docs(skill): add on-invocation guard to socratic-code-theory-recovery#480
Conversation
The skill described the methodology but did not tell the LLM what to do the moment it is invoked. Result: invoking the slash command displayed the SKILL.md content, and Claude defaulted to a meta-conversation about the skill instead of starting Phase 1. The user has to know to either add the bounded-context path to the invoking message or chase it with a follow-up. Add a four-step "On invocation" section at the top of SKILL.md: 1. Check whether the user already named a bounded context (path + name). 2. If not, ask one specific question for it — do not assume the current working directory, because Phase 1 produces files and a wrong target wastes work. 3. Run Phase 1 with the user's path. 4. Stop after Phase 1; Phase 2 needs team answers and must not run silently in the same session. The pre-commit hook mirrors this into the plugin bundle. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
Warning Rate limit exceeded
You’ve run out of usage credits. Purchase more in the billing tab. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
2 participants
Follow-up to #478 / #479.
Problem
When a user invokes `/semantic-anchors:socratic-code-theory-recovery`, the LLM loads the SKILL.md content but has no clear instruction on what to do next. Symptom seen in practice: the slash command's output is displayed, and the model defaults to a meta-conversation about the skill ("here's what it does, give it a try sometime") instead of actually starting Phase 1.
Fix
Prepend an "On invocation" section to `SKILL.md` with four explicit steps:
This converts the skill from a passive document into an active behaviour spec without changing the methodology or any of the references.
Affected files
🤖 Generated with Claude Code