DSH PluginsSkill
skills
anthropics
Public repository for Agent Skills
Structure check pending
agent-skills
Back to Marketplace
DSH PluginsPlugin
dsh-auto-approval-llm
cuddly-guacamole/dsh-auto-approval-llm
dsh-auto-approval-llm is a tool for DeepSeek Harness. LLM-assisted auto approval + timeout fallback for the DeepSeek Harness Auto preset
- Stars
- 8
- Forks
- 3
- Issues
- 0
- Update
- 33 days
REVIEW SCORECARD
Review Scorecard
7.6/10Average
License compliance9.0
Engineering quality5.9
Content completeness7.0
Repository scale7.0
Maintenance activity8.0
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Worth AI Review
7.2/10Consider
Feature-rich LLM-assisted auto-approval plugin with strong safety design, but install instructions and platform support
Code quality7
README describes detailed architecture (guard/pre-execute/approval pipeline, audit logs, retries) but no tests, CI, or install/dev docs are visible, so rigor is only partially evidenced.
Security7
Design is explicitly fail-closed with hard denies, credential-store secrets, audit trails, and locked dangerous categories, though the plugin grants broad Auto-tier approval authority and no source review is possible here.
Utility8
Solves a real pain point by automating approval decisions in DeepSeek Harness Auto mode with timeout fallback, LLM classification, and circuit breakers for unattended sessions.
Maintenance8
Last updated 2026-09-12, not archived, with a versioned changelog-style README (0.0.16) and active feature evolution indicating ongoing maintenance.
Documentation6
README is extremely detailed on behavior and configuration but the install command is unknown and platform support is Windows/Git Bash-centric with macOS/Linux/WSL only 'welcome feedback'.
Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.
PROJECT READMEREADMEExpandCollapse
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryPROJECT TOPICS
Project topics
VALIDATION LADDER
Validation progress
01Store discoveryPassed
02ClassificationPending
03Structure checkPending
04Sandbox validationPending
FAQ
Frequently Asked Questions
What is dsh-auto-approval-llm used for?
LLM-assisted auto approval + timeout fallback for the DeepSeek Harness Auto preset
How popular is dsh-auto-approval-llm?
dsh-auto-approval-llm has 8 stars and 3 forks on GitHub, last updated 2026-09-18.
What license does dsh-auto-approval-llm use?
dsh-auto-approval-llm is distributed under the BSD-3-Clause license.
Is dsh-auto-approval-llm compatible with DeepSeek Harness?
dsh-auto-approval-llm 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
Classification evidence
Project typePlugin
Feature categoryDSH Plugins
Rule confidenceLow
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:No valid category tags。
DSH PluginsSkill
graphify
Graphify-Labs
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Structure check pending
ai-agentsantigravityastclaude-code
DSH PluginsSkill
caveman
JuliusBrussee
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Structure check pending
aianthropiccavemanclaude
DSH PluginsSkill
taste-skill
Leonxlnx
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
Structure check pending
agentaiclaudeclaude-code
DSH PluginsSkill
awesome-claude-skills
ComposioHQ
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
Structure check pending
agent-skillsai-agentsantigravityautomation
DSH PluginsSkill
cherry-studio
CherryHQ
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
Structure check pending
agent-skillsai-agentclaude-codecodex