Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →github/debugging-workflows
Debug gh-aw workflows using run logs, audits, and failure triage.
Passed 19 of 23 test cases with the skill, and 6 of 23 without it.
and 13 more in the full report
14 fixed5 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
What command compiles an agentic workflow markdown file into a GitHub Actions lock file, and what file extension is produced?
| Checked | Without skill | With skill |
|---|---|---|
| gh aw compile | Passed | Passed |
| Explains that compiling `.github/workflows/<name>.md` produces `.github/workflows/<name>.lock.yml`. | Missed | Passed |
The instructions your model reads when the skill loads.
Use this reference to diagnose workflows: download/analyze existing logs, audit runs, and trace failures. These reads are not an active debug loop.
Follow the shared local-first strategy for all reproduction, fixes, uploads, and live tests. This page is an evidence and CLI reference, not a separate execution policy. Respect explicit no-dispatch contexts. Apply its live-outcome table, credential triage and untrusted-evidence rules. Without accessible existing logs, use source/fixtures; never dispatch for evidence.
Require one read-only security-review agent per revision, not multiple judges.
Show the user an annotated overview of changed authored .md sources explaining
their security impacts; ignore .lock.yml diffs in that overview while retaining
generated locks as execution-review evidence. Follow the shared
single-reviewer and
annotated overview rules.
Workflow registration/activation and secret presence, validity, or expiry are runtime readiness checks, not pre-dispatch prerequisites. Do not require workflow or secret inventories or organization-admin metadata access. An otherwise authorized dispatch and the workflow's startup/authentication checks determine readiness; report their failures without automatic enabling, provisioning, or dispatch retries. Missing readiness metadata alone is not a safety finding. Declared credential flows, authorized destinations, permissions, source/lock review, and human live-validation gates remain in scope.
The user may grant explicit session authorization for bounded in-scope debug iterations without repeated approval. Re-review every changed source/lock revision; any compiler security warning invalidates the grant and requires fresh authorization after resolution.
For workflow updates, recommend publishing the reviewed Markdown and generated lock on a feature branch and opening a draft PR, then testing that explicit reviewed ref rather than requiring a merge or simply refusing because the changes are unpublished. Reuse an existing suitable branch or PR. The agent owns authorized preparation, compilation, publication and testing; the user owns the required live-effect authorization. Follow the shared branch-testing path. A branch or PR does not isolate secrets, queue state or outputs, and cannot
test cases passed, vs 6 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.