AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Adlc Fix

skill-davidvictor-adlc-skills-adlc-fix · by davidvictor

Diagnose and fix bugs while writing reusable learning patches for future runs.

↗ Repository
— No reviews yet
0 installs
2 views
0.0% view→install

Install

$ agentstack add skill-davidvictor-adlc-skills-adlc-fix

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

Are you the author of Adlc Fix? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

ADLC Fix

Use this for failures, bugs, regressions, flaky checks, and hotfixes.

Modes

  • fix now: reproduce, diagnose, patch, verify.
  • plan first: write .adlc/fixes/.md and stop for review.

Process

  1. Resolve effective ADLC paths from .adlc/config.yaml; use adlc resolve-config when the CLI is available.
  2. Reproduce or observe the failure before editing.
  3. Minimize the failing surface.
  4. Patch the smallest behavior boundary.
  5. Add or update regression evidence when practical.
  6. Write a patch note under the configured patches path when the lesson should improve future work.
  7. Hand the fix back to an autonomous review or verify gate when scoped checks pass. Do not label ordinary code, docs, tests, rules, or security fixes as needing human review.

Human-Gated Blockers

Pause for the operator only when the next step requires an explicit human decision, credential or external account, destructive or production operation, legal/security sign-off, scope or product ambiguity, or user-requested approval point.

Output

Report root cause, changed files, verification, patch note path, whether adlc-evolve should run, and the next gate: autonomous adlc-review/adlc-verify or a specific human-gated blocker reason.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

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.

More in Agent Skills