fusion-issue-solving

Handles GitHub issue resolution end-to-end for prompts like "solve #123", "lets solve #123", "work on #123", "work on https://github.com/owner/repo/issues/123", or by pasting a direct GitHub issue URL as the request. USE FOR: solve #123, continue work on issue #123, work on https://github.com/owner/repo/issues/123, paste a GitHub issue URL for implementation work. DO NOT USE FOR: issue drafting only, PR review only, or non-implementation research.

Quality

76%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/fusion-issue-solving/SKILL.md

Quality

Discovery

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description with excellent trigger term coverage and completeness, including both positive and negative use-case boundaries. Its main weakness is that the actual capabilities (what concrete steps it performs during 'end-to-end' resolution) could be more specific—listing actions like reading the issue, writing code, creating branches, or opening PRs would strengthen it. Overall it would perform well in a multi-skill selection scenario.

Suggestions

Replace 'end-to-end' with specific concrete actions like 'reads the issue, implements code changes, runs tests, and creates a pull request' to improve specificity.

Dimension	Reasoning	Score
Specificity	It names the domain (GitHub issue resolution) and describes the general action ('end-to-end' resolution, 'implementation work'), but doesn't list multiple specific concrete actions like reading the issue, writing code, creating a PR, running tests, etc. The phrase 'end-to-end' is somewhat vague about what steps are actually performed.	2 / 3
Completeness	Clearly answers both 'what' (handles GitHub issue resolution end-to-end for implementation work) and 'when' (explicit USE FOR and DO NOT USE FOR clauses with specific trigger phrases). The negative boundary conditions (DO NOT USE FOR) add extra clarity.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would actually type: 'solve #123', 'work on #123', 'continue work on issue #123', GitHub issue URLs, and pasting direct URLs. These closely match real user phrasing patterns.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with clear niche (GitHub issue resolution/implementation), explicit trigger patterns (#123, issue URLs), and explicit exclusions (not for issue drafting, PR review, or research) that reduce conflict with adjacent skills.	3 / 3
	Total	11 / 12 Passed

Implementation

62%

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-structured orchestration skill with strong workflow clarity and good safety constraints. Its main weaknesses are moderate verbosity (especially in trigger examples and rate-limiting details) and a lack of concrete executable examples—commands, tool invocations, or code snippets that would make the guidance more immediately actionable. The progressive disclosure is adequate but could be improved by extracting detailed API strategy guidance into a separate reference file.

Suggestions

Add concrete examples of MCP tool invocations or specific commands for key steps (e.g., reading an issue, running validation, creating a PR) to improve actionability.

Extract the detailed rate-limiting and API budget strategy (step 4) into a separate reference file like `assets/api-strategy.md` to reduce inline verbosity and improve progressive disclosure.

Trim the 'When to use' trigger list to 3-4 representative examples since the pattern is clear from the first few entries.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably well-structured but includes some unnecessary verbosity. The 'When to use' section repeats many trigger examples that overlap with the frontmatter description. The rate-limiting details in step 4 (GraphQL mutation costs, specific call budgets) are useful but border on over-specification. Some sections like 'When not to use' and the extensive trigger list could be trimmed.	2 / 3
Actionability	The workflow provides clear procedural steps and specific guidance (e.g., draft PR body in `.tmp/pr-body-issue-123-scope-summary.md`, use `.github/pull_request_template.md`), but lacks executable code examples or concrete command snippets. Steps like 'Run targeted checks first' and 'Inspect relevant files' remain somewhat abstract without specifying exact commands or tool invocations.	2 / 3
Workflow Clarity	The 10-step workflow is clearly sequenced with logical dependencies, includes explicit validation checkpoints (step 8: 'If checks fail, fix relevant issues and re-run before proceeding'), confirmation gates before mutations (step 10), and feedback loops for error recovery. The workflow handles rate-limit failures gracefully with fallback strategies. Each step has clear entry/exit criteria.	3 / 3
Progressive Disclosure	The skill references an asset file (assets/issue-solving-checklist.md) and mentions delegation to 'fusion-issue-authoring' skill, but no bundle files are provided to verify these references exist. The main content is fairly long (~120 lines) and some sections like the detailed rate-limiting strategy in step 4 could be extracted to a referenced file. The structure is reasonable but could benefit from better separation of concerns.	2 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: equinor/fusion-framework
Commit: 060e3af

Reviewed: about 8 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.