Results for “prompt-guard”

13 skills
thedixitjain
Guard
Full safety mode: destructive command warnings + directory-scoped edits. (gstack)
2 · bundle
lovits
Guard
Full safety mode: destructive command warnings + directory-scoped edits. (gstack)
0 · bundle
affaan-m
Safety Guard
Prevents destructive operations on production systems and restricts file edits to a specific directory when running agents autonomously.
226k
livelybug
Guard
Full safety mode: destructive command warnings + directory-scoped edits. (gstack)
0
livelybug
Safety Guard
Use this skill to prevent destructive operations when working on production systems or running agents autonomously.
0
netanel-abergel
Pre Commit Guard
Runs before every git commit on heleni-memory. Checks: no credentials in tracked files, no oversized files, valid SKILL.md frontmatter for any new/modified skill. Triggers: "commit", "before push", "validate repo", or auto-runs as a git pre-commit hook.
6 · bundle
livelybug
Gateguard
Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.
0
mhassan0000
Gateguard
Blocks Edit/Write/Bash actions until the agent presents concrete facts about imports, data schemas, and the user's instruction, improving output quality.
1
rajanthar
Gateguard
Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.
0
affaan-m
Gateguard
Forces AI agents to investigate before editing or running destructive commands, improving code quality by requiring concrete facts like importers, data schemas, and user instructions.
226k
yanacuti1121
Gateguard
Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.
2
kk20300113-png
Guard
Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety". (gstack)
0
intense-visions
TS Type Guards
TypeScript Type Guards
18 · bundle