fusion-issue-task-planning

Plan and break down user-story issues into ordered, traceable task issue drafts with explicit publish gates.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/fusion-issue-task-planning/SKILL.md

Quality

Content

73%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 a well-sequenced, validation-rich workflow with concrete delegated contracts and good asset separation; its main weaknesses are repetition of the publish-gate/draft-only rules and a somewhat long inlined procedural body.

Suggestions

Consolidate the publish-gate and draft-only rules into a single authoritative section and reference it from steps 6, 7, and 9 instead of restating them.

Move the per-mode orchestration detail (orchestrated/direct-subordinate/inline) into a short matrix or a referenced asset to slim the inlined body.

Clarify the cross-skill reference to agents/devils-advocate.agent.md by noting it lives in fusion-issue-authoring, so the navigation path is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is dense and procedural without explaining known concepts, but the publish-gate and draft-only rules are restated across steps 1, 6, 7, 9, and the safety section, so it is mostly efficient with redundancy that could be tightened (anchor 3).	3 / 5
Actionability	Instruction-only yet concrete: names tools (mcp_github::sub_issue_write), file paths (.tmp/TASK-<nn>-<slug>.md, assets/task-plan-template.md), delegated contracts, and post-flight fields, giving mostly executable guidance with minor gaps (anchor 4).	4 / 5
Workflow Clarity	Ten sequenced steps with a devil's-advocate checkpoint, publish gates, post-flight verification, idempotent repair, feedback loops on partial failure, and an explicit ambiguity checklist match anchor 5 for a batch/destructive operation with validation.	5 / 5
Progressive Disclosure	A clear overview signals one-level-deep references to real asset files (follow-up-questions.md, task-plan-template.md, verified present), but the long inlined procedural body and one cross-skill reference (agents/devils-advocate.agent.md) leave minor organization gaps (anchor 4).	4 / 5
	Total	16 / 20 Passed

Description

58%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 is specific and distinct, clearly stating what the skill does, but it lacks an explicit "Use when…" trigger clause and natural user-facing keywords, capping completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to plan tasks for, break down, or split a user story into task issue drafts."

Include natural user phrasings and synonyms ("break this story into steps", "create task issues", "plan tasks for #123") alongside the technical terms.

Consider naming file/issue references users mention (e.g. "GitHub user-story issue") to sharpen trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Plan and break down user-story issues into ordered, traceable task issue drafts with explicit publish gates" names the domain plus several specific actions (plan, break down, order, trace, gate publishing), matching anchor 4 rather than 5 which requires broader comprehensive coverage.	4 / 5
Completeness	The description gives a clear "what" but contains no "Use when…" trigger clause, so per the judging guidelines a missing explicit trigger guidance caps completeness at 3 (clear what, when missing).	3 / 5
Trigger Term Quality	Terms like "user-story issues", "task issue drafts", and "publish gates" are domain-relevant but jargon-leaning and miss natural synonyms users would actually say (e.g. "split", "create tasks"), fitting anchor 3 (some relevant keywords, missing common variations).	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche (user-story task planning with publish gates) but has minor overlap risk with the closely related sibling skills fusion-issue-authoring and fusion-issue-author-task, matching anchor 4.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: equinor/fusion-framework
Path: .agents/skills/fusion-issue-task-planning/SKILL.md
Commit: 5b70066

Reviewed: 2 days 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.