agent-github-modes

Agent skill for github-modes - invoke with $agent-github-modes

1.07x

Quality

—

Does it follow best practices?

Impact

86%

1.07x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

50%

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

The body presents a well-organized catalog of GitHub integration modes with usage strings and example invocations, but it is padded with descriptive metadata, lacks executable copy-paste commands, and provides no validation feedback loops for its batch operations. It scores 2 across all dimensions.

Suggestions

Trim repetitive spec metadata fields ('Coordination Mode', 'Max Parallel Operations', 'Batch Optimized: Yes') that do not change what Claude does, keeping only actionable detail.

Replace the notational usage examples ('$github pr-manager "..."') with concrete, executable gh/git shell commands Claude can run directly.

Add explicit validation/verification checkpoints for the batch operations section (e.g. verify PR state with 'gh pr view' before merging, re-run checks on failure), since batch/destructive operations require feedback loops.

Split the per-mode reference material into a bundled reference file referenced one level deep from the SKILL.md overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is a ~150-line catalog padded with repetitive spec-like metadata ('Coordination Mode: Hierarchical', 'Max Parallel Operations: 10') and descriptive marketing text rather than lean instructions, fitting anchor 2; it is not the lean token-efficient content of anchor 3.	2 / 3
Actionability	It gives usage strings ('$github pr-manager <PR management task>') and tool lists plus two example invocations, but these are notational/pseudocode rather than copy-paste executable shell, matching anchor 2's 'some concrete guidance but incomplete'.	2 / 3
Workflow Clarity	No multi-step workflow with validation checkpoints is provided, and batch operations are mentioned without any validate/verify feedback loops; per the scoring notes this caps workflow_clarity at 2, fitting the 'steps present but checkpoints missing' anchor.	2 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and all content is a single inline monolithic catalog under section headers rather than split into one-level-deep referenced files, matching anchor 2's 'content that should be separate is inline'.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 clearly identifies a GitHub-integration domain and lists several relevant capability areas, but it relies on high-level buzzwords and omits any explicit 'Use when' trigger guidance. It is adequate but not exemplary, scoring 2 across all dimensions.

Suggestions

Add an explicit 'Use when...' clause naming concrete user triggers, e.g. 'Use when coordinating GitHub PRs, issues, releases, or multi-repo workflows.'

Replace abstract categories ('workflow orchestration', 'batch optimization') with concrete actions users would say, such as 'create and review PRs, manage issues, coordinate releases'.

Include natural term variations users actually say (e.g. 'pull requests', 'PRs', 'GitHub Actions', 'CI/CD') to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'workflow orchestration, PR management, and repository coordination with batch optimization' name the domain and several actions, but they are high-level categories rather than concrete actions like 'create PRs' or 'merge branches', matching anchor 2 rather than the multiple-specific-actions anchor 3.	2 / 3
Completeness	The description answers 'what' (GitHub integration modes for orchestration/PR/repo coordination) but provides no 'Use when...' or equivalent explicit 'when' guidance, so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Terms 'GitHub', 'PR management', and 'repository coordination' are somewhat natural but miss common variations and explicit trigger phrasing, fitting anchor 2 rather than the full natural-term coverage of anchor 3.	2 / 3
Distinctiveness Conflict Risk	The GitHub integration niche is fairly specific, but broad terms like 'workflow orchestration' and 'PR management' could overlap with general git/PR skills, matching anchor 2 rather than the clearly-distinct-niche anchor 3.	2 / 3
	Total	8 / 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: ruvnet/claude-flow
Commit: 03d4f84

Reviewed: 2 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.