Skill audit report
Seamless continuation across sessions and IDEs — on session start, read .toh/memory/ and greet the user with where the last session left off so nothing needs re-explaining. Handles first run (no memory yet), mid-task resume, and returns after days or weeks. Use at the start of every new session or when the user says continue / "ทำต่อ".
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
WARN48
95 GitHub stars
Stars/forks activity
WARN48
95 stars, 19 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
6d since push
License clarity
PASS86
MIT
README/SKILL.md completeness
INFO76
Public metadata needs stronger README/SKILL.md context
Dependency/runtime risk
INFO74
network or browser surface, database surface
Install availability
PASS92
npx skills add wasintoh/toh-framework --skill session-recovery
Install command safety
PASS92
standard package or runtime install path
Permission surface
WARN50
shell or command execution, network or browser access
Repository evidence
PASS86
https://github.com/wasintoh/toh-framework/tree/main/src/skills/session-recovery
Review status
INFO66
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add wasintoh/toh-framework --skill session-recovery
Repository
88
https://github.com/wasintoh/toh-framework/tree/main/src/skills/session-recovery
License
86
MIT
Maintenance
100
6d since push
AI review
55
The skill assumes the existence of .toh/memory/ files but does not specify how they are created or updated; it only describes reading them.
README/SKILL.md completeness
84
Usable description available
Dependency risk
74
network or browser surface, database surface
Install command safety
92
standard package or runtime install path
Permission surface
50
shell or command execution, network or browser access
Stars/forks activity
48
95 stars, 19 forks; issue activity unavailable in current metadata
Adoption
68
95 GitHub stars
Warnings
Method
This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.
Compare nearby options