agent-pr-manager

Agent skill for pr-manager - invoke with $agent-pr-manager

3.94x

Quality

50%

Does it follow best practices?

Impact

75%

3.94x

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-pr-manager/SKILL.md

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 skill is well-sectioned and example-rich, but the examples are non-executable pseudocode with placeholder values and inconsistent tool names, and merge workflows lack explicit validation checkpoints. It is a single inline document with no progressive disclosure structure.

Suggestions

Replace placeholder MCP pseudocode with concrete, executable commands (e.g., actual `gh pr create`/`gh pr merge` invocations with real flags) and reconcile the inconsistent mcp__claude-flow__* vs mcp__github__* tool names.

Add explicit validation checkpoints before destructive operations — e.g., verify `gh pr checks` and `gh pr view --json mergeable` pass before calling merge, with a fix-and-retry loop on failure.

Move the lengthy code examples and integration details into reference files (e.g., references/examples.md) and keep SKILL.md as a lean overview that links to them.

Dimension	Reasoning	Score
Conciseness	The body is mostly example-driven and reasonably lean, but code snippets are illustrative MCP calls rather than executable commands and some sections (Best Practices, Integration, Error Handling) restate capabilities Claude already understands.	2 / 3
Actionability	It provides concrete-looking MCP call examples, but many are non-executable pseudocode with placeholder values and inconsistent tool names (mcp__claude-flow__* vs mcp__github__*), so guidance is incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	Usage patterns are numbered and sequenced, and a TodoWrite checklist appears, but there are no explicit validation checkpoints before destructive merge operations, which the rubric caps at 2 for batch/destructive workflows.	2 / 3
Progressive Disclosure	Content is organized into clear sections, but everything is inline in a single monolithic SKILL.md with no referenced bundle files, so there is no one-level-deep reference structure to navigate.	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 names a clear domain and several action categories but relies on generic phrasing and omits any explicit 'Use when' trigger guidance. It is distinguishable only moderately from general GitHub skills.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., 'Use when managing pull requests, coordinating multi-agent code reviews, or automating PR merge and test workflows').

Replace generic action categories with concrete operations (e.g., 'create and review pull requests, run test and lint checks, resolve merge conflicts, and merge via squash').

Add common trigger terms users would naturally say, such as 'PR', 'code review', 'open a pull request', and 'merge a PR'.

Dimension	Reasoning	Score
Specificity	States 'pull request management' and 'automated reviews, testing, and merge workflows', naming a domain and some actions, but the actions are generic categories rather than multiple concrete, specific operations.	2 / 3
Completeness	It answers 'what' the skill does, but there is no 'Use when...' or equivalent explicit trigger guidance for when Claude should invoke it, which caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant keywords like 'pull request', 'reviews', 'testing', and 'merge workflows' that a user would say, but misses common variations such as 'PR', 'code review', or 'open a pull request'.	2 / 3
Distinctiveness Conflict Risk	The 'swarm coordination' framing is somewhat distinctive, but 'pull request management' broadly overlaps with general git/GitHub skills and could trigger for the wrong PR-related skill.	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
Path: .agents/skills/agent-pr-manager/SKILL.md
Commit: 26c35b5

Reviewed: about 7 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.