[skills] Hermes Agent Onboarding — 10 skills + recipe#337
Open
djairjr wants to merge 7 commits into
Open
Conversation
Generative 6-stage meta-skill for ANY user. Transforms a blank AI agent into a customized ecosystem with persistent relational identity. Skills (10): - agent-onboarding, context-bridge, supabase-startup-protocol - identity-self-audit, identity-cqrs, checkpoint-workflow - mbti-guru-hermes, stage-3-financial, stage-4-system-ontologist - stage-5-agent-calibration Recipe: hermes-agent-onboarding with 4 DB migrations + setup docs. Schema: 10 identity tables (user_profiles, identity_faults, etc.) Based on NateBJones/OB1 Edge Function + MCP pattern. Built by djairjr from djairjr/hermes-agent-onboarding.
github-actions
Bot
added
recipe
|
Hey @djairjr — welcome to Open Brain Source! 👋 Thanks for submitting your first PR. The automated review will run shortly and check things like metadata, folder structure, and README completeness. If anything needs fixing, the review comment will tell you exactly what. Once the automated checks pass, a human admin will review for quality and clarity. Expect a response within a few days. If you have questions, check out CONTRIBUTING.md or open an issue. |
…UL.md stable tier Key discovery: countermeasures in Supabase database do NOT automatically become behavior rules. The missing piece was SOUL.md — a physical file loaded by the agent framework as the first element of the system prompt, before any user message or skill. This completes the identity cycle for the meta-skill: - REGISTER: identity_faults, agent_capabilities in Supabase - INJECT: countermeasures via SOUL.md (primary, stable tier) + identity-cqrs startup scan (secondary, runtime) - BEHAVE: automatic behavior correction at generation time Curation protocol: SOUL.md is a curated extract (severity >= 4, active, max ~10 rules) — not the full database. Deliberate compression. Use for model retraining: fault pairs serve as LoRA/DPO dataset. Updates: - stage-5-agent-calibration v1.1.0: full identity cycle doc, SOUL.md as physical file, curation protocol, model retraining section - agent-onboarding: identity cycle in core principle section
…talog Two new fault types from real usage: schema guessing during DML and context recovery failure (starting from zero when past context exists). Countermeasures documented.
Adds Pitfall 6 (never guess schema, 2 SQL queries for any table), Pitfall 7 (same rule for file edits), and 4 default countermeasures for SOUL.md generation. Works on ANY Supabase without local docs.
djairjr
commented
Jun 1, 2026
djairjr
left a comment
djairjr
left a comment
Author
There was a problem hiding this comment.
Improving metaskill definitiions
…ase) - agent-onboarding/SKILL.md: add Two-Tier Architecture section, separation principle, storage options - identity-self-audit/SKILL.md: add Storage section, identity_db.py helper format as primary, SQL as fallback Signed-off-by: djair.jr <djair.jr@gmail.com>
The ContextStressTest.md is a research paper directed at the authors of Context-CoT (2605.25354) and CL-Bench (2602.03587), describing how the identity layer enables adversarial context degradation testing using Cain's Jawbone — a 100-page shuffled novel with no canonical ordering. The paper argues that context learning benchmarks miss the reliability dimension of the agentic interface. Signed-off-by: djair.jr <djair.jr@gmail.com>
djairjr
commented
Jun 2, 2026
djairjr
left a comment
djairjr
left a comment
Author
There was a problem hiding this comment.
Include very complex context stress test using "Cain's Jawbone" book.
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.
Generative 6-stage meta-skill for ANY user. Transforms a blank AI agent into a customized ecosystem with persistent relational identity.
Skills (10):
Recipe: hermes-agent-onboarding with 4 DB migrations + setup docs.
Schema: 10 identity tables (user_profiles, identity_faults, etc.)
Based on NateBJones/OB1 Edge Function + MCP pattern. Built by djairjr from djairjr/hermes-agent-onboarding.
Contribution Type
/recipes)/schemas)/dashboards)/integrations)/skills)What does this do?
Requirements
Checklist
README.mdwith prerequisites, step-by-step instructions, and expected outcomemetadata.jsonhas all required fields