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.

1.23x

Quality

72%

Does it follow best practices?

Impact

100%

1.23x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./apps/picooraclaw/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.

The content is a tight, command-first reference that assumes Claude's competence and provides mostly executable gh examples organized by task area. Its only weak spot is the absence of explicit validation/verification steps in the PR/CI workflows.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient — short imperatives ('Check CI status on a PR:', 'View logs for failed steps only:') followed directly by executable commands, with no explanation of what GitHub/CI is or how gh works; every token earns its place.	5 / 5
Actionability	Commands are concrete and copy-paste ready (e.g. 'gh pr checks 55 --repo owner/repo', 'gh run view <run-id> --log-failed') covering common cases, but the '<run-id>' placeholder and 'owner/repo' are not fully concrete, leaving minor gaps versus a fully-specified 5.	4 / 5
Workflow Clarity	Sections are clearly organized by task (PRs, workflow runs, API, JSON output) with a useful progress path from listing runs to viewing to failed logs, but there are no explicit validation/verification checkpoints (e.g. 'confirm checks pass before merge'), which keeps it at 4.	4 / 5
Progressive Disclosure	This is a simple single-purpose skill under 50 lines with no bundle files (references/, scripts/, assets/ are absent), so the well-organized section headers and inline command examples fully satisfy progressive disclosure per the simple-skill exception.	5 / 5
	Total	18 / 20 Passed

Description

58%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 specific and names concrete gh subcommands with their domains, giving it strong action clarity, but it lacks an explicit 'when to use this' trigger clause and relies on technical subcommand names rather than natural user phrases. This caps completeness at 3 and limits trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when working with GitHub issues, pull requests, CI/Actions runs, or when the user mentions GitHub.'

Surface natural user-facing phrases ('pull requests', 'GitHub Actions', 'CI checks', 'GitHub API') alongside the subcommand names to improve trigger-term quality.

Optionally note scope boundaries (e.g., repo/gist/release management) to distinguish from a generic git skill and push distinctiveness toward 5.

Dimension	Reasoning	Score
Specificity	Quotes concrete actions via specific subcommands ('gh issue', 'gh pr', 'gh run', 'gh api for issues, PRs, CI runs, and advanced queries'), naming multiple specific capabilities with only minor coverage gaps (e.g., no mention of gist/release/repo management).	4 / 5
Completeness	The 'what' is clearly stated (interact with GitHub via gh subcommands) but there is no explicit 'when' / 'Use when...' trigger clause, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	It lists GitHub domain terms ('issues, PRs, CI runs') but these are subcommand outputs rather than natural user phrasing; common variations a user would actually say ('GitHub PRs', 'check my CI', 'GitHub Actions') are partially covered but synonyms are thin, so it sits at 3 rather than 4.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche around the gh CLI and its subcommands, mostly distinct from generic git/file skills with only minor overlap risk against a plain git skill; it is not a perfect 5 because the trigger is not explicit enough to fully disambiguate.	4 / 5
	Total	14 / 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: oracle-devrel/oracle-ai-developer-hub
Path: apps/picooraclaw/workspace/skills/github/SKILL.md
Commit: 3afe8ec

Reviewed: 1 day 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.