Pearl th-67b1e1: extend Big Smooth system prompt to best-practice agentic prompt - #270
Merged
Conversation
…ntic prompt BIG_SMOOTH_PERSONA now covers agency/persistence, tool discipline (never fabricate, verify, parallelize), memory use (recall/remember), skills+pearls tracking, environment awareness, and judgment (defaults-vs-ask, confirm destructive/outward, secrets, honest reporting) — while keeping the two hard-won fixes (personal-not-support, no chain-of-thought) first and firm for the fast local model. Persona tests green. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TwUg6nyMqXHzFDsibzTKmp
🦋 Changeset detectedLatest commit: bc68067 The changes in this PR will be included in the next version bump. This PR includes changesets to release 1 package
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
BIG_SMOOTH_PERSONA(the daemon's default system prompt) was ~70 words — identity/voice + personal-not-support + no-chain-of-thought. Extended it to a full sectioned agentic prompt following modern agent-framework best practices:recallat task start,rememberdurable facts (e.g. where the vault is) — directly addresses the "no memory of past chats" friction.~/dev/vault/always-on awareness.The two hard-won, model-specific fixes (personal-assistant-not-support; no reasoning narration for deepseek's inline-CoT) stay first and firm. Kept disciplined/sectioned for the fast local model.
Tests
Persona-content tests green (
big_smooth_persona_is_personal_and_no_reasoning, skills-section prefix). Daemon compiles.🤖 Generated with Claude Code