test-project
Run a Swallow project's tests through the pricing engine and analyse results
Skill by llow-group
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/llow-group-test-project
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
test-project- Description
- Run a Swallow project's tests through the pricing engine and analyse results
- License
- MIT
- Instructions
- 20 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Test Project
The user wants to run tests against a Swallow project configuration.
1. **Load the project** — Read the JSON file the user provides or references.
2. **Check test format** — Before running, verify every test has an `output` object with `result` (number) and `valid` (boolean). If any test has `output: {}` or is missing these fields, fix it before submitting (use `result: 0, valid: true` as placeholders for discovery runs).
3. **Run tests** — Call `test_swallow_project` via MCP with the project JSON.
4. **Analyse results** — For each test case:
- Show the test name, expected output, and actual output
- Flag any mismatches between expected and actual `result` or `valid`
- List any errors from the pricing engine (missing properties, expression failures, etc.)
5. **Summarise** — Report how many tests passed vs failed, and what the common issues are.
6. **Fix if asked** — Suggest specific changes to steps/expressions to fix failing tests. Re-run after each fix to confirm.From llow-group/swallow-claude-plugin, MIT.
More from llow-group/swallow-claude-plugin
- 0.406score
excel-to-swallow
llow-group
Convert an Excel rating workbook (.xls/.xlsx) into a Swallow pricing engine configuration.
SkillDFreshness: DClaude Code +9 - 0.404score
swallow-docs
llow-group
Load the Swallow Pricing Engine documentation and JSON schema as reference context
SkillDFreshness: DClaude Code +9 - 0.404score
build-pricing-model
llow-group
Build a Swallow pricing engine configuration from a natural language description of an insurance product
SkillDFreshness: DClaude Code +9 - 0.399score
validate-project
llow-group
Validate an existing Swallow project configuration against the schema
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 26, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from llow-group
- 0.406score
excel-to-swallow
llow-group
Convert an Excel rating workbook (.xls/.xlsx) into a Swallow pricing engine configuration.
SkillDFreshness: DClaude Code +9 - 0.404score
swallow-docs
llow-group
Load the Swallow Pricing Engine documentation and JSON schema as reference context
SkillDFreshness: DClaude Code +9 - 0.404score
build-pricing-model
llow-group
Build a Swallow pricing engine configuration from a natural language description of an insurance product
SkillDFreshness: DClaude Code +9 - 0.399score
validate-project
llow-group
Validate an existing Swallow project configuration against the schema
SkillDFreshness: DClaude Code +9
Cite this page
test-project skill. Agent Mart. https://agentmart.dev/skills/llow-group-test-project (last updated 2026-10-24)