Install
$ agentstack add skill-pjuniszewski-cook-cook-menu ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
cook-menu Skill
Interactive menu for managing cook artifacts using native Claude Code UI.
Execution Flow
When /cook-menu is invoked, follow this flow:
Step 1: Scan Artifacts
Run this command to get artifact list with metadata:
for f in cook/*.cook.md; do
if [ -f "$f" ]; then
name=$(basename "$f" .cook.md)
status=$(grep -m1 "^## Status" -A1 "$f" | tail -1 | tr -d '[:space:]')
mode=$(grep -m1 "^## Cooking Mode" -A1 "$f" | tail -1 | tr -d '[:space:]')
echo "$name|$status|$mode"
fi
done
Step 2: Select Artifact
Use AskUserQuestion tool to present artifacts:
Question: "Which artifact do you want to manage?"
Header: "Artifact"
Options: [list of artifacts with status as description]
If user selects "Exit" or cancels, end the skill.
Step 3: Select Action
Use AskUserQuestion tool to present actions:
Question: "What do you want to do with ?"
Header: "Action"
Options:
- "Validate" - "Run validation checks on this artifact"
- "Compare" - "Diff with another artifact"
- "Status" - "View artifact metadata summary"
- "Back" - "Return to artifact selection"
Step 4: Execute Action
Based on selection:
Validate:
./scripts/cook-validate "cook/.cook.md" --verbose
Compare:
- Use AskUserQuestion to select second artifact
- Run:
./scripts/cook-diff "cook/.cook.md" "cook/.cook.md"
Status:
./scripts/cook-validate "cook/.cook.md" --quiet
Then display: filename, status, mode, owner, date, section count.
Back: Return to Step 2.
Step 5: Loop
After action completes, return to Step 3 (action selection) for same artifact. User can select "Back" to return to artifact selection.
Example Flow
/cook-menu
│
▼
[AskUserQuestion: Select artifact]
- dry-run-validation.2026-01-10 (well-done)
- artifact-versioning.2026-01-10 (ready-for-merge)
│
▼ user selects "dry-run-validation"
│
[AskUserQuestion: Select action]
- Validate
- Compare
- Status
- Back
│
▼ user selects "Validate"
│
[Runs cook-validate, shows results]
│
▼
[AskUserQuestion: Select action] (loop)
Requirements
- Artifacts in
cook/*.cook.md scripts/cook-validatefor validationscripts/cook-difffor comparisons
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: PJuniszewski
- Source: PJuniszewski/cook
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.