Adlc Grounded
Answer with strict evidence when assumptions or stale facts would be unsafe.
Install
$ agentstack add skill-davidvictor-adlc-skills-adlc-grounded ✓ 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.
About
ADLC Grounded
Use this when the user asks for certainty, current facts, or a no-guess answer.
Process
- Resolve effective ADLC paths from
.adlc/config.yamlwhen repo artifacts are relevant; useadlc resolve-configwhen the CLI is available. - Identify the claim or decision that needs proof.
- Prefer primary sources: live repo files, runtime output, official docs, current database/tool state.
- Separate observed facts from inference.
- Stop with
INSUFFICIENT INFORMATIONwhen the evidence cannot support the answer. - When evidence is sufficient but the remaining gap is a human decision, recommend
adlc-interview. - Do not implement or plan unless the user redirects.
Output
Include confidence, evidence sources, gaps, and the next check that would improve certainty.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: davidvictor
- Source: davidvictor/adlc-skills
- 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.