Fusion Issue Solving
Run a repeatable issue-to-PR workflow with scoped work, MCP-first lookups, validation gates, and a PR-ready summary.
Overview
Fusion Issue Solving is an agent skill most often used in Build (also Ship, Operate) that executes a 12-step checklist from scoped issue work through validation to a PR-ready summary.
Install
npx skills add https://github.com/equinor/fusion-skills --skill fusion-issue-solvingWhat is this skill?
- 12-step issue-solving checklist from scope confirmation through follow-ups
- Branch/worktree strategy and single capture of issue metadata for reuse
- MCP tools preferred over redundant API lookups
- Rate-limit fallback plan that forbids retry loops
- Targeted validation plus required repository checks before PR summary
Adoption & trust: 1k installs on skills.sh; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have a tracked issue but no consistent way to scope work, avoid redundant API calls, validate changes, and land a merge-ready PR without policy violations.
Who is it for?
Indie builders or small teams fixing GitHub issues in repos with strict validation, MCP integrations, and documented PR policies.
Skip if: Exploratory spikes with no issue ID, one-line typo fixes where you already have an approved spec and CI green without needing a workflow ritual.
When should I use this skill?
You are executing an Equinor Fusion issue-solving workflow on a scoped ticket that will end in a PR.
What do I get? / Deliverables
You finish with implemented scoped changes, passing targeted and repo-required checks, a PR-ready summary, and documented blockers—then follow local repo policy for commit and PR creation.
- Actionable todo plan
- Scoped code/test/doc changes
- PR-ready summary with blockers noted
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Build because the skill drives scoped implementation and inspection before merge, even though it hands off to Ship checks. PM subphase fits tracking issue scope, todos, blockers, and handoff metadata—the control plane around the actual code change.
Where it fits
Break a Fusion-core issue into todos after confirming scope and capturing metadata once.
Implement scoped backend changes after inspecting tests and docs tied to the ticket.
Run targeted validation plus mandatory repo checks before claiming the issue is done.
Draft a PR-ready summary that lists what changed and what still blocks merge.
Log open follow-ups when rate limits or policy handoffs pause the fix mid-stream.
How it compares
Structured issue-to-PR ritual instead of ad-hoc “fix it in chat” without scope, validation, or policy handoff.
Common Questions / FAQ
Who is fusion-issue-solving for?
Solo and indie developers (and small squads) who ship from issue trackers and want agent steps aligned with branch strategy, MCP usage, validation, and PR hygiene.
When should I use fusion-issue-solving?
During Build when implementing a ticket; during Ship when running required checks and preparing the PR; during Operate when recording blockers and follow-ups after a partial fix.
Is fusion-issue-solving safe to install?
Review the Security Audits panel on this Prism page and your org’s fusion-skills source before granting MCP, git, or network access to your agent.
SKILL.md
READMESKILL.md - Fusion Issue Solving
# Issue Solving Checklist Use this checklist while executing the issue-solving workflow. | Step | Notes | | --- | --- | | [ ] Confirm issue scope and out-of-scope | | | [ ] Decide branch/worktree strategy | | | [ ] Capture issue metadata once and reuse | | | [ ] Prefer MCP tools and avoid redundant API lookups | | | [ ] Define rate-limit fallback plan (no retry loops) | | | [ ] Build actionable todo plan | | | [ ] Inspect relevant code/tests/docs | | | [ ] Implement scoped changes | | | [ ] Run targeted validation | | | [ ] Run required repository checks | | | [ ] Prepare PR-ready summary | | | [ ] Record blockers/open follow-ups | | # Changelog ## 0.1.7 - 2026-05-07 ### patch - [#170](https://github.com/equinor/fusion-skills/pull/170) [`5e43223`](https://github.com/equinor/fusion-skills/commit/5e432232917b2b1642431d80cf1698bbefe80ee8) - Apply caveman-compress prose style to SKILL.md. - Drop articles, filler, hedging from SKILL.md activation body ## 0.1.6 - 2026-03-24 ### patch - [#126](https://github.com/equinor/fusion-skills/pull/126) [`1470bc8`](https://github.com/equinor/fusion-skills/commit/1470bc81e1b04e9727049f01742ea881579ad57b) - Add repository-policy handoff section for governance alignment - Add explicit "Repository-policy handoff" section that defers commit, validation, changeset, and PR rules to repo-local instructions Resolves equinor/fusion-core-tasks#581 ## 0.1.5 - 2026-03-17 ### patch - [#85](https://github.com/equinor/fusion-skills/pull/85) [`c8ba3df`](https://github.com/equinor/fusion-skills/commit/c8ba3df924c5a712c835cdb9f4de44bac03b7ad4) - Make all GitHub-API-consuming skills more conservative with token usage. - `fusion-issue-authoring`: concrete session-cache flow for labels and assignee candidates; per-session budget table - `fusion-issue-solving`: expanded low-token strategy with session-cache references and budget awareness - `fusion-github-review-resolution`: token budget guidance for thread-heavy reviews; cache PR metadata once - `fusion-issue-task-planning`: session-cache delegation rules and batch-size warning for large task plans - `fusion-dependency-review`: explicit data-reuse rules across parallel advisor fan-out - `fusion-discover-skills`: tighter GraphQL budget and call-count cap for discovery sessions resolves equinor/fusion-core-tasks#797 ## 0.1.4 - 2026-03-11 ### patch - [#76](https://github.com/equinor/fusion-skills/pull/76) [`3efc478`](https://github.com/equinor/fusion-skills/commit/3efc47886871a14b18eb9f68abd562a10c6cf277) - Improve issue-solving workflow reliability under GitHub API limits by documenting a low-token execution strategy. - Require reuse of fetched issue context instead of repeated reads - Add MCP-first guidance for issue workflow mutations and lookups - Add explicit no-retry-loop behavior for rate-limit failures - Extend the workflow checklist with token-usage and fallback controls resolves equinor/fusion-core-tasks#535 ## 0.1.3 - 2026-03-11 ### patch - [#71](https://github.com/equinor/fusion-skills/pull/71) [`b7fe258`](https://github.com/equinor/fusion-skills/commit/b7fe2581ba6bab7325d953c44b853a2a94ba65da) - Strengthen issue-solving discovery cues for short prompts and direct GitHub issue URLs. - move representative activation phrases into the frontmatter description so semantic routing can match `solve #123`, `lets solve #123`, and full `https://github.com/owner/repo/issues/123` prompts - clarify that direct GitHub issue URLs can stand in for `#123` references, including URL-first prompts resolves equinor/fusion-skills#66 ## 0.1.2 - 2026-03-05 ### patch - [#55](https://github.com/equinor/fusion-skills/pull/55) [`2d346c8`](https://github.com/equinor/fusion-skills/commit/2d346c812b4927ed1fdf17c92d51856d1fdc09c3) - Add required ownership metadata (`metadata.owner`, `metadata.status`) to all skills. Owner is set to `@equinor/fusion-core` (repository default) and status is set according to skill lifec