Menu

Not in the top 1,000 by GitHub stars

udaysharmadev/Gravitas

Make Gemini code like Claude Models. Forces it to inspect files before editing, plan changes, test its work, and back up every “done” with actual evidence.

Claude CodeCodexGemini CLIEngineeringWritingTesting

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

dist/gravitas-antigravity/skills/gravitas/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 6444b1e35c5c

No earlier version was observed for comparison.

Compare on GitHub

dist/gravitas-antigravity/skills/gravitas-highstakes/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 6444b1e35c5c

No earlier version was observed for comparison.

Compare on GitHub

plugins/gravitas-perf/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 6444b1e35c5c

No earlier version was observed for comparison.

Compare on GitHub

plugins/gravitas-security/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 6444b1e35c5c

No earlier version was observed for comparison.

Compare on GitHub

skills/gravitas/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 6444b1e35c5c

No earlier version was observed for comparison.

Compare on GitHub

skills/gravitas-highstakes/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 6444b1e35c5c

No earlier version was observed for comparison.

Compare on GitHub

skills/gravitas-python/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 6444b1e35c5c

No earlier version was observed for comparison.

Compare on GitHub

skills/gravitas-typescript/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 6444b1e35c5c

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 6444b1e35c5cd1715fc56ebd56497046841a53f3

git clone --filter=blob:none --no-checkout https://github.com/udaysharmadev/Gravitas.git .hotskills/udaysharmadev-gravitas && git -C .hotskills/udaysharmadev-gravitas checkout --detach 6444b1e35c5cd1715fc56ebd56497046841a53f3 # Copy each selected skill directory from .hotskills/udaysharmadev-gravitas into .claude/skills/<skill-name>/
git clone --filter=blob:none --no-checkout https://github.com/udaysharmadev/Gravitas.git .hotskills/udaysharmadev-gravitas && git -C .hotskills/udaysharmadev-gravitas checkout --detach 6444b1e35c5cd1715fc56ebd56497046841a53f3 # Copy each selected skill directory from .hotskills/udaysharmadev-gravitas into .agents/skills/<skill-name>/
git clone --filter=blob:none --no-checkout https://github.com/udaysharmadev/Gravitas.git .hotskills/udaysharmadev-gravitas && git -C .hotskills/udaysharmadev-gravitas checkout --detach 6444b1e35c5cd1715fc56ebd56497046841a53f3 # Copy each selected skill directory from .hotskills/udaysharmadev-gravitas into .gemini/skills/<skill-name>/
443GitHub stars
40stars in 7 days
8skills in this repository
89commits in 30 days

Heat

8.1
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Nov 6, 2026443

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

gravitas

When your agent uses it

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.

What it loads into context

Frontmatter

84 tokens

Always available to the agent

SKILL.md

1,338 tokens

When the skill is activated

Reference documents

26,516 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. THE 6 INVARIANTS
  2. POLICY RECORD
  3. MODES
  4. DECISION RECORDS
  5. VERIFICATION HIERARCHY
  6. EFFORT PROFILES
  7. DELEGATION
  8. OUTPUT FORMAT
  9. What Changed
  10. Evidence
  11. Why
  12. DEEP REFERENCES

Scripts executed separately

  • scripts/detect_project.py
  • scripts/doctor.py
  • scripts/run-checks.sh
  • scripts/verify.py
  • scripts/verify.sh

Files

  • PROMPT-TEMPLATE.mddoc7,393 bytes
  • SESSION_FAILURES.mddoc118 bytes
  • SKILL.mdcore6,035 bytes
  • agents/coordinator.mddoc338 bytes
  • agents/explore.mddoc5,593 bytes
  • agents/general.mddoc4,732 bytes
  • agents/plan.mddoc8,340 bytes
  • agents/verify.mddoc4,849 bytes
  • references/delegation.mddoc2,415 bytes
  • references/model-routing.mddoc2,631 bytes
  • references/reasoning.mddoc2,297 bytes
  • references/reconnaissance.mddoc1,688 bytes
  • references/recovery.mddoc4,194 bytes
  • references/task-contract.mddoc2,853 bytes
  • references/verification.mddoc5,055 bytes
  • resources/adversarial-critique.mddoc5,723 bytes
  • resources/anti-rationalization.mddoc8,872 bytes
  • resources/context-management.mddoc5,539 bytes
  • resources/gemini-native.mddoc7,100 bytes
  • resources/memory-protocol.mddoc5,868 bytes
  • resources/persona-protocol.mddoc5,661 bytes
  • resources/subagent-patterns.mddoc6,076 bytes
  • resources/tool-orchestration.mddoc5,992 bytes
  • resources/verification-engine.mddoc7,159 bytes
  • scripts/detect_project.pyruns3,092 bytes
  • scripts/doctor.pyruns2,134 bytes
  • scripts/run-checks.shruns4,591 bytes
  • scripts/verify.pyruns4,074 bytes
  • scripts/verify.shruns8,141 bytes
Read SKILL.md

# 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.
View the complete source on GitHub

Skills included

  • gravitas
  • gravitas-highstakes
  • gravitas-perf
  • gravitas-security
  • gravitas
  • gravitas-highstakes
  • gravitas-python
  • gravitas-typescript

Repository facts

License
MIT
Created
Sep 8, 2026
Last pushed
Nov 3, 2026
Forks
38
Open issues
22
Project activity
Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 24 notes
  • plugins/gravitas-perf/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/gravitas-perf/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/gravitas-perf/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/gravitas-perf/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/gravitas-perf/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/gravitas-security/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/gravitas-security/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/gravitas-python/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/gravitas-python/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/gravitas-python/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/gravitas-python/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/gravitas-python/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/gravitas-python/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/gravitas-python/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/gravitas-python/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/gravitas-python/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/gravitas-python/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/gravitas-python/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/gravitas-python/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/gravitas-python/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 24 signals by file

dist/gravitas-antigravity/skills/gravitas/agents/explore.md

  • Access to secretsline 65
    [Credential-related source omitted]

dist/gravitas-antigravity/skills/gravitas/resources/memory-protocol.md

  • Network accessline 126
    https://stripe.com/docs/webhooks/signatures

dist/gravitas-antigravity/skills/gravitas/resources/verification-engine.md

  • Access to secretsline 190
    [Credential-related source omitted]

dist/gravitas-antigravity/skills/gravitas/scripts/detect_project.py

  • Executable scriptline 1
    #!/usr/bin/env python3

dist/gravitas-antigravity/skills/gravitas/scripts/doctor.py

  • Executable scriptline 1
    #!/usr/bin/env python3

dist/gravitas-antigravity/skills/gravitas/scripts/run-checks.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

dist/gravitas-antigravity/skills/gravitas/scripts/verify.py

  • Executable scriptline 1
    #!/usr/bin/env python3

dist/gravitas-antigravity/skills/gravitas/scripts/verify.sh

  • Executable scriptline 1
    #!/bin/bash

plugins/gravitas-perf/SKILL.md

  • Network accessline 75
    # API latency (using autocannon, wrk, or k6) autocannon -c 10 -d 10 http://localhost:3000/api/users
  • Network accessline 76
    autocannon -c 10 -d 10 http://localhost:3000/api/users
  • Network accessline 201
    # Before/after latency comparison autocannon -c 10 -d 30 http://localhost:3000/api/endpoint
  • Network accessline 202
    autocannon -c 10 -d 30 http://localhost:3000/api/endpoint
  • Network accessline 207
    # Memory usage node --max-old-space-size=512 -e "require('./dist/server')" & sleep 5 && curl http://localhost:3000/api/heavy-endpoint
  • Network accessline 209
    sleep 5 && curl http://localhost:3000/api/heavy-endpoint

plugins/gravitas-security/SKILL.md

  • Dangerous shell operationline 81
    □ A08 Software/Data Integrity  — dependencies verified, no eval()
  • Access to secretsline 110
    [Credential-related source omitted]

skills/gravitas/agents/explore.md

  • Access to secretsline 65
    [Credential-related source omitted]

skills/gravitas/resources/memory-protocol.md

  • Network accessline 126
    https://stripe.com/docs/webhooks/signatures

skills/gravitas/resources/verification-engine.md

  • Access to secretsline 190
    [Credential-related source omitted]

skills/gravitas/scripts/detect_project.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/gravitas/scripts/doctor.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/gravitas/scripts/run-checks.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/gravitas/scripts/verify.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/gravitas/scripts/verify.sh

  • Executable scriptline 1
    #!/bin/bash

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 24 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativePath CLAUDE.md.claude/skills/<skill-name>/
CodexNativeManifest AGENTS.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md dist/gravitas-antigravity/skills/gravitas/SKILL.md.cursor/skills/<skill-name>/
Gemini CLINativePath GEMINI.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md dist/gravitas-antigravity/skills/gravitas/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md dist/gravitas-antigravity/skills/gravitas/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

mohitagw15856/pm-claude-skills

1,310 professional Agent Skills for Claude, Claude Duet, ChatGPT, Gemini, Cursor & Codex: PRDs, postmortems, leases, medical bills, payroll checks, morning briefs. 21 skills built…

1.5kGitHub stars

rohitg00/skillkit

Supercharge AI coding agents with portable skills. Install, translate & share skills across Claude Code, Cursor, Codex, Copilot & 40 more

1.6kGitHub stars

Emily2040/nano-banana-image-skill

Production-grade, agent-portable image prompting skill for Nano Banana Pro and Nano Banana 2 in the Gemini image family

36GitHub stars

Joonghyun-Lee-Frieren/oh-my-antigravity

Context-engineering-powered multi-agent team workflow pack for Antigravity CLI.

218GitHub stars

Emily2040/gravitas

Gravitas is a free add-on for Google Antigravity that makes its AI agent check what your answer depends on, tell you kindly when something you assumed is wrong, and still give you…

30GitHub stars

JellyBrick/korean-prose-skill

이상한 해요체는 이제 그만...!! 한국어 작성 및 교정 스킬

27GitHub stars