Agent Skill
Momentic Spec skill
momentic-specmomentic-ai/skillsskills/momentic-spec/SKILL.md
Improve code correctness using Momentic specs in the feature development process
always on
16 tokname + description
once used
2,060 tokSKILL.md body
bundled files
11 KB
repo stars
16GitHub
Install the Momentic Spec skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/momentic-ai/skills --skill momentic-spec
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/momentic-ai/skills.git /tmp/skills mkdir -p ~/.claude/skills cp -R /tmp/skills/skills/momentic-spec ~/.claude/skills/momentic-spec
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 16 tok |
| When the agent uses it | The SKILL.md instructions | 2,060 tok |
| Only if opened | 1 bundled files (1 KB) | varies |
Until it is used, momentic-spec costs about 85× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 6 skills from momentic-ai/skills would load 284 tokens of descriptions. Skills vs MCP study
Checks
Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Momentic spec-driven development
- Non-negotiable sequence
- Choose the affected tests
- Write the product specification first
- Follow the codebase's testing language
- Prefer AI action V3 for new specifications
- Run at durable end-to-end checkpoints
- Own the test data and application state
- Edit and validate safely
More skills from momentic-ai/skills
- momentic-testmomentic-ai/skills
Create, run, and maintain Momentic browser E2E tests and modules stored as *.test.yaml and *.module.yaml files.
68k30 tok idle · 3,669 in use - momentic-result-classificationmomentic-ai/skills
Classify or explain Momentic test run results using Momentic MCP tools. Use when the user asks to categorize a failure, understand why a run failed, triage test results, or compare run results to past run results.
68k51 tok idle · 4,134 in use - mo-qamomentic-ai/skills
Run and control Mo QA sessions with Momentic's `qa` CLI. Use for bug bashes, status checks, report export, replies to Mo, file transfer, or repairs based on Mo findings.
1645 tok idle · 3,966 in use - momentic-maintainmomentic-ai/skills
Diagnose, classify, triage, and repair failing Momentic tests with MCP run tools, the Momentic CLI, and manual run artifacts. Use when a developer asks what happened on a branch, DevX or on-call asks why main is red, or the user wants to inspect classifications, de-flake quarantined or recovered tests, reduce retries, re-classify runs, run AI triage, or repair failures.
1689 tok idle · 6,522 in use - momentic-mobile-testmomentic-ai/skills
Create, run, and maintain Momentic mobile E2E tests and modules for Android and iOS. Use Momentic MCP tools for live device validation, and use direct v2 YAML edits only for high-confidence local mobile v2 changes.
1653 tok idle · 3,517 in use