CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-pr-manager

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

53

3.94x
Quality

35%

Does it follow best practices?

Impact

75%

3.94x

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-pr-manager/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

53%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 reasonably structured and gives concrete examples for a PR-management workflow, but it is padded with redundant sections and its code examples are inconsistent or malformed. Destructive merge operations lack the explicit validation checkpoints the rubric requires.

Suggestions

Add an explicit validation checkpoint before merge, e.g. verify `gh pr checks` passes and conflicts are resolved before running `gh pr merge`.

Fix the malformed/placeholder code examples: replace "$" path separators, resolve the :owner/:repo vs hardcoded ruvnet inconsistency, and align tools with the declared tool list.

Trim redundancy: merge the Capabilities bullets into the Purpose section and remove restated best-practice bullets that duplicate the Usage Patterns.

DimensionReasoningScore

Conciseness

The body is mostly efficient and does not explain concepts Claude already knows, but the Capabilities list restates the Purpose line and the hardcoded ruvnet/ruv-FANN/pull-54 examples plus repeated best-practice bullets add padding that could be tightened.

3 / 5

Actionability

Concrete MCP tool calls and gh CLI commands are provided, but they are inconsistent and partly malformed (e.g., "src$index.js", mixed :owner/:repo placeholders with hardcoded values, mcp__github__ tools absent from the declared tool list), leaving gaps that prevent copy-paste execution.

3 / 5

Workflow Clarity

Sequences for create/review/merge are present with TodoWrite tracking, but this is a destructive/batch skill (merges) and the workflows lack explicit validation checkpoints before merge (e.g., confirm CI passes), which caps workflow clarity at 3 per the rubric.

3 / 5

Progressive Disclosure

No bundle files exist and the single SKILL.md is well-organized with clear section headers (Purpose, Capabilities, Usage Patterns, Best Practices, Integration, Error Handling); the only gap is that verbose API-call examples are inlined rather than split out.

4 / 5

Total

13

/

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 frontmatter description is effectively a stub: it tells Claude how to invoke the skill but not what it does or when to use it. Natural trigger terms and concrete capabilities are entirely absent.

Suggestions

Rewrite the description to state concrete actions, e.g. "Manages pull requests: creates, reviews, tests, and merges PRs with coordinated agents."

Add an explicit "Use when..." trigger clause naming natural terms users say: pull requests, PRs, code review, merging branches.

Remove the invocation-token framing ("invoke with $agent-pr-manager") from the description and keep it focused on what + when.

DimensionReasoningScore

Specificity

The description only names the domain ("pr-manager") and an invocation token ("invoke with $agent-pr-manager") without stating any concrete actions; it is below the 3-anchor which requires 1-2 concrete actions, but above entirely-vague because it identifies the domain.

2 / 5

Completeness

It gives a vague identity ("Agent skill for pr-manager") and a weak invocation hint but no clear statement of what the skill does or when to use it; the "when" is missing and the "what" is essentially absent, sitting between the missing-both and vague-what anchors.

2 / 5

Trigger Term Quality

The only keyword is the technical invocation token "$agent-pr-manager"; there are no natural phrases a user would say (e.g., "pull request", "PR", "merge", "review"), matching the "only technical jargon" anchor.

1 / 5

Distinctiveness Conflict Risk

Beyond the identifier "pr-manager", nothing distinguishes its trigger niche from other dev/PR skills, and no trigger context is provided, placing it at very-broad/high-overlap risk just above entirely-generic.

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.