agent-github-modes

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

1.07x

Quality

26%

Does it follow best practices?

Impact

86%

1.07x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-github-modes/SKILL.md

Quality

Content

36%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 body catalogues ten GitHub coordination modes with named gh/git tools, but reads as marketing metadata rather than executable instruction: buzzword attributes, placeholder-laden examples, no sequenced workflow, and no validation for batch PR/issue operations. A stray duplicate YAML block inside the body signals malformed frontmatter handling.

Suggestions

Replace attribute tables ('Review Mode: Automated', 'Merge Strategy: Intelligent') with one concrete, copy-paste-ready command or short workflow per mode, including inputs and expected outputs.

Add a validation/feedback loop for the batch operations section (e.g., check 'gh pr checks' status and abort on failure before merging) so destructive batch steps have checkpoints.

Remove the stray second '---' frontmatter block from the body, and split per-mode detail into references/ files (e.g., modes/pr-manager.md) linked from a lean SKILL.md overview to enable progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is padded with low-information buzzword attributes ('Conflict Resolution: Intelligent', 'Review Quality: Deep', 'Versioning: Semantic', 'Conflict Prevention: Proactive') and a stray duplicate frontmatter block with echo-based hooks, none of which teaches Claude anything actionable. It is not score-1 verbose (it never explains basic GitHub concepts), but several sections are filler that could be cut or tightened.	2 / 5
Actionability	Some concrete material exists — real gh subcommands are named ('gh pr create --title ... --head ... --base ...', 'gh pr checks', 'gh workflow list') and tool lists are given per mode — but the primary usage syntax ('$github pr-manager <PR management task>') is a non-executable pseudo-invocation, and examples carry placeholders ('--body '...'', 'todo1, todo2') missing the key details. It sits between 'high-level hints' and 'mostly executable guidance'.	3 / 5
Workflow Clarity	The document is a mode catalog, not a workflow: no multi-step sequence exists anywhere, and the batch operations section (creating issues/PRs in parallel, merging) has no validation or verification checkpoints at all. Per the rubric's batch-operation cap, workflow clarity cannot exceed 3; the near-total absence of any sequence places it below that.	2 / 5
Progressive Disclosure	Sections ('GitHub Workflow Modes', 'Repository Management Modes', 'Integration Commands', 'Usage Examples') give the body recognizable structure, but ~120 lines of per-mode attribute tables and the integration examples are inlined monolithically with no bundle files or references to offload detail. The stray second '---' metadata block inside the body further muddies navigation.	3 / 5
	Total	10 / 20 Passed

Description

16%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 a placeholder: it identifies the skill's domain (GitHub) and how to invoke it, but says nothing about what it does or when to use it. It would rarely be selected by a real user query and is nearly indistinguishable from any other GitHub skill.

Suggestions

List the concrete capabilities in the description itself (e.g., 'Orchestrate GitHub workflows: create and review PRs, manage issues, cut releases, coordinate CI/CD across repositories').

Add an explicit 'Use when...' trigger clause covering natural user phrases such as 'pull request', 'PR review', 'GitHub issues', 'release', or 'repo coordination'.

Drop the meta invocation text ('invoke with $agent-github-modes') in favor of user-facing trigger vocabulary, which currently contributes no retrieval value.

Dimension	Reasoning	Score
Specificity	'Agent skill for github-modes' names the domain but lists zero concrete actions — no PR management, issue tracking, release, or CI/CD work is mentioned in the description itself. It sits above score 1 ('Helps with documents') only because the domain is named, and well below score 3, which requires 1-2 concrete actions.	2 / 5
Completeness	Neither 'what' nor 'when' is present: no capability is described ('Agent skill for github-modes' says nothing about what it does) and there is no 'Use when...' or equivalent trigger guidance — only an invocation instruction. Both dimensions are effectively missing, matching the lowest anchor; the rubric's cap of 3 for a missing trigger clause is not even approached.	1 / 5
Trigger Term Quality	The only natural keyword is 'github'; the rest is the internal invocation token '$agent-github-modes' and the label 'github-modes', which users would not say. Common natural phrases users would actually use — 'pull request', 'PR review', 'issue', 'release', 'repo' — are all missing, matching the 'one or two generic keywords; missing the natural phrases users say' anchor.	2 / 5
Distinctiveness Conflict Risk	'github-modes' is very broad and would overlap heavily with any other GitHub-related skill; nothing in the description narrows to orchestration or coordination specifically. The niche-y invocation token gives it a slight identity, keeping it above the purely generic score-1 anchor.	2 / 5
	Total	7 / 20 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/ruflo
Path: .agents/skills/agent-github-modes/SKILL.md
Commit: b14c79e

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.