CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-github-pr-manager

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

59

1.08x
Quality

39%

Does it follow best practices?

Impact

94%

1.08x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

The canonical home for this skill is agent-github-pr-manager in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

Quality

Content

61%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 well-structured, mostly concise overview with executable gh CLI commands, but workflow steps are largely prose rather than commands and lack the validation checkpoints required for destructive/batch merge operations. Progressive disclosure is reasonable for a standalone file but could separate the template and workflow patterns.

Suggestions

Add explicit validation checkpoints before destructive actions, e.g. 'Verify all status checks pass before merging' and 'Re-validate after rebasing an outdated branch'.

Make workflow steps executable by pairing each step with the concrete gh command (e.g., 'Create PR: gh pr create --title ... --base main') instead of prose.

Clarify or remove vague claims like 'Automated resolution for simple cases' merge conflicts, or point to a concrete conflict-resolution procedure.

DimensionReasoningScore

Conciseness

The body is well-organized with tight headers and lists, mostly avoiding explanations of concepts Claude already knows; minor redundancy where the capability list echoes the frontmatter block keeps it just below a 5.

4 / 5

Actionability

Concrete gh CLI commands and a PR template are provided, but the workflow steps are prose ('Create PR with detailed description') rather than executable commands, and items like 'Automated resolution for simple cases' are hand-wavy, leaving gaps.

3 / 5

Workflow Clarity

The Standard/Hotfix/Large-Feature workflows are sequenced, but merging, auto-merge, admin-override merge, and rollback are destructive/batch operations with no validation checkpoints (e.g., verifying all checks pass before merge), which caps this dimension at 3 per the rubric.

3 / 5

Progressive Disclosure

No bundle files exist and the single SKILL.md is organized into clear sections (Purpose, Workflows, CLI Integration, Error Handling); it is a ~150-line monolith with some content (PR template, multiple workflow patterns) that could be split out, leaving minor organization gaps.

4 / 5

Total

14

/

20

Passed

Description

17%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 generic boilerplate that names the skill domain but provides no concrete capabilities or natural trigger terms, and lacks any 'use when' guidance. It would not reliably drive correct activation over similarly-named skills.

Suggestions

Replace the boilerplate with concrete actions, e.g. 'Creates, reviews, and merges pull requests using the gh CLI, coordinates multi-stage reviews, and manages merge strategies.'

Add an explicit 'Use when...' trigger clause naming natural user phrases such as 'pull request', 'create a PR', 'merge a branch', 'code review', or 'resolve merge conflicts'.

Drop the 'invoke with $agent-github-pr-manager' technical token from the user-facing description in favor of third-person capability and trigger language.

DimensionReasoningScore

Specificity

The phrase 'Agent skill for github-pr-manager' names the domain but lists no concrete actions (no mention of creating PRs, coordinating reviews, merging, etc.), matching the score-2 anchor of minimal/generic actions.

2 / 5

Completeness

It offers only a vague 'what' ('Agent skill for github-pr-manager') and no 'when' trigger clause; both what and when are essentially missing or vague, fitting the score-2 anchor.

2 / 5

Trigger Term Quality

The only guidance is 'invoke with $agent-github-pr-manager', a technical invocation token rather than natural keywords a user would say; no trigger phrases like 'pull request', 'merge', or 'code review' appear.

1 / 5

Distinctiveness Conflict Risk

The boilerplate 'Agent skill for <name>' pattern is generic across many skills, with no specific capability language to distinguish it, creating high overlap risk.

2 / 5

Total

7

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/ruflo
Reviewed

Table of Contents

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.