Run any Skill in Manus with one click

gh-actions-diagnostics

Stars3

Forks0

UpdatedJune 7, 2026 at 03:10

Diagnose GitHub Actions failures with gh by tracing failing runs, jobs, and step logs. Trigger on CI red/failing checks, flaky workflows, rerun decisions, or release pipeline breakages.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

bryanbarton525

bryanbarton525/prism

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

4 files

SKILL.md

readonly

name	gh-actions-diagnostics
description	Diagnose GitHub Actions failures with gh by tracing failing runs, jobs, and step logs. Trigger on CI red/failing checks, flaky workflows, rerun decisions, or release pipeline breakages.
compatibility	Requires GitHub CLI and workflow log visibility; collector can auto-download gh into ~/.cache/prism/bin (set GH_VERSION / GH_BIN / PRISM_BIN_DIR).
metadata	{"prism-agents":"github-cli"}

GH Actions diagnostics

Inputs expected

Workflow name, run URL/ID, branch/SHA, or PR number.
Desired scope (latest failure vs historical flake pattern).

Command workflow (gh CLI)

Locate candidate runs.
- gh run list --limit 20
- gh run list --branch <branch> --limit 20
- gh run list --workflow "<workflow>" --limit 20
Inspect failing run details and jobs.
- gh run view <run-id>
- gh run view <run-id> --json jobs,conclusion,createdAt,updatedAt,headSha,event,workflowName
Pull failing logs.
- gh run view <run-id> --log-failed
- For full context: gh run view <run-id> --log
Pattern-match root causes.
- Infra/transient: timeouts, network, rate limits.
- Deterministic: test assertion, migration mismatch, unknown flags.
- Config drift: missing secrets/env/permissions.
Recommend next action.
- rerun safe? (transient)
- patch required? (deterministic/config)
- handoff target (k8s/argo/docs) if failure is downstream.

Output requirements

summary: short root-cause hypothesis with confidence.
findings: failing job, failing step, first concrete error, recurrence signal.
artifacts: include run/job IDs and key log snippets.
confidence: high when error is explicit and reproducible; medium/low otherwise.

Guardrails

Do not trigger reruns or workflow dispatch without explicit approval.
Clearly separate observed evidence from hypotheses.
If repo/run identifiers are missing, return insufficient_evidence with a callback request to parent for exact run URL/ID.
Do not output fabricated file paths, run IDs, or generic placeholders as observed evidence.

More from this repository

same repository

verify

bryanbarton525/prism

Build, launch, and drive prism's real surfaces (CLI, MCP stdio server, downstream MCP bridge, benchmarks) to verify changes end-to-end.

2026-07-153

argo-sync-health

bryanbarton525/prism

Diagnose Argo CD app sync/health drift with argocd (and kubectl when needed). Trigger on OutOfSync, Degraded, failed sync hooks, or unexpected desired/live diffs.

2026-06-073

argo-workflow-debug

bryanbarton525/prism

Debug Argo Workflow failures with argo CLI by tracing nodes, retries, template errors, and timing. Trigger on failed/hanging workflows, extract-step errors, or regression after upgrades.

2026-06-073

docs-source-harvest

bryanbarton525/prism

Harvest authoritative docs for a target library/service and extract implementation-ready guidance with citations. Trigger on "how do I use/configure X" and API/reference requests.

2026-06-073

frontend-localstorage

bryanbarton525/prism

Implement vanilla JS todo logic with localStorage persistence and deterministic state updates.

2026-06-073

frontend-readme

bryanbarton525/prism

Write concise README instructions for opening and testing static HTML/CSS/JS apps locally.

2026-06-073

name	gh-actions-diagnostics
description	Diagnose GitHub Actions failures with gh by tracing failing runs, jobs, and step logs. Trigger on CI red/failing checks, flaky workflows, rerun decisions, or release pipeline breakages.
compatibility	Requires GitHub CLI and workflow log visibility; collector can auto-download gh into ~/.cache/prism/bin (set GH_VERSION / GH_BIN / PRISM_BIN_DIR).
metadata	{"prism-agents":"github-cli"}

GH Actions diagnostics

Inputs expected

Workflow name, run URL/ID, branch/SHA, or PR number.
Desired scope (latest failure vs historical flake pattern).

Command workflow (gh CLI)

Locate candidate runs.
- gh run list --limit 20
- gh run list --branch <branch> --limit 20
- gh run list --workflow "<workflow>" --limit 20
Inspect failing run details and jobs.
- gh run view <run-id>
- gh run view <run-id> --json jobs,conclusion,createdAt,updatedAt,headSha,event,workflowName
Pull failing logs.
- gh run view <run-id> --log-failed
- For full context: gh run view <run-id> --log
Pattern-match root causes.
- Infra/transient: timeouts, network, rate limits.
- Deterministic: test assertion, migration mismatch, unknown flags.
- Config drift: missing secrets/env/permissions.
Recommend next action.
- rerun safe? (transient)
- patch required? (deterministic/config)
- handoff target (k8s/argo/docs) if failure is downstream.

Output requirements

summary: short root-cause hypothesis with confidence.
findings: failing job, failing step, first concrete error, recurrence signal.
artifacts: include run/job IDs and key log snippets.
confidence: high when error is explicit and reproducible; medium/low otherwise.

Guardrails

Do not trigger reruns or workflow dispatch without explicit approval.
Clearly separate observed evidence from hypotheses.
If repo/run identifiers are missing, return insufficient_evidence with a callback request to parent for exact run URL/ID.
Do not output fabricated file paths, run IDs, or generic placeholders as observed evidence.