publish

Publish Seed specification as GitHub Issues for team-based project management

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude-plugin/skills/publish/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable gh commands and a well-sequenced, validated workflow, but it is a long monolithic document with some redundant sections and inline template content that could be offloaded to reference files. Trimming the meta/footer material and splitting the templates would improve token efficiency and disclosure.

Suggestions

Trim or remove the 'RFC #1392 State Breadcrumb Footer' section and consolidate the Notes, which restate guidance already shown in the steps.

Move the large Epic/Task heredoc body templates into reference files (e.g. references/epic_template.md) referenced one level deep, keeping SKILL.md as a procedural overview.

Factor the repeated AskUserQuestion JSON blocks into a single documented pattern to reduce duplication.

Dimension	Reasoning	Score
Conciseness	The procedure is mostly efficient and procedural, but the ~365-line body carries redundant material — repeated AskUserQuestion JSON blocks, a restated Notes section, and the verbose 'RFC #1392 State Breadcrumb Footer' meta-section — that could be tightened.	2 / 3
Actionability	Provides fully executable gh CLI commands, heredoc issue-body templates, and a copy-paste issue-number extraction pattern, matching the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	Clear 8-step sequence with explicit validation checkpoints (gh install/auth checks, duplicate detection, plan approval) before the batch issue creation, satisfying the validation requirement for batch operations rather than capping at 2.	3 / 3
Progressive Disclosure	Well-organized into numbered steps but presented as a single 365-line monolithic file with large inline heredoc templates and no reference files, where the Epic/Task body templates could be split out to keep SKILL.md an overview.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 concise and states a concrete action, but it omits any 'Use when' trigger guidance and relies on ecosystem jargon ('Seed specification'), so every dimension lands at the middle anchor. Adding explicit activation triggers and natural keyword variations would lift it across the board.

Suggestions

Add a 'Use when...' clause with natural triggers, e.g. 'Use when the user wants to publish a seed/spec to GitHub as issues, or asks to turn a spec into team tasks.'

Expand specificity by listing concrete outputs: 'creates an Epic plus Task issues with labels, acceptance-criteria checklists, and parent/child task linking.'

Gloss 'Seed specification' with user-facing terms like 'spec' or 'project spec' so the description matches language a user would actually say.

Dimension	Reasoning	Score
Specificity	Names one concrete action ('Publish Seed specification as GitHub Issues') but lists only a single primary operation rather than multiple specific actions, matching the 'names domain and some actions' anchor rather than the multi-action level 3.	2 / 3
Completeness	Clearly states what the skill does, but provides no explicit 'Use when' trigger guidance for when Claude should activate it, which caps completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Contains some natural terms ('Publish', 'GitHub Issues') a user might say, but leans on ecosystem jargon ('Seed specification') and omits a 'Use when' clause, missing common variations like 'turn a spec into issues'.	2 / 3
Distinctiveness Conflict Risk	The described niche (Seed to GitHub issues) is fairly specific, but with no explicit distinct triggers in the description it could still overlap with other issue-creation skills.	2 / 3
	Total	8 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Q00/ouroboros
Path: .claude-plugin/skills/publish/SKILL.md
Commit: f09fa36

Reviewed: about 3 hours ago

Table of Contents

Discovery Implementation Validation

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.