Issue Solving Workflow
When to use
Use when the user wants to solve or continue a GitHub issue end-to-end, including short current-repo prompts like solve #123, direct GitHub issue URLs, or requests like lets work on https://github.com/owner/repo/issues/123.
Typical triggers:
Treat GitHub issue URLs as interchangeable with #123 references for verbs like solve, fix, implement, continue, finish, or work on. A direct GitHub issue URL can serve as the main request payload when no competing intent is stated.
When not to use
- Request is only issue drafting/authoring
- No implementation changes expected
- Repository write operations are disallowed
Required inputs
Collect before execution:
- issue URL or
owner/repo#number
- repository and branch/worktree decision
- acceptance criteria and out-of-scope constraints
- required validation commands for the target repository
Optional:
- related issues/PRs
- risk areas to prioritize
- requested commit/PR granularity
Instructions
Ask whether to use a dedicated git worktree
- Ask this before any other workflow questions.
- If yes, use/create the worktree and continue there.
Confirm issue context and success criteria
- Read the issue body, labels, and linked discussions once, then reuse that context instead of refetching.
- Restate the implementable scope and explicitly list out-of-scope items.
Confirm assignee intent for issue closure work
- Check whether the current user is assigned to the primary issue.
- If the current user is not assigned, ask whether they want to assign themselves before continuing.
- For each sub-issue that will be resolved or closed by this workflow, check assignee status once and reuse the result for closure decisions.
- If the current user is not assigned on a sub-issue, ask whether they want to assign themselves before resolving/closing it.
Apply low-token GitHub strategy
- Prefer MCP-backed tools over ad hoc
gh api or GraphQL calls when equivalent tools exist.
- Avoid duplicate lookups for labels, issue types, and duplicate detection.
- Cache per-run context (issue metadata, duplicate matches, issue-type support, label sets, assignee candidates) and reuse it — do not re-fetch data that was already retrieved in this session.
- When delegating to
fusion-issue-authoring or its subordinate skills, the orchestrator's session-cache rules apply: labels and assignee candidates are fetched once per repository, issue types once per organization.
- Use GraphQL fallback only when MCP coverage is unavailable and do not loop retries.
- GraphQL mutations cost 5 secondary-limit points each (vs 1 for queries); batch fields into single calls and pause at least 1 second between mutation calls.
- Budget awareness: a typical implementation session (read issue + duplicate check + 1–2 mutations + sub-issue links) should stay under ~20 MCP read calls and ~5 mutations. If the running total approaches 30+ calls, pause optional enrichment and proceed with local work.
- Respect
retry-after and x-ratelimit-reset headers; do not retry before the indicated wait.
- If rate limits are hit, stop non-essential operations and continue with local implementation/PR preparation when possible.
Build and track a concrete plan
- Create actionable todos ordered by dependencies.
- Keep exactly one step in progress and update status as work completes.
Research before edits
- Inspect relevant files, tests, and adjacent usage.
- Prefer root-cause fixes over surface patches.
Implement in small scoped changes
- Keep each change aligned to issue acceptance criteria.
- Avoid unrelated refactors and generated release artifacts.
Validate incrementally
- Run targeted checks first, then required project checks.
- If checks fail, fix relevant issues and re-run before proceeding.
Prepare PR-ready output
- Summarize what changed and why.
- Include validation evidence and known follow-ups.
- Draft the PR body in a
.tmp/ file with an issue/context-specific name (for example, .tmp/pr-body-issue-123-scope-summary.md), not a shared .tmp/pr-body.md.
- Base the draft on
.github/pull_request_template.md and keep it updated as implementation evolves.
- Ask which base branch to target and propose a likely default (typically
main, or the branch the current branch was cut from).
- Ask whether the PR should be opened as draft or ready for review.
- Ask whether the PR should be assigned to the user and whether related issues should be linked.
Optional GitHub mutation steps
- Before any GitHub mutation (create/edit/comment/close), ask for explicit user confirmation.
- If requested, update issue status/comments with objective progress.
- Prefer MCP tool mutations over ad hoc API calls when equivalent operations exist.
- If GitHub API rate limits block mutation, report the failure clearly, stop retry loops, and propose a safe retry sequence.
- If requested, create or update the PR using the repository PR template and the
.tmp/ PR body draft file, using the confirmed base branch, draft/ready state, assignee choice, and related issue links.
Expected output
Return a concise delivery report with:
- implemented scope vs original issue criteria,
- files changed,
- validation commands and outcomes,
- assignment decisions for primary issue and affected sub-issues,
- API usage strategy used (MCP-first/cache reuse/fallbacks),
- open risks/blockers,
- PR body summary (or
.tmp/ draft file path when created).
Assets
- assets/issue-solving-checklist.md
Safety & constraints
- This skill is mutation-capable. Repository-local workflow instructions take precedence over inline guidance when they conflict.
- Never request or expose secrets/credentials.
- Never run destructive commands without explicit confirmation.
- Keep changes minimal and scoped to the issue.
- Do not claim checks passed without running them.
- Follow repository instructions and contribution rules.
1---2name: fusion-issue-solving3description: '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.'4license: MIT5metadata:6 source: https://skillmd.com/skills/equinor/fusion-issue-solving7 version: "0.1.7"8 status: experimental9 owner: "@equinor/fusion-core"10 tags:11 - github12 - github-issue13 - issue-solving14 - issue-workflow15 - implementation16 - workflow17 - continue18 mcp:19 suggested:20 - github21 - mcp_fusion22---2324# Issue Solving Workflow2526## When to use2728Use when the user wants to solve or continue a GitHub issue end-to-end, including short current-repo prompts like `solve #123`, direct GitHub issue URLs, or requests like `lets work on https://github.com/owner/repo/issues/123`.2930Typical triggers:31- "lets solve #123"32- "solve #123"33- "work on #123"34- "lets work on https://github.com/owner/repo/issues/123"35- "https://github.com/owner/repo/issues/123"36- "continue work on issue #123"37- "implement issue #123 end-to-end"38- "work on this ticket: [issue URL]"39- "research, implement, and prepare a PR for this issue"4041Treat GitHub issue URLs as interchangeable with `#123` references for verbs like `solve`, `fix`, `implement`, `continue`, `finish`, or `work on`. A direct GitHub issue URL can serve as the main request payload when no competing intent is stated.4243## When not to use4445- Request is only issue drafting/authoring46- No implementation changes expected47- Repository write operations are disallowed4849## Required inputs5051Collect before execution:52- issue URL or `owner/repo#number`53- repository and branch/worktree decision54- acceptance criteria and out-of-scope constraints55- required validation commands for the target repository5657Optional:58- related issues/PRs59- risk areas to prioritize60- requested commit/PR granularity6162## Instructions63641. Ask whether to use a dedicated git worktree65 - Ask this before any other workflow questions.66 - If yes, use/create the worktree and continue there.67682. Confirm issue context and success criteria69 - Read the issue body, labels, and linked discussions once, then reuse that context instead of refetching.70 - Restate the implementable scope and explicitly list out-of-scope items.71723. Confirm assignee intent for issue closure work73 - Check whether the current user is assigned to the primary issue.74 - If the current user is not assigned, ask whether they want to assign themselves before continuing.75 - For each sub-issue that will be resolved or closed by this workflow, check assignee status once and reuse the result for closure decisions.76 - If the current user is not assigned on a sub-issue, ask whether they want to assign themselves before resolving/closing it.77784. Apply low-token GitHub strategy79 - Prefer MCP-backed tools over ad hoc `gh api` or GraphQL calls when equivalent tools exist.80 - Avoid duplicate lookups for labels, issue types, and duplicate detection.81 - Cache per-run context (issue metadata, duplicate matches, issue-type support, label sets, assignee candidates) and reuse it — do not re-fetch data that was already retrieved in this session.82 - When delegating to `fusion-issue-authoring` or its subordinate skills, the orchestrator's session-cache rules apply: labels and assignee candidates are fetched once per repository, issue types once per organization.83 - Use GraphQL fallback only when MCP coverage is unavailable and do not loop retries.84 - GraphQL mutations cost 5 secondary-limit points each (vs 1 for queries); batch fields into single calls and pause at least 1 second between mutation calls.85 - Budget awareness: a typical implementation session (read issue + duplicate check + 1–2 mutations + sub-issue links) should stay under ~20 MCP read calls and ~5 mutations. If the running total approaches 30+ calls, pause optional enrichment and proceed with local work.86 - Respect `retry-after` and `x-ratelimit-reset` headers; do not retry before the indicated wait.87 - If rate limits are hit, stop non-essential operations and continue with local implementation/PR preparation when possible.88895. Build and track a concrete plan90 - Create actionable todos ordered by dependencies.91 - Keep exactly one step in progress and update status as work completes.92936. Research before edits94 - Inspect relevant files, tests, and adjacent usage.95 - Prefer root-cause fixes over surface patches.96977. Implement in small scoped changes98 - Keep each change aligned to issue acceptance criteria.99 - Avoid unrelated refactors and generated release artifacts.1001018. Validate incrementally102 - Run targeted checks first, then required project checks.103 - If checks fail, fix relevant issues and re-run before proceeding.1041059. Prepare PR-ready output106 - Summarize what changed and why.107 - Include validation evidence and known follow-ups.108 - Draft the PR body in a `.tmp/` file with an issue/context-specific name (for example, `.tmp/pr-body-issue-123-scope-summary.md`), not a shared `.tmp/pr-body.md`.109 - Base the draft on `.github/pull_request_template.md` and keep it updated as implementation evolves.110 - Ask which base branch to target and propose a likely default (typically `main`, or the branch the current branch was cut from).111 - Ask whether the PR should be opened as draft or ready for review.112 - Ask whether the PR should be assigned to the user and whether related issues should be linked.11311410. Optional GitHub mutation steps115 - Before any GitHub mutation (create/edit/comment/close), ask for explicit user confirmation.116 - If requested, update issue status/comments with objective progress.117 - Prefer MCP tool mutations over ad hoc API calls when equivalent operations exist.118 - If GitHub API rate limits block mutation, report the failure clearly, stop retry loops, and propose a safe retry sequence.119 - If requested, create or update the PR using the repository PR template and the `.tmp/` PR body draft file, using the confirmed base branch, draft/ready state, assignee choice, and related issue links.120121## Expected output122123Return a concise delivery report with:124- implemented scope vs original issue criteria,125- files changed,126- validation commands and outcomes,127- assignment decisions for primary issue and affected sub-issues,128- API usage strategy used (MCP-first/cache reuse/fallbacks),129- open risks/blockers,130- PR body summary (or `.tmp/` draft file path when created).131132## Assets133134- [assets/issue-solving-checklist.md](assets/issue-solving-checklist.md)135136## Safety & constraints137138- This skill is mutation-capable. Repository-local workflow instructions take precedence over inline guidance when they conflict.139- Never request or expose secrets/credentials.140- Never run destructive commands without explicit confirmation.141- Keep changes minimal and scoped to the issue.142- Do not claim checks passed without running them.143- Follow repository instructions and contribution rules.