agent-github-pr-manager
Agent skill for github-pr-manager - invoke with $agent-github-pr-manager
43
13%
Does it follow best practices?
Impact
94%
1.08xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-github-pr-manager/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an extremely weak description that fails on all dimensions. It reads as a placeholder or auto-generated stub, providing only the skill's internal name and invocation command without any information about capabilities, use cases, or trigger conditions. It would be nearly impossible for Claude to correctly select this skill from a pool of available skills.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Creates, reviews, merges, and manages GitHub pull requests, adds reviewers, checks PR status, and resolves merge conflicts.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about pull requests, PRs, code reviews, merging branches, or GitHub repository management.'
Remove the invocation instruction ('invoke with $agent-github-pr-manager') from the description as it wastes space that should be used for capability and trigger information.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for github-pr-manager' is entirely vague and does not describe what the skill actually does (e.g., create PRs, review PRs, merge PRs, etc.). | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states it's an 'agent skill' and how to invoke it, providing no functional or trigger information. | 1 / 3 |
Trigger Term Quality | The only potentially relevant term is 'github-pr-manager' which is a tool name, not a natural keyword a user would say. Missing natural terms like 'pull request', 'PR', 'review', 'merge', 'GitHub', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so generic that it provides no distinguishing characteristics. Without knowing what the skill does, it could conflict with any GitHub-related skill and offers no clear niche. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is overly verbose and descriptive rather than actionable, explaining many concepts Claude already understands (merge strategies, PR best practices, what CI/CD is). While it includes some useful gh CLI commands, much of the content describes capabilities abstractly ('spawn specialized review agents') without concrete implementation. The monolithic structure with no external references and missing validation checkpoints in workflows further weaken its effectiveness.
Suggestions
Cut at least 60% of the content by removing explanations of concepts Claude already knows (merge strategy definitions, what PR descriptions should contain, generic best practices) and focus only on project-specific conventions and concrete commands.
Make the multi-agent coordination section actionable by providing specific commands or code to spawn and coordinate review agents, rather than abstract descriptions like 'Spawn specialized agents'.
Add explicit validation checkpoints to workflows, e.g., after 'Run automated checks' add 'If checks fail: diagnose with `gh pr checks`, fix issues, push, and re-verify before proceeding'.
Split the PR description template, error handling strategies, and multi-agent coordination into separate referenced files to improve progressive disclosure and reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive content Claude already knows (what merge strategies are, what PR descriptions should contain, basic gh CLI commands). The PR description template, best practices, and multi-agent coordination sections are largely generic knowledge that wastes tokens. Much of this reads like documentation for humans, not actionable instructions for Claude. | 1 / 3 |
Actionability | The gh CLI commands section provides some concrete, executable commands, and the workflow patterns give numbered steps. However, much of the content is descriptive rather than instructive ('Spawns specialized review agents', 'Coordinates security reviews') without specifying how to actually do these things. The 'multi-agent coordination' and 'review swarm' concepts reference capabilities that aren't concretely defined. | 2 / 3 |
Workflow Clarity | Multiple workflow patterns are listed with numbered steps, but they lack validation checkpoints and feedback loops. For example, the Standard Feature PR workflow says 'Run automated checks' but doesn't specify what to do if checks fail. The error handling section mentions recovery strategies but doesn't integrate them into the workflows. No explicit validate-then-proceed gates. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. All content—from basic commands to templates to multi-agent coordination—is inlined in a single document. The PR description template, detailed review coordination guidelines, and error handling could all be split into separate referenced files. No navigation structure beyond flat headings. | 1 / 3 |
Total | 6 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ruvnet/ruflo
- Commit
ccb062f
- 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.