AgentStack
SKILL verified Apache-2.0 Self-run

Debug Autofix Skills

skill-opendatahub-io-autofix-skills-debug-autofix-skills · by opendatahub-io

Investigate agent-side failures in the autofix-skills plugin. Covers wrong verdicts, review loop issues, state machine bugs, and prompt problems. Use when the agent ran but produced wrong results.

No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add skill-opendatahub-io-autofix-skills-debug-autofix-skills

✓ 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 Debug Autofix Skills? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Debug Autofix-Skills

Investigate failures in the agent-side layer: skill prompts, review orchestration, verdict generation, and state management.

Key entry points

| Area | Entry point | |------|-------------| | Orchestration | skills/autofix-resolve/SKILL.md, skills/autofix-cve-resolve/SKILL.md | | Triage | skills/autofix-triage/SKILL.md | | State machine | scripts/state.py (duplicated in each skill's scripts/ dir) | | Review merging | scripts/merge_findings.py | | Verdict writing | scripts/write_json.py + schemas/*.json | | Prompts | prompts/*.md within each skill directory | | Hook recovery | hooks/hooks.json, tmp/dispatch-recovery.sh |

Protocol

  1. Read this repo's AGENTS.md for architecture context.
  2. Check [references/symptoms.md](references/symptoms.md) for known patterns matching the failure.
  3. Investigate the relevant skill's SKILL.md, prompts, scripts, and schemas.
  4. Write RCA using [assets/rca-template.md](assets/rca-template.md).

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.

Versions

  • v0.1.0 Imported from the upstream source.