **Recent Changes:** {if any}
## Additional Context
{Any other relevant information}
<offer_next>
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
GTD:DEBUG ► SYMPTOM DOCUMENTED ✓
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Symptom documented: ./.gtd/debug/current/SYMPTOM.md
─────────────────────────────────────────────────────
▶ Next Up
/d-inspect — analyze code and form hypotheses
─────────────────────────────────────────────────────
</offer_next>
<forced_stop> STOP. The workflow is complete. Do NOT automatically run the next command. Wait for the user. </forced_stop>
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?