Individual skill
gravitas
Use for software implementation, debugging, refactoring, review, migration, and other repository-changing engineering work where correctness must be verified. Enforces scoped reconnaissance, adaptive planning, evidence-backed verification, requirement tracking, failure recovery, and budget-aware delegation. Model-agnostic reliability runtime for coding agents -- measured, not claimed.
dist/gravitas-antigravity/skills/gravitas/SKILL.md
Source commit e0d22cd4f7639b1af3899bc3e70d314b2ae6339a
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Not checked yet
- Last checked
- Nov 7, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 448
- Repository last updated
- Nov 3, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- antigravity-skills Repository topic
- gemini Repository topic
- prompt-engineering Repository topic
- skills Repository topic
- engineering Derived category
- finance Derived category
- testing Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
PROMPT-TEMPLATE.mddoc · 7,393 bytesSESSION_FAILURES.mddoc · 118 bytesSKILL.mdcore · 6,035 bytesagents/coordinator.mddoc · 338 bytesagents/explore.mddoc · 5,593 bytesagents/general.mddoc · 4,732 bytesagents/plan.mddoc · 8,340 bytesagents/verify.mddoc · 4,849 bytesreferences/delegation.mddoc · 2,415 bytesreferences/model-routing.mddoc · 2,631 bytesreferences/reasoning.mddoc · 2,297 bytesreferences/reconnaissance.mddoc · 1,688 bytesreferences/recovery.mddoc · 4,194 bytesreferences/task-contract.mddoc · 2,853 bytesreferences/verification.mddoc · 5,055 bytesresources/adversarial-critique.mddoc · 5,723 bytesresources/anti-rationalization.mddoc · 8,872 bytesresources/context-management.mddoc · 5,539 bytesresources/gemini-native.mddoc · 7,100 bytesresources/memory-protocol.mddoc · 5,868 bytesresources/persona-protocol.mddoc · 5,661 bytesresources/subagent-patterns.mddoc · 6,076 bytesresources/tool-orchestration.mddoc · 5,992 bytesresources/verification-engine.mddoc · 7,159 bytesscripts/detect_project.pyruns · 3,092 bytesscripts/doctor.pyruns · 2,134 bytesscripts/run-checks.shruns · 4,591 bytesscripts/verify.pyruns · 4,074 bytesscripts/verify.shruns · 8,141 bytes
Read excerpt
# GRAVITAS -- Engineering Reliability Runtime
**One rule above all:** Report what actually happened, not what you intended.
When you claim something is done, fixed, or verified -- that claim rests on
output you observed in this session. If you did not check, say you did not
check.
---
## THE 6 INVARIANTS
These hold across models and hosts. The runtime enforces the
machine-checkable ones at hook level; the rest are on you.
