fusion-issue-authoring

Classify issue type, activate the matching agent mode for type-specific drafting, and enforce shared safety gates before GitHub mutation.

Quality

64%

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 ./.agents/skills/fusion-issue-authoring/SKILL.md

Quality

Content

77%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 a well-sequenced, actionable workflow with strong validation around destructive GitHub mutations and good deferred detail in references/assets. Its main defect is that the agent-mode routing files it depends on are referenced but not present in the bundle.

Suggestions

Add the missing `agents/*.agent.md` files (bug, feature, user-story, task, devils-advocate) to the bundle, or restructure so type-specific drafting logic lives in real files the skill actually ships.

De-duplicate the label/assignee cache policy by stating it once and cross-referencing from "Required inputs" to "Step 6".

Inline at least one minimal `mcp_github::issue_write` payload example in Step 7 so the core mutation is executable without opening references.

Dimension	Reasoning	Score
Conciseness	The body is dense but substantive with no padding about concepts Claude already knows; minor tightening is possible as the label/assignee cache policy is restated in both "Required inputs" and "Step 6".	4 / 5
Actionability	Concrete MCP tool names, an ordered mutation sequence, specific draft path `.tmp/{TYPE}-{CONTEXT}.md`, and template paths make it mostly executable; payload specifics are deferred to references/instructions.md and references/mcp-server.md, leaving minor gaps inline.	4 / 5
Workflow Clarity	An explicit 8-step sequence with validation checkpoints (duplicate check, draft review, explicit publish confirmation, shared gates) and a feedback loop (mutation failure → guide to mcp-server.md setup → retry) covers the destructive GitHub mutation workflow thoroughly.	5 / 5
Progressive Disclosure	references/ and assets/ files are real, one level deep, and clearly signaled, but the core routing targets `agents/bug.agent.md`, `agents/feature.agent.md`, `agents/user-story.agent.md`, and `agents/task.agent.md` are referenced throughout yet no `agents/` directory exists in the bundle, breaking navigation for the skill's central mechanism.	3 / 5
	Total	16 / 20 Passed

Description

51%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, third-person "what" with several concrete actions but omits any explicit "when to use" trigger guidance, which limits completeness and trigger-term quality. It is reasonably distinctive within the GitHub issue-authoring niche.

Suggestions

Append a "Use when..." clause with concrete triggers (e.g. "Use when creating or updating GitHub issues — 'create an issue', 'draft a ticket', 'turn this into a GitHub issue', adding sub-issues or setting parent links").

Replace abstract phrasing like "shared safety gates" with a more user-recognizable phrase such as "confirm labels, assignees, and draft review before publishing".

Add common synonyms/file cues (e.g. "GitHub issues, tickets, sub-issues") to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Classify issue type", "activate the matching agent mode for type-specific drafting", "enforce shared safety gates before GitHub mutation" — with only minor abstraction in "safety gates"; not quite comprehensive enough for a 5.	4 / 5
Completeness	The "what" is clear (classify, route to agent mode, enforce gates) but there is no "Use when..." or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Only generic terms ("issue", "GitHub") appear; the natural phrases users actually say ("create an issue", "draft a ticket") are absent from the description and live only in the body, so it misses the common trigger language.	2 / 5
Distinctiveness Conflict Risk	The GitHub issue-authoring niche with type-classification and agent-mode routing is mostly distinct from other skills, though the abstract phrasing and missing triggers leave minor overlap risk with general GitHub skills.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 4 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: equinor/fusion-framework
Path: .agents/skills/fusion-issue-authoring/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.