CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-pr-manager

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

48

3.94x
Quality

Does it follow best practices?

Impact

75%

3.94x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

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 body is a reasonably organized, code-heavy reference for PR management with swarm coordination, but it mixes an embedded definition block with redundant prose and offers examples that are only partially executable. Workflows lack explicit validation gates for risky merge operations, and everything lives in one monolithic file.

Suggestions

Add explicit validation checkpoints to the merge workflow (e.g. verify PR checks pass and review approval before merge, with a retry-on-failure loop) so workflow clarity can rise above 2.

Make code examples consistent and executable — use the actual mcp__claude-flow__github_* tool names that match the declared tools, or prefer the real gh CLI commands already shown in the batch section.

Trim redundancy between the embedded YAML block, the 'Capabilities' list, and 'Usage Patterns' to tighten token efficiency.

DimensionReasoningScore

Conciseness

The body is mostly lists and code rather than prose, but it carries redundancy — the embedded YAML definition block plus a separate 'Capabilities' section that restates the 'Usage Patterns', and some bullet points that overlap — so it is efficient-ish but not lean enough for a 3.

2 / 3

Actionability

It provides concrete guidance via real gh CLI commands and TodoWrite examples, but the MCP call blocks use inconsistent/non-existent tool prefixes (mcp__github__ vs mcp__claude-flow__github_*) and pseudo-JSON syntax that is not copy-paste executable, leaving the examples partly incomplete.

2 / 3

Workflow Clarity

Usage patterns are numbered (1, 2, 3) and a batch lifecycle is laid out, but for destructive/batch operations like merges there are no explicit validate-then-proceed checkpoints; the 'Error Handling' section describes retry conceptually without a feedback loop, capping clarity at 2 per the rubric.

2 / 3

Progressive Disclosure

There are no bundle files (references/scripts/assets absent) and no external file references, so all content sits inline in one ~150-line document; the sections are clearly headed and organized, but long code blocks that could be split out remain inline, which is 'some structure but could be better organized'.

2 / 3

Total

8

/

12

Passed

Description

7%

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 essentially a placeholder label — it identifies the skill's name and invocation command but conveys no capabilities, use cases, or natural triggers. It fails to inform a user or Claude when or why to invoke it.

Suggestions

Replace the description with concrete actions, e.g. 'Manages pull requests: creates PRs, runs multi-agent code reviews, validates tests, and merges with squash. Use when the user asks to create, review, test, or merge a pull request.'

Add an explicit 'Use when...' clause with natural trigger terms users would actually say (e.g. 'open a PR', 'review my pull request', 'merge this branch').

Keep third person and avoid the circular 'agent skill for pr-manager' phrasing; describe what it does, not what it is named.

DimensionReasoningScore

Specificity

The phrase 'Agent skill for pr-manager' names no concrete actions at all; it only labels what the skill is, matching the vague 'Helps with documents' anchor rather than any action-listing example.

1 / 3

Completeness

It states neither what the skill concretely does (the 'for pr-manager' label is circular) nor any 'Use when...' guidance, and the rubric caps completeness at 2 for a missing explicit trigger — here both what and when are effectively missing.

1 / 3

Trigger Term Quality

The only trigger-like term is the literal command 'invoke with $agent-pr-manager', which is technical invocation syntax rather than natural language a user would say, so it offers no usable keyword coverage.

1 / 3

Distinctiveness Conflict Risk

The token 'pr-manager' names a specific enough niche to be somewhat distinguishable, but the generic 'Agent skill for ...' framing gives no distinct triggers, so it could still overlap with other development skills.

2 / 3

Total

5

/

12

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/claude-flow
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.