github-ci-debug

Diagnose failing GitHub Actions runs from bounded run, job, and step evidence, propose a focused fix, and modify the local checkout only when the requested task includes implementation.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./examples/plugin-packages/github/.opencode/skills/github-ci-debug/SKILL.md

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-organized for a simple skill, but the local-verification step is vague and the workflow lacks an explicit validate-and-retry feedback loop.

Suggestions

Specify the local check command or how to choose it (e.g. "re-run the failing job's local equivalent: `npm test`, `pytest`, etc.") so step 6 is executable.

Add an explicit validate->fix->retry loop: after running the local check, if it fails, fix and re-run before summarizing.

Clarify the `actions-failure` call form (expected arguments / service name) so step 2 is concrete rather than named-only.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept explanations Claude already knows ("Resolve the repository and Actions run ID from the supplied URL, PR, or current branch context"), so every token earns its place; matches the score-3 anchor.	3 / 3
Actionability	Steps name concrete targets ("Call `actions-failure`", "implement it locally"), but "run the relevant local check" leaves the specific command unspecified and the tool invocation lacks syntax, so key details are missing; matches the score-2 anchor rather than 3.	2 / 3
Workflow Clarity	A clear numbered sequence is present with a local-check checkpoint at step 6, but there is no explicit validate->fix->retry loop and the recovery path is only implicit; matches the score-2 anchor and is not a 3 because feedback loops are not spelled out.	2 / 3
Progressive Disclosure	The skill is under 50 lines, needs no external references, and is organized into clear Workflow and Guardrails sections; per the simple-skills scoring note this matches the score-3 anchor. No bundle files exist to verify.	3 / 3
	Total	10 / 12 Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and clearly scoped to GitHub Actions debugging, but it lacks an explicit "Use when..." trigger clause and is missing several natural keyword variations a user might say.

Suggestions

Add an explicit trigger clause, e.g. "Use when a GitHub Actions run fails or the user asks why CI is red."

Include natural keyword variations users actually say, such as "CI failure", "build broken", or "failing checks".

Soften the clinical phrasing ("bounded run, job, and step evidence") into more user-natural trigger language.

Dimension	Reasoning	Score
Specificity	"Diagnose failing GitHub Actions runs from bounded run, job, and step evidence, propose a focused fix, and modify the local checkout only when the requested task includes implementation" lists multiple concrete actions (diagnose, propose fix, conditionally modify checkout), matching the score-3 anchor; it is not a 2 because it goes beyond naming a domain plus a few actions.	3 / 3
Completeness	The "what" is explicit but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Terms like "failing GitHub Actions runs" and "run, job, and step" are natural, but common variations users would say (e.g. "CI failure", "build broken", "red X") are missing and the phrasing is somewhat clinical, matching the score-2 anchor.	2 / 3
Distinctiveness Conflict Risk	The skill is tightly scoped to GitHub Actions failures with a clear niche and distinct triggers, making it unlikely to fire for the wrong skill; matches the score-3 anchor.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Devin-AXIS/iPolloWork
Path: examples/plugin-packages/github/.opencode/skills/github-ci-debug/SKILL.md
Commit: bd5caef

Reviewed: about 14 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.