fusion-issue-task-planning

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

Quality

70%

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

81%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.

This is a well-engineered procedural skill: an ordered ten-step workflow with explicit gates, degradation modes, failure handling, and idempotent repair, plus real, well-signaled asset references. The main improvements are tightening repeated delegation instructions and moving the long step-6/step-9 detail into reference files, with a worked draft example adding the last increment of actionability.

Dimension	Reasoning	Score
Conciseness	The body is dense and procedural with no explanations of concepts Claude already knows ('Tool names follow <mcp_server>::<tool>', mode taxonomy, explicit file naming). It is not a 5 because the delegation-to-fusion-issue-authoring rule is restated in steps 7, 9, 10, the Common failures section, and Safety & constraints, which could be tightened.	4 / 5
Actionability	Guidance is concrete and executable: exact draft paths ('.tmp/TASK-<nn>-<slug>.md'), a three-way mode taxonomy with per-mode behavior, the exact context fields to pass on delegation, and per-issue post-flight report fields. It stops short of 5 only because there is no worked example of a task draft or a filled ambiguity checklist.	4 / 5
Workflow Clarity	The ten steps are clearly ordered with explicit validation checkpoints: the devil's-advocate ambiguity checklist before drafting, a publish gate requiring confirmation or explicit risk acceptance, post-flight verification with per-issue statuses, idempotent repair mode, and batch/rate-limit warnings. Despite involving batch GitHub mutations, validation and feedback loops are thoroughly present, matching the anchor-5 example's structure.	5 / 5
Progressive Disclosure	Section headers are clear, and both referenced assets (assets/follow-up-questions.md, assets/task-plan-template.md) are real files, signaled at point of need and listed in an Assets section. It is not a 5 because steps 6 and 9 carry substantial inline detail (ambiguity-signal checklist, delegation/budget rules) that would fit better in a one-level-deep reference file, keeping the main body leaner.	4 / 5
	Total	17 / 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 states a clear, concrete 'what' with domain-specific language, but entirely lacks a 'when to use' trigger clause and misses several natural trigger phrasings. Adding an explicit 'Use when...' sentence with common user phrasings would raise both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to plan tasks, break a user story into steps, or create task issue drafts from a story issue.'

Include natural synonyms and phrasings users would actually say ('split this story', 'task planning', 'create sub-tasks') to broaden trigger-term coverage.

Optionally mention the draft-first/publish-gated safety posture ('drafts stay local until confirmed') to further distinguish the skill from generic planning and issue-authoring skills.

Dimension	Reasoning	Score
Specificity	The description names several concrete actions — 'Plan and break down user-story issues into ordered, traceable task issue drafts with explicit publish gates' — covering decomposition, ordering, traceability, and gating. It falls short of a 5 because it omits verification, repair, and issue-linking capabilities that the skill actually performs.	4 / 5
Completeness	The 'what' is clear (plan and break down user stories into task drafts with publish gates), but there is no 'Use when...' clause or equivalent explicit trigger guidance. Per the judging guidelines, a missing 'when' clause caps completeness at 3.	3 / 5
Trigger Term Quality	It includes relevant keywords ('user-story', 'task issue', 'plan', 'break down', 'drafts') but misses common natural variations users would say, such as 'task planning', 'create tasks from a story', or 'split this story'. Coverage is comparable to the anchor-3 example of relevant-but-incomplete keywords rather than the good-with-a-few-missing level of 4.	3 / 5
Distinctiveness Conflict Risk	'User-story task planning with explicit publish gates' carves a fairly distinct niche; it is mostly distinguishable from generic planning or issue-authoring skills with only minor overlap risk (e.g., a sibling issue-authoring skill). It is not a 5 because 'plan' and 'task' alone are broad enough to invite overlap with general planning skills.	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: e026972

Reviewed: 5 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.