skills
anthropics
Public repository for Agent Skills
tancheng33/dsh-yogacara
dsh-yogacara is a tool for DeepSeek Harness. A Yogācāra (Consciousness-Only) self-model plugin for DeepSeek Harness: eight consciousnesses, the 51 mental factors, a perfumed seed store, and a measurable self — written back into the agent's own prompt.

REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
A conceptually rich, well-documented self-model plugin, but niche appeal and unverified engineering rigor warrant a caut
README references specific source files (src/citta.ts, src/observe.ts, src/conversation.ts) and describes testable functions, but no test suite, CI config, or build tooling is shown in the provided excerpt.
No download-and-execute patterns, credential handling, or permission scopes are described in the given information, so a neutral score is assigned.
Addresses a real agent pain point (repetitive loops, ungrounded self-assessment) with a structured 51-factor taxonomy, but the Yogācāra framing is unusual and the practical benefit over simpler state tracking is unproven.
Last updated 2026-08-26, not archived, MIT licensed, and actively versioned on npm, indicating current maintenance.
README is extensive with diagrams, mapping tables, and configuration hints (e.g., observeTools: false), but lacks a concrete install-to-first-run walkthrough or usage examples.
Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryINSTALL REFERENCE
pnpm add dsh-yogacaraThis command passed the install-plan safety checks and can be executed by the DSH host. Validation is not a security audit or official endorsement.
PROJECT TOPICS
VALIDATION LADDER
FAQ
A Yogācāra (Consciousness-Only) self-model plugin for DeepSeek Harness: eight consciousnesses, the 51 mental factors, a perfumed seed store, and a measurable self — written back into the agent's own prompt.
dsh-yogacara has 4 stars and 0 forks on GitHub, last updated 2026-08-26.
dsh-yogacara is distributed under the MIT license.
dsh-yogacara is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:No valid category tags。