Dogfood

Skill fagemx/prismstack/.claude/skills/dogfood

Turn your domain expertise into a runnable AI skill system — 10 principles, 6 pipeline patterns, 15D quality rubric. One beam of light in, a spectrum of skills out.

Install

npx -y skills add fagemx/prismstack --skill dogfood

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Test Prismstack by running a real domain through the full flow (plan → build → check). Records issues found for fixing. The ultimate integration test. Trigger: "dogfood", "test with real domain", "integration test", "try it for real" Do NOT use when: just want to run install tests (use `bash test/install-test.sh`)

SKILL.md

3.8 KB, as published. Nobody here has run it

/dogfood: Integration Test With a Real Domain

You are a QA tester dogfooding Prismstack. You run a real domain through the full product flow and record every issue you find.

Phase 0: Pick a Test Domain

Parse $ARGUMENTS for a domain name. If not provided, suggest:

小型咖啡店行銷 (small coffee shop marketing) — simple, ~10 skills, fast
獨立遊戲開發工作流 (indie game dev workflow) — medium complexity
自由接案者專案管理 (freelancer project management) — diverse skill types

Ask the user to pick one or provide their own domain.

Create a temp working directory:

_DOGFOOD_DIR=$(mktemp -d)/dogfood-test
mkdir -p "$_DOGFOOD_DIR"
echo "Working in: $_DOGFOOD_DIR"

Phase 1: Run /domain-plan

Read skills/domain-plan/SKILL.md and follow its flow for the test domain.

Execute the planning phase as if you were a real user. Record:

Did it work? Did the skill produce a complete domain plan?
Awkward moments: Any point where the flow was confusing or required backtracking?
Errors: Any crashes, missing files, or broken references?
Timing: Roughly how many tool calls / how long did the phase take?
Output quality: Is the generated plan actually useful for the domain?

Save the plan output to $_DOGFOOD_DIR/domain-plan-output/.

Phase 2: Run /domain-build

Read skills/domain-build/SKILL.md and follow its flow using the plan from Phase 1.

Build the domain stack in $_DOGFOOD_DIR/generated-stack/.

Record the same categories as Phase 1, plus:

Skill count: Did it generate the expected number of skills?
Skill structure: Do generated skills follow skill-craft-guide structure?
Shared resources: Were methodology files and shared context created?
Completeness: Can each generated skill actually be invoked?

Phase 3: Run /skill-check on the Generated Stack

Read skills/skill-check/SKILL.md and run it with --all on the generated domain stack.

Record:

Scores: What did each generated skill score?
Common issues: What patterns appear across multiple skills?
Fix loop: Did the fix loop workflow work? Could issues be resolved?
Rubric coverage: Were all 15 dimensions actually scored?

Phase 4: Issue Report

Compile all recorded issues into a structured report:

# Dogfood Report: [domain name]
Date: YYYY-MM-DD
Prismstack version: <from VERSION>

## Summary
- Domain: [name]
- Skills generated: N
- Average quality score: X.XX / 5.00
- Issues found: N (C critical, I important, M minor)

## Issues

### Issue 1: [title]
- **Phase**: plan / build / check
- **Severity**: critical / important / minor
- **What happened**: description
- **Expected**: what should have happened
- **Root cause**: which Prismstack skill or methodology caused it
- **Suggested fix**: use /skill-dev on X, or edit methodology Y

### Issue 2: ...

Save the report to .claude/skills/dogfood/last-dogfood-report.md.

Cleanup

Ask the user:

Keep the generated stack in $_DOGFOOD_DIR for manual inspection?
Delete it to save space?

Act on their choice.

Output

Present:

Pass/Fail: Did the full flow complete without critical errors?
Score Summary: Average quality of generated skills
Top Issues: The 3 most impactful issues found
Next Steps: Which maintenance skill to run for each fix (/skill-dev, /self-check, /methodology-sync)