feat: add zero-hallucination-coder skill to engineering#854
Open
mehanshbarthwal-lab wants to merge 2 commits into
Open
feat: add zero-hallucination-coder skill to engineering#854mehanshbarthwal-lab wants to merge 2 commits into
mehanshbarthwal-lab wants to merge 2 commits into
Conversation
Synthesizes four open-source agent repos into a single unified coding discipline for Claude Code and other AI agents: - Ralph (github.com/snarktank/ralph): atomic PRD loop, fresh-context per story, progress.txt memory - GSD Core (github.com/open-gsd/gsd-core): Discuss→Plan→Execute→Verify phase loop, context-rot prevention, structured STATE.md memory files - Graphify (github.com/safishamsi/graphify): KNOWN/INFERRED/UNKNOWN codebase mapping, zero hallucination because you read real structure - Ponytail (github.com/DietrichGebert/ponytail): lazy-senior-dev six-rung hierarchy, 80-94% less code by deleting before writing Includes: - Full five-phase loop (Discuss → Map → Decompose → Execute → Verify) - Anti-hallucination rules 1-7 - Context engineering rules (GSD Core context-rot prevention) - Ponytail check before every story (Phase 3.5) - Installation guide for Claude Code, Amp, Gemini CLI, Cursor, Windsurf, Codex, and Claude web (Project Instructions method) - Full credits table linking all four source repos
- Rename Anti-Hallucination Rules to Anti-Patterns - Rename Related Skills to Cross-References - Add plugin.json manifest to satisfy check_plugin_json.py
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a zero-hallucination coding skill to engineering -- synthesizes four open-source agent repos into one unified pipeline.
What this skill does
Enforces a strict Discuss -> Map -> Decompose -> Execute -> Verify loop before any code is written, with the Ponytail lazy-senior-dev hierarchy applied before every story to eliminate unnecessary code.
Credits and inspiration
Installation
Covers both AI agents (Claude Code, Amp, Gemini CLI, Cursor, Windsurf, Codex) and Claude web (Project Instructions method).