github-multi-repo

Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration

2.83x

Quality

38%

Does it follow best practices?

Impact

88%

2.83x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/github-multi-repo/SKILL.md

Quality

Content

27%

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

The content is an expansive feature catalog rather than a lean skill: extremely verbose, reliant on placeholder/pseudocode examples, lacking validation checkpoints for risky batch operations, and monolithic with no progressive disclosure. It scores low on token efficiency and organization despite offering a broad command reference.

Suggestions

Cut the body to a concise overview and move exhaustive command catalogs and architecture patterns into separate reference files linked from SKILL.md.

Replace placeholder/pseudocode blocks (`[Parallel Multi-Repo Operations]:`, `mcp__claude-flow__...`, literal `[GitHub modes documentation]`) with executable, copy-paste-ready commands.

Add explicit validation checkpoints and error-recovery loops for batch/destructive operations (e.g. verify tests pass, then create PR; on failure, report and halt).

Dimension	Reasoning	Score
Conciseness	The body runs ~870 lines with repetitive feature-showcase command blocks for dozens of subcommands and conceptual padding Claude already knows ("swarm intelligence", "intelligent dependency resolution"), matching the level-1 anchor of a verbose, padded document that explains concepts unnecessarily.	1 / 3
Actionability	It includes many concrete bash/gh CLI commands, but key blocks are non-executable placeholders or pseudocode such as `[Parallel Multi-Repo Operations]:`, `Task(...)`, `mcp__claude-flow__swarm_init(...)`, and literal `[GitHub modes documentation]` content strings, fitting the level-2 anchor of some concrete guidance with incomplete/pseudocode details.	2 / 3
Workflow Clarity	Multi-step batch operations (clone, update, test, commit, push, PR across many repos) are sequenced but lack explicit validation checkpoints, rollback, or error-recovery feedback loops; per the guidelines, missing validation for batch/destructive operations caps workflow clarity at 2.	2 / 3
Progressive Disclosure	The skill is a single monolithic ~870-line SKILL.md with no bundle files, no separate reference documents, and no "See X.md" navigation, so all detail is inline, matching the level-1 anchor of a monolithic wall of text with poor organization.	1 / 3
	Total	6 / 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 identifies a specific niche but relies on abstract domain nouns and jargon ("AI swarm orchestration") rather than concrete actions and natural user trigger terms, and it omits any explicit "Use when" guidance. It sits at level 2 across all dimensions: adequate but not exemplary.

Suggestions

Rewrite with concrete verbs, e.g. "Synchronize dependencies, align package versions, and coordinate PRs across multiple GitHub repositories".

Add a trigger clause: "Use when coordinating changes, syncing versions, or managing architecture across multiple repositories."

Drop buzzwords like "AI swarm orchestration" in favor of terms users would actually say ("coordinate repos", "sync packages").

Dimension	Reasoning	Score
Specificity	The description names a concrete domain ("Multi-repository coordination, synchronization, and architecture management") but the actions are abstract gerunds rather than specific concrete operations, so it matches the level-2 anchor of naming a domain and some actions without being comprehensive.	2 / 3
Completeness	The description answers "what" (multi-repo coordination, synchronization, architecture management) but provides no "Use when..." or equivalent trigger clause for when to invoke it, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Terms like "multi-repository coordination" and "synchronization" are recognizable but "AI swarm orchestration" is jargon users would not naturally say, and common phrasings ("sync my repos", "coordinate changes across repos") are missing, fitting the level-2 anchor of some relevant keywords with missing variations.	2 / 3
Distinctiveness Conflict Risk	"Multi-repository coordination" defines a relatively clear niche, but the buzzword-heavy framing and overlap with general GitHub/sync skills mean it could still conflict with similar skills, matching the level-2 anchor.	2 / 3
	Total	8 / 12 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
skill_md_line_count	SKILL.md is long (875 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: ruvnet/agentic-flow
Path: .claude/skills/github-multi-repo/SKILL.md
Commit: d069fff

Reviewed: about 11 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.