CtrlK
BlogDocsLog inGet started
Tessl Logo

github-project-management

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

48

Quality

52%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/github-project-management/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%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 highly detailed and command-rich but suffers from pervasive `$`-for-`/` corruption that breaks many code blocks and URLs, excessive redundancy across ~1244 lines, and a complete absence of validation checkpoints for destructive/batch operations. It is a monolithic document with no bundle files despite being far too long to keep in one file.

Suggestions

Fix the pervasive character corruption (replace stray `$` with `/` in URLs, paths, and HTML closing tags like `</strong>`, `</summary>`, `</details>`, and `2>$dev$null` -> `2>/dev/null`) so code blocks and links are actually executable.

Add explicit validation/verification checkpoints before destructive and batch steps — e.g., preview the stale-issue list, confirm counts, and verify sync results before closing issues or moving cards.

Split inlined material into one-level-deep bundle files (issue templates, command reference, workflow YAML) and reference them from a lean SKILL.md overview to improve progressive disclosure and conciseness.

DimensionReasoningScore

Conciseness

The body runs ~1244 lines with many near-identical, redundant `npx ruv-swarm github <subcommand>` blocks and repeated patterns (e.g., board-init appears multiple times, similar issue-create blocks recur), matching the anchor for noticeably verbose with several padded sections; not a 1 because it does not explain basic concepts Claude already knows (what GitHub is).

2 / 5

Actionability

Substantial concrete commands and code are provided, but a meaningful fraction is corrupted and non-executable (`$` substituted for `/` in URLs/paths like `https:/$github.com/$GITHUB_REPOSITORY$issues/$issue`, `.github$swarm-labels.json`, `2>$dev$null`) and the `mcp__claude-flow__swarm_init { ... }` blocks are pseudocode rather than real call syntax; matches the anchor for some concrete guidance but incomplete.

3 / 5

Workflow Clarity

Sequences exist (the numbered Complete Workflow Example), but batch and destructive operations — auto-closing stale issues, `--close-duplicates`, bulk card operations — have no validation/verification checkpoints, so workflow clarity is capped at 3 per the feedback-loop rule.

3 / 5

Progressive Disclosure

Section headers and collapsible `<details>` blocks give some structure and in-file progressive disclosure, but content that clearly belongs in separate files (issue templates, the full command reference, workflow YAML) is inlined and no bundle files or one-level-deep references exist; matches the anchor for some structure with content that should be separate left inline.

3 / 5

Total

11

/

20

Passed

Description

62%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 description clearly states what the skill does across three capability areas using natural trigger terms, but it omits any explicit "Use when..." trigger clause, which caps completeness. Distinctiveness is moderate given the family of related GitHub skills.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when managing GitHub issues, project boards, sprints, or coordinating multi-agent work on a repository.'

Include natural synonyms/variants users might say (GitHub Projects, kanban, agile, backlog grooming) to improve trigger-term coverage.

Sharpen distinctiveness by contrasting with sibling skills, e.g. '...for board and sprint coordination (not PR or release workflows).'

DimensionReasoningScore

Specificity

Names the domain and lists three concrete capability areas — "swarm-coordinated issue tracking, project board automation, and sprint planning" — which matches the anchor for several specific actions with minor gaps; not a 5 because the actions are fairly high-level categories rather than granular operations, and "swarm-coordinated" is partly buzzword.

4 / 5

Completeness

There is a clear "what" but no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the judging guidelines; the "when" is only weakly implied.

3 / 5

Trigger Term Quality

Natural terms a user would say are present ("GitHub project management", "issue tracking", "project board", "sprint planning"), giving good coverage; not a 5 because synonyms and variants (e.g., GitHub Projects, kanban, agile, .yml) are absent and "swarm-coordinated" is jargon users would not naturally say.

4 / 5

Distinctiveness Conflict Risk

The description is somewhat specific to GitHub project management with a swarm-coordination angle, but it could still overlap with closely related skills (github-pr-workflow, github-release-management) and nothing sharply distinguishes it; not a 4 because overlap risk with sibling GitHub skills remains.

3 / 5

Total

14

/

20

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 — 13 / 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

relative_links

Relative link issues: 4 suspicious

Warning

Total

13

/

16

Passed

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.