github-issue-solver
Skill18 starsChanged 6 months agoMITView on GitHub
Read GitHub issues, triage them, solve them using GRASP/OOAD principles, run or add tests, commit, push, open a PR linked to the issue, merge into development, and close the issue only after merge. Use when the user says /github-issue-solver, "solve issue #N", "fix GitHub issue", or "work on issue".
- Reads credentials
- Installs packages
- Commits and pushes
In this repository55 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-cost-manager-reducerSkill
- api-contract-reviewerSkill
- apps-language-rulesSkill
- cli-developerSkill
- contract-dto-consistency-reviewerSkill
- database-schema-reviewerSkill
- deep-code-reviewerSkill
- docs-managerSkill
- docs-publication-managerSkill
- feature-slice-designerSkill
- grasp-ooad-reviewSkill
- language-integratorSkill
- link-workspace-packagesSkill
- mcp-managerSkill
- migration-risk-reviewerSkill
- mobile-app-designerSkill
- mobile-app-integratorSkill
- mobile-app-product-ownerSkill
- mobile-app-reviewerSkill
- mobile-language-checkerSkill
- mobile-rulesetSkill
- mobil-ui-ux-rulesetSkill
- monitor-ciSkill
- nx-generateSkill
- nx-importSkill
- nx-pluginsSkill
- nx-run-tasksSkill
- nx-workspaceSkill
- product-owner-deciderSkill
- react-native-performance-reviewerSkill
- react-vite-performance-reviewerSkill
- release-readiness-reviewerSkill
- repo-architecture-auditorSkill
- repo-performance-guardSkill
- repository-pattern-reviewerSkill
- security-reviewerSkill
- smart-commitSkill
- supabase-api-rpc-reviewerSkill
- supabase-index-trigger-reviewerSkill
- supabase-rls-security-reviewerSkill
- supabase-schema-reviewerSkill
- tailwind-ui-ux-reviewerSkill
- ui-contract-guardSkill
- test-managerSkill
- unit-test-plannerSkill
- vite-performance-engineerSkill
- link-workspace-packagesSkill
- monitor-ciSkill
- nx-generateSkill
- nx-importSkill
- nx-pluginsSkill
- nx-run-tasksSkill
- nx-workspaceSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
34 rules. About 0 are common, 27 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈27
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 36
All comments (may contain constraints or partial solutions)
- Distinctive: line 39
If no issue number is provided, ask the user which issue(s) to target.
- Distinctive: line 48
If a duplicate exists: comment on the issue linking the canonical one, then stop.
- Distinctive: line 52
Do not assume architecture.
- Distinctive: line 106
Before writing any code:
- Distinctive: line 110
Check whether the bug is in domain, data, feature, UI, or infra layer.
- Distinctive: line 128
No duplicated domain logic across layers
- Distinctive: line 129
No unrelated refactors bundled with the fix
- Distinctive: line 130
No hardcoded temporary fixes
- Very specific: line 144
Never work on main or development directly.
- Distinctive: line 150
No doc additions unless the behavior change requires them.
- Very specific: line 151
If schema changes are needed, create a new migration file in supabase/migrations/.
- Very specific: line 152
If RLS changes are needed, invoke supabase-rls-security-reviewer first.
- Distinctive: line 153
Keep changes auditable: one logical concern per commit.
- Distinctive: line 169
Run the smallest relevant test set first:
- Distinctive: line 177
If no adequate tests exist for the fixed behavior, add them.
- Distinctive: line 179
If the fix touches database logic, run migration/RLS tests:
- Distinctive: line 186
If the fix crosses feature boundaries, run integration tests.
- Distinctive: line 188
Run broader checks if the affected area is critical (auth, billing, RLS, battle engine):
- Distinctive: line 195
If tests cannot be run, explain why and what manual verification was done.
- Very specific: line 199
Use the smart-commit skill for staged changes, or:
- Very specific: line 219
Never commit .env, secrets, or credentials
- Distinctive: line 287
Read the failure output.
- Distinctive: line 292
Do NOT merge while CI is failing.
- Distinctive: line 297
All CI checks pass
- Very specific: line 307
Use --squash only if the team's merge strategy is squash.
- Distinctive: line 323
If post-merge validation fails, open a follow-up issue immediately and do not close the original.
- Distinctive: line 327
Only after merge is confirmed and post-merge validation passes:
- Very specific: line 333
If the PR used Closes #N syntax and GitHub auto-closed the issue on merge, verify the issue is closed and add a comment with the merge …
- Distinctive: line 358
No unrelated refactors bundled in the fix
- Distinctive: line 361
No force-push to protected branches
- Distinctive: line 363
No detached HEAD states
- Distinctive: line 364
No stale branch work
- Distinctive: line 386
After completing the workflow, output:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
GitHub Issue Solver
Solve GitHub issues end-to-end: triage → explore → design → implement → test → PR → merge → close.
Never guess architecture. Never close an issue before the PR is merged.
Activation Criteria
Invoke this skill when:
- User says
/github-issue-solveror/solve-issue - User says "solve issue #N", "fix GitHub issue #N", "work on issue #N"
- User pastes a GitHub issue URL
- User asks to process open issues from the repository
Workflow
Step 1 — Fetch Issue Metadata
gh issue view <number> --json title,body,labels,milestone,assignees,comments,url,state,linkedBranchesCapture and record:
- Title and full body
- Labels (bug, feature, security, docs, performance, DX, auth, database, workflow, battle, CLI, mobile, web)
- Milestone and due date
- All comments (may contain constraints or partial solutions)
- Linked PRs or branches
If no issue number is provided, ask the user which issue(s) to target.
Step 2 — Check for Duplicates and Related Work
gh issue list --state all --search "<key terms from title>"
gh pr list --state all --search "<key terms>"If a duplicate exists: comment on the issue linking the canonical one, then stop.
Step 3 — Repository Exploration
Do not assume architecture. Explore:
apps/* — entry points and composition roots
libs/domain/* — business concepts, invariants, core types
libs/api/* — contracts and DTOs
libs/data/* — repositories, Supabase integration
libs/features/* — feature slices and orchestration
libs/infra/* — analytics, moderation, storage adapters
libs/ui/* — UI components, forms, layout, tokens
libs/utils/* — low-level shared utilities
supabase/ — schema, migrations, RLS policies, SQL functions
.github/workflows/ — CI/CD pipelines and test commands
apps/cli/ — CLI if issue is CLI-related
apps/mobile/ — mobile app if issue is mobile-related
package.json / pnpm-workspace.yaml — test and build commands
CLAUDE.md / CONTRIBUTING.md — coding standards and rules
.claude/skills/ — available AI agent skillsLoad relevant skills before implementing:
- Feature placement →
feature-slice-designer - Architecture concern →
repo-architecture-auditor - Schema change →
supabase-schema-reviewer - RLS/security →
supabase-rls-security-reviewer - Migration →
migration-risk-reviewer - Contract/DTO →
contract-dto-consistency-reviewer - Code quality →
deep-code-reviewerorgrasp-ooad-review - Performance →
vite-performance-engineer - UI/UX →
tailwind-ui-ux-reviewer - Tests →
unit-test-planner
Step 4 — Classify the Issue
Determine issue type:
| Type | Detection criteria |
bug | Unexpected behavior, crash, incorrect output |
feature | New capability or enhancement request |
security | Auth bypass, data leak, RLS gap, injection |
performance | Slow query, bundle size, N+1, memory leak |
docs | Missing or incorrect documentation |
DX | Dev tooling, CI, build, test setup |
database | Schema change, migration, RLS, index |
workflow | Battle workflow, automation, trigger |
CLI | CLI command, output, TUI |
mobile | Mobile app screen, navigation, native |
web | Web app route, UI, API integration |
A single issue may span multiple types; note all that apply.
Step 5 — Identify Root Cause
Before writing any code:
- Trace data flow from the issue symptom back to its origin.
- Identify which module owns the broken invariant.
- Check whether the bug is in domain, data, feature, UI, or infra layer.
- Confirm whether backend validation is missing (do not enforce only in frontend).
- Identify affected tests and whether they currently catch the bug.
State the root cause explicitly before designing a solution.
Step 6 — Design Solution (GRASP + OOAD)
Apply references/grasp-ooad-checklist.md.
Rules:
- Single source of truth: one place owns each business rule
- Low coupling: changes should not ripple unexpectedly
- High cohesion: related behavior stays together
- Information Expert: assign responsibility to the class/module with the required data
- Creator: the object that aggregates or uses another creates it
- Controller: one entry point handles a use case
- Backend validation: business rules enforced server-side, never frontend-only
- No duplicated domain logic across layers
- No unrelated refactors bundled with the fix
- No hardcoded temporary fixes
- No security bypasses
Design the solution in 1–3 sentences before touching any file.
Step 7 — Create a Branch
git checkout development
git pull origin development
git checkout -b fix/issue-<number>-<short-slug>
# or feat/issue-<number>-<short-slug> for featuresNever work on main or development directly. See docs/en/how-to/contributors/branching.md for naming rules and conventional commit format.
Step 8 — Implement Minimal Correct Fix
- Edit only files required to resolve the root cause.
- No opportunistic refactors.
- No doc additions unless the behavior change requires them.
- If schema changes are needed, create a new migration file in
supabase/migrations/. - If RLS changes are needed, invoke
supabase-rls-security-reviewerfirst. - Keep changes auditable: one logical concern per commit.
Step 9 — Add or Update Tests
Load references/test-discovery-checklist.md.
- Find existing test commands:
# From workspace config
cat package.json | grep -E '"test|"spec'
pnpm nx show project <affected-project> --json | jq '.targets | keys'
# From CI
cat .github/workflows/*.yml | grep -E 'run:|nx run'- Run the smallest relevant test set first:
pnpm nx test <affected-project> --testPathPattern=<related-spec>
pnpm nx typecheck <affected-project>
pnpm nx lint <affected-project>- If no adequate tests exist for the fixed behavior, add them. Do not ship without test coverage for the root cause.
- If the fix touches database logic, run migration/RLS tests:
pnpm nx test supabase --testPathPattern=<related>
# or pgTAP via supabase test db- If the fix crosses feature boundaries, run integration tests.
- Run broader checks if the affected area is critical (auth, billing, RLS, battle engine):
pnpm nx affected --target=test --base=origin/development
pnpm nx affected --target=typecheck --base=origin/developmentIf tests cannot be run, explain why and what manual verification was done.
Step 10 — Commit
Use the smart-commit skill for staged changes, or:
git add <specific-files>
git commit -m "$(cat <<'EOF'
fix(scope): concise imperative description
Root cause: <one sentence>
Closes #<issue-number>
Co-Authored-By: Claude <noreply@anthropic.com>
EOF
)"Rules:
- Conventional Commits format
- Include
Closes #Nonly when the PR fully resolves the issue - Never use
--no-verify - Never commit
.env, secrets, or credentials
Step 11 — Push and Open PR
git push -u origin <branch-name>
gh pr create \
--base development \
--title "<type>(scope): short description (fixes #N)" \
--body "$(cat <<'EOF'
## Issue
Closes #<number>
## Root Cause
<one paragraph>
## Solution
<one paragraph>
## Files Changed
- `path/to/file.ts` — what changed and why
## Tests
- [ ] Existing tests pass
- [ ] New tests added for: <what>
- [ ] Typecheck passes
- [ ] Lint passes
## Commands Run
\`\`\`bash
pnpm nx test <project> --testPathPattern=<spec>
pnpm nx typecheck <project>
\`\`\`
## Migration Notes
<!-- If schema changed -->
## Security Notes
<!-- If auth/RLS/data/provider logic changed -->
## Screenshots
<!-- If UI changed -->
## Remaining Risks
<!-- Anything not fully addressed -->
EOF
)"Load references/pr-template.md for a full PR body template.
Step 12 — Monitor CI
gh pr checks <pr-number> --watchIf CI fails:
- Read the failure output.
- Fix the root cause locally.
- Push the fix.
- Re-run failing checks.
Do NOT merge while CI is failing.
Step 13 — Merge into Development
Only after:
- All CI checks pass
- No unresolved conflicts
- No unsafe migrations
- No security regressions
- Implementation is complete
gh pr merge <pr-number> --merge --delete-branchUse --squash only if the team's merge strategy is squash. Use --rebase only if the team uses rebase. Default to --merge unless CLAUDE.md or CONTRIBUTING.md specifies otherwise.
Step 14 — Post-Merge Synchronization
git checkout development
git pull origin developmentVerify:
pnpm install --frozen-lockfile
pnpm nx typecheck <affected-project>
pnpm nx test <affected-project>If post-merge validation fails, open a follow-up issue immediately and do not close the original.
Step 15 — Close the Issue
Only after merge is confirmed and post-merge validation passes:
gh issue close <number> --comment "Fixed in PR #<pr-number> (merged into development)."If the PR used Closes #N syntax and GitHub auto-closed the issue on merge, verify the issue is closed and add a comment with the merge commit hash for traceability.
Issue Closing Rules
| Condition | Action |
| PR merged, fully resolves issue | Close with merge commit reference |
| PR merged, partial fix | Leave open, comment what remains |
| Duplicate | Link canonical issue, close as duplicate |
| Not reproducible | Comment evidence, close as invalid |
| CI fails | Do not merge, do not close |
| Post-merge test fails | Open follow-up, leave original open |
Never close an issue speculatively or before the PR merges.
Engineering Constraints
- Single source of truth — one module owns each business rule
- GRASP principles enforced — see references/grasp-ooad-checklist.md
- Backend validation for all business rules — never frontend-only
- No duplicated domain logic across layers
- No unrelated refactors bundled in the fix
- No hardcoded temporary fixes
- No security bypasses
- No force-push to protected branches
- No
--no-verifyon commits - No detached HEAD states
- No stale branch work
Failure Handling
| Failure | Response |
| Issue not found | Ask user to confirm issue number and repo |
| Cannot reproduce | State what was tried, ask for reproduction steps |
| Root cause unclear | Document exploration, ask for clarification |
| Tests fail after fix | Diagnose failure, do not suppress |
| Migration unsafe | Invoke migration-risk-reviewer, halt if risky |
| RLS regression detected | Invoke supabase-rls-security-reviewer, halt |
| CI fails | Fix before merging, never skip |
| Merge conflict | Resolve conflict, verify tests still pass |
| Post-merge regression | Open follow-up issue, link to original |
Final Report Format
After completing the workflow, output:
## GitHub Issue Solver — Final Report
### Issue
#<number>: <title>
URL: <url>
### Root Cause
<one paragraph>
### Solution
<one paragraph>
### PR
URL: <pr-url>
Branch: <branch-name>
### Merge
Commit: <hash>
Branch: development
Status: merged / failed
### Post-Merge Validation
- Install: pass / fail
- Typecheck: pass / fail
- Tests: pass / fail
- Migrations: valid / invalid
### Issue Status
Closed / Open (reason)
### Remaining Risks
<bullet list or "none">Example Triggers
/github-issue-solver 42/solve-issue 118- "Fix GitHub issue #86"
- "Work on issue #139"
- "Solve the bug reported in issue #84"
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

