CtrlK
BlogDocsLog inGet started
Tessl Logo

github-project-management

Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

68

1.51x
Quality

52%

Does it follow best practices?

Impact

100%

1.51x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/github-project-management/SKILL.md

The canonical home for this skill is github-project-management in ruvnet/agentic-flow

SKILL.md
Quality
Evals
Security

Quality

Content

38%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 body is command-rich and covers many real workflows, but it is a bloated 1,240-line monolith with significant redundancy, non-executable pseudo-tool-call blocks, and unverified third-party CLI invocations. Destructive/batch operations lack validation checkpoints, and no progressive disclosure structure exists at all.

Suggestions

Split the body into a lean SKILL.md overview plus one-level-deep reference files (e.g., references/issue-templates.md, references/board-config.md, references/sprint-planning.md) and delete the redundant Quick Start / Complete Workflow / Quick Reference overlap.

Add explicit validation checkpoints before destructive/batch operations (e.g., dry-run or list-only preview before 'gh issue close', '--close-duplicates', and 'board-bulk'; confirm counts before batch edits).

Replace the pseudo-code 'mcp__claude-flow__*' and 'mcp__github__*' blocks with either real executable commands or clearly-labeled optional tool-call sequences, and mark which 'npx ruv-swarm' subcommands are verified vs. aspirational.

DimensionReasoningScore

Conciseness

The ~1,240-line body is noticeably verbose and redundant: Quick Start, 'Complete Workflow Example', and 'Quick Reference Commands' restate the same commands, and full issue templates, board-mapping YAML, and dashboard JSON configs are inlined wholesale. Not 1 because it is command-dense rather than explaining concepts Claude already knows.

2 / 5

Actionability

Concrete 'gh' CLI commands appear throughout, but the ```javascript blocks (e.g. 'mcp__claude-flow__swarm_init { topology: "star", maxAgents: 3 }') are non-executable pseudo-representations of tool calls, and dozens of 'npx ruv-swarm github <subcommand>' invocations are presented with no indication they are real, verified commands. This sits between concrete and pseudocode.

3 / 5

Workflow Clarity

The 'Complete Workflow Example' provides a clear numbered 5-step sequence, but destructive and batch operations (auto-closing stale issues at 37 days, '--close-duplicates', 'board-bulk', 'issues-batch --parallel') lack any validation, dry-run, or verification checkpoints. Per the judging guidelines this caps workflow clarity at 3; most other sections are unordered command catalogs rather than sequenced workflows.

3 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and this is a monolithic single file inlining content that clearly belongs in separate files (four issue templates, board-sync mapping config, dashboard/view configs, GitHub Actions workflow). The '<details>' sections provide some navigation structure, which keeps it above the incoherent-monolith anchor, but the inline-vs-split placement is a clear anchor-2 failure.

2 / 5

Total

10

/

20

Passed

Description

66%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.

A solid, mostly specific description that names the domain and three concrete capability areas with natural trigger keywords. Its main weakness is the complete absence of a 'Use when...' clause (capping completeness at 3) plus buzzword padding ('Comprehensive', 'swarm-coordinated') that adds no information.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to manage GitHub issues, project boards, sprints, milestones, or asks about agile/kanban workflow setup with gh'.

Remove buzzword padding like 'Comprehensive' and the vague 'swarm-coordinated' qualifier; replace with concrete sub-actions (triage, decompose, label automation) or drop them.

Include common synonyms users would actually say ('agile', 'kanban', 'backlog', 'milestones') in the description itself rather than only in frontmatter tags.

DimensionReasoningScore

Specificity

Names the domain ('GitHub project management') and three concrete capability areas ('swarm-coordinated issue tracking, project board automation, and sprint planning'), matching the 'several specific actions; minor gaps' anchor. Not 5 because 'Comprehensive' and 'swarm-coordinated' are buzzword padding rather than additional concrete actions; not 3 because it lists more than 1-2 actions.

4 / 5

Completeness

The 'what' is clear (issue tracking, board automation, sprint planning) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. The 'when' is entirely absent, not merely weak.

3 / 5

Trigger Term Quality

'GitHub', 'project management', 'issue tracking', 'project boards', and 'sprint planning' are natural phrases users would say, giving good keyword coverage. A few natural terms are missing (e.g., 'agile', 'kanban', 'backlog', 'milestone' appear only in frontmatter tags), so it does not reach comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

'GitHub project management' with issue tracking, project boards, and sprint planning carves a mostly distinct niche with natural triggers. Minor overlap risk remains with closely related skills such as 'github-pr-workflow' and 'github-release-management' listed in related_skills.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

14

/

16

Passed

Repository
ruvnet/RuView
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.