github-project-management
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
51
26%
Does it follow best practices?
Impact
100%
1.51xAverage score across 3 eval scenarios
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/github-project-management/SKILL.mdQuality
Discovery
32%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 identifies a clear domain (GitHub project management) and lists several capability areas, but it reads more like a tagline than a functional description. It lacks concrete actions, explicit trigger guidance ('Use when...'), and natural user-facing keywords. The term 'swarm-coordinated' is internal jargon that adds confusion rather than clarity.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user asks to create or manage GitHub issues, organize project boards, plan sprints, or track milestones.'
Replace vague category labels with concrete actions, e.g., 'Creates and assigns GitHub issues, moves project board cards between columns, sets up sprint milestones, and generates progress reports.'
Remove or clarify internal jargon like 'swarm-coordinated' and add natural user terms like 'kanban', 'backlog', 'GitHub Projects', 'labels', 'milestones'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (GitHub project management) and some actions (issue tracking, project board automation, sprint planning), but these are more like category labels than concrete actions. It doesn't specify what concrete operations are performed (e.g., 'create issues', 'move cards between columns', 'assign milestones'). | 2 / 3 |
Completeness | Describes what the skill does at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause should cap completeness at 2, and since the 'what' is also somewhat vague, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'GitHub', 'issue tracking', 'project board', and 'sprint planning' that users might naturally say. However, it misses common variations like 'kanban', 'backlog', 'milestone', 'labels', 'assignees', or specific GitHub terms like 'GitHub Projects v2'. The term 'swarm-coordinated' is internal jargon unlikely to be used by users. | 2 / 3 |
Distinctiveness Conflict Risk | The GitHub focus and mention of 'swarm-coordinated' provide some distinctiveness, but 'project management', 'issue tracking', and 'sprint planning' are broad enough to overlap with generic project management or Jira-related skills. The scope is somewhat specific but not sharply delineated. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
20%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an extremely verbose feature catalog for a hypothetical swarm-based GitHub project management system. The vast majority of commands reference 'npx ruv-swarm' with invented subcommands that don't appear to be real, documented tools, making the content largely non-actionable. The document would benefit enormously from being reduced to ~100 lines focusing on real, executable gh CLI commands with clear validation steps, moving templates and aspirational features to separate reference files.
Suggestions
Remove or drastically reduce all 'npx ruv-swarm' commands unless they reference a real, documented tool — replace with actual gh CLI commands or MCP tool calls that Claude can execute
Cut the document to under 150 lines by moving issue templates, dashboard configs, and YAML configurations to separate bundle files referenced from the main skill
Add explicit validation checkpoints to multi-step workflows (e.g., verify issue was created before adding to project board, check sync status after board-sync)
Replace the pseudo-JavaScript MCP function calls (mcp__claude-flow__swarm_init) with the actual MCP tool call syntax or remove them entirely
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 700+ lines. Massive amounts of speculative CLI commands for tools (ruv-swarm, claude-flow) that appear hypothetical. Includes extensive templates, dashboard JSON configs, and repetitive patterns that bloat the document enormously. Much content describes aspirational features rather than providing actionable instructions Claude needs. | 1 / 3 |
Actionability | Nearly all commands reference 'npx ruv-swarm github ...' with dozens of subcommands and flags that appear to be invented/hypothetical rather than documented real tools. The gh CLI commands are real but basic. The JavaScript blocks use pseudo-function-call syntax (mcp__claude-flow__swarm_init) that isn't executable. Most content describes what a tool *would* do rather than providing working, verifiable commands. | 1 / 3 |
Workflow Clarity | The 'Complete Workflow Example' section at the end provides a reasonable 5-step sequence, and some individual sections have numbered steps. However, there are no validation checkpoints, no error handling guidance, no feedback loops for when commands fail, and the batch operations (stale issue management, bulk operations) lack verification steps. The overall document is more of a feature catalog than a guided workflow. | 2 / 3 |
Progressive Disclosure | Good use of HTML <details> tags to collapse sections, and the document has clear hierarchical organization with numbered sections. However, with no bundle files, all content is crammed into one massive file. The references to external skills and documentation are present but the sheer volume of inline content (templates, configs, examples) should be split into separate files. The Quick Reference at the end is helpful. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1278 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- ruvnet/agentic-flow
- Commit
6a06854
- 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.