github

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./bot/workspace/skills/github/SKILL.md

The canonical home for this skill is github in mitsuhiko/agent-stuff

Quality

Content

86%Weight 40%Scale 1-5

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

A tight, token-efficient command reference with fully executable examples and clean organization that suits its small scope. Its only weakness is slightly uneven coverage — issue and PR-mutation commands are thin relative to what the description promises.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient: short section headers ('## Pull Requests', '## JSON Output') followed immediately by executable commands, with no explanation of concepts Claude already knows. The single framing sentence ('The `gh api` command is useful for accessing data not available through other subcommands') earns its place by signaling when to reach for the API. It is above 4 because nothing here is padding or over-explanation.	5 / 5
Actionability	Every example is a concrete, executable command with sensible placeholders ('gh pr checks 55 --repo owner/repo', 'gh run view <run-id> --repo owner/repo --log-failed'), covering the common CI-diagnostic cases. Not 5 because coverage has minor gaps: issues get only one example (in the JSON section), and common operations like creating a PR, commenting, or viewing issue details are not shown despite the description advertising `gh issue`.	4 / 5
Workflow Clarity	The commands are grouped under clear headings and ordered in a sensible implicit diagnostic sequence (check CI status → list runs → view a failed run → fetch failed-step logs). It is above 3 because the sequence is coherent and all commands are read-only so no validation checkpoints are needed, but not 5 because it presents a collection of snippets rather than one single unambiguous action or an explicit multi-step workflow.	4 / 5
Progressive Disclosure	The skill is under 50 lines, self-contained, and needs no external references; content is organized into three well-labeled sections (Pull Requests, API for Advanced Queries, JSON Output) with each snippet scannable. Per the simple-skill guideline, this warrants 5.	5 / 5
	Total	18 / 20 Passed

Description

66%Weight 40%Scale 1-5

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 concise, concrete, and tool-specific, with clear command-to-capability mapping. Its main weakness is the complete absence of any 'when to use' trigger guidance, which caps completeness at 3, alongside some missing natural synonyms in its trigger terms.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions GitHub, pull requests, issues, CI/Actions runs, or needs repository data via the gh CLI.'

Include common synonyms in the trigger terms — 'pull requests' (not just PRs), 'GitHub Actions', 'workflows', 'repositories' — so the description fires on natural user phrasing.

Optionally round out the action list (e.g. repos, releases, gists) to move specificity from several-actions toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — 'Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries' — mapping specific commands to specific domains. It falls short of 5 because coverage is not comprehensive (no mention of repos, releases, gists, or auth), and above 3 because it goes well beyond naming 1-2 actions with generic verbs.	4 / 5
Completeness	The 'what' is clear (interact with GitHub via the gh CLI for issues, PRs, CI runs, and advanced queries), but there is no 'Use when...' clause or any equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is above 2 because the 'what' half is concrete and specific, not vague.	3 / 5
Trigger Term Quality	It includes natural terms users would say — 'GitHub', 'issues', 'PRs', 'CI runs', 'advanced queries' — giving good keyword coverage. Not 5 because common synonyms and variations are missing: 'pull requests', 'GitHub Actions', 'repositories', 'check runs', 'workflow runs'.	4 / 5
Distinctiveness Conflict Risk	'Interact with GitHub using the `gh` CLI' carves out a distinct niche with tool-specific triggers (gh, GitHub, CI runs) and minimal conflict risk. Not 5 because 'Interact with GitHub' is broad and could mildly overlap with generic git-related or CI-related skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: volcengine/OpenViking
Path: bot/workspace/skills/github/SKILL.md
Commit: b2f1f9d

Reviewed: 3 days 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.