Install
$ agentstack add skill-lightconeresearch-lightcone-cli-lc-feedback ✓ 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
/lc-feedback
File a bug report against the right Lightcone repo based on the current session.
Be fast. The user is in the middle of work and wants to get back to it.
Prerequisites
Run gh auth status silently. If it fails:
> GitHub CLI is not authenticated. Run gh auth login, then try again.
Stop.
Step 1: Description
The user should have provided a description inline (e.g., /lc-feedback pipeline dies on second output). If they didn't, ask briefly:
What went wrong?
Step 2: Draft and Confirm
Triage the repo from context:
- ASTRA —
astraCLI, schema validation, YAML parsing, helpers - lightcone-cli —
lcCLI, recipe execution, container builds, scaffolding, skills
Default to lightcone-cli if ambiguous.
Collect versions silently:
python3 -c "import astra; print(astra.__version__)" 2>/dev/null || echo "n/a"
python3 -c "import lightcone.cli; print(lightcone.cli.__version__)" 2>/dev/null || echo "n/a"
python3 --version 2>&1
uname -s -r
Show the user a single confirmation message with the target repo, title, and body. Use AskUserQuestion with options "File it" / "Let me edit". The issue body format:
## What happened
[1-3 sentences combining user description + session context]
## Error
[Trimmed error/traceback from session, if any]
## Reproduction
[Brief steps from session context]
## Environment
- ASTRA: [version]
- lightcone-cli: [version]
- Python: [version]
- OS: [os]
Omit sections that don't apply (e.g., no Error section if there was no traceback).
Step 3: File
gh issue create --repo LightconeResearch/ --title "" --label "beta-feedback" --body ""
If it fails due to the label not existing, retry without --label. Print the issue URL.
Rules
- Be fast — minimize back-and-forth, one confirmation then file
- Read-only — never modify project files
- Trim aggressively — only the relevant portion of errors, not full files
- No sensitive data — strip absolute paths, credentials, tokens
- Don't editorialize — report what happened, don't speculate on fixes
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: LightconeResearch
- Source: LightconeResearch/lightcone-cli
- License: BSD-3-Clause
- Homepage: https://docs.lightconeresearch.org/
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.