GitHub Solution Research

Use GitHub as problem-solving evidence and an implementation source. The goal is to find open-source projects and GitHub evidence that already solve the user's specific engineering problem, report the relevant project information, then translate the existing solution into a local fix, implementation path, or verification plan.

This skill is for concrete problems first. For general tool or architecture selection, use it only after the local goal has been framed as a specific capability, blocker, workflow, or integration need.

When to Use

• Runtime, build, test, deploy, package, SDK, API, dependency, framework, or integration errors.
• A feature implementation is blocked by an unclear edge case, missing usage pattern, or uncertain API behavior.
• A local issue resembles something that maintainers or other open-source users may have resolved in issues, PRs, examples, code, or release notes.
• The user asks whether GitHub/open-source projects can solve the same problem.
• Mature implementation examples or reusable projects would reduce uncertainty for one concrete capability.
• The answer should compare suitable GitHub repositories and explain how to use one with local adaptation.

Do not use for tiny edits, copy changes, local-only refactors where the codebase already dictates the answer, or requests that explicitly forbid web/GitHub research. Do not inspect private repositories unless the user explicitly scopes and authorizes that access.

Default Workflow

1. Frame the problem locally first. Capture the goal, actual symptom, error signature, reproduction path, versions, runtime, dependency/framework names, recent changes, constraints, and attempted fixes. If a discoverable fact is missing, inspect local files/logs before asking.
2. Choose the evidence mode. For errors/regressions, search issues, PRs, releases, and code first. For capability or tool needs, search repository candidates first. For feature implementation, use both repository candidates and issue/PR/code evidence.
3. Create targeted searches. Prefer exact error text, package/API names, version numbers, framework + symptom, file names, config keys, stack trace fragments, failing command names, or capability + framework/runtime/API names.
4. Find suitable GitHub projects when relevant. Prefer high-fit, high-Star, active, non-archived repositories with clear licenses and real examples. Lower the Star threshold when the high-Star set is too broad or misses the exact problem.
5. Search GitHub evidence surfaces. Use issues, PRs, discussions, code, examples, release notes, and official project docs within relevant open-source repos. Repository search is required when a project itself may solve the problem.
6. Rank by problem fit first, with Stars as a strong maturity signal. A high-Star repository is a strong candidate for inspection, but maintainer-confirmed issues, merged PRs, released fixes, official examples, and exact matching code beat popular adjacent projects. Use research-rubric.md when ranking matters.
7. Deep-read the strongest projects and evidence. Use extraction-playbook.md to extract project basics, reusable surfaces, root cause or implementation pattern, version constraints, risks, adaptation boundaries, and verification steps.
8. Translate to local work with minimal adaptation. Prefer the existing GitHub solution's public workflow, API, or architecture. Adapt only the parts required by the user's local interfaces, configuration, data/auth model, deployment target, or language/runtime.
9. If evidence is weak, say so. Do not stretch weak matches into a confident recommendation. Mark the recommendation as first-principles or local-only when GitHub evidence is insufficient.

Use scripts/github_problem_search.py when a structured GitHub search helper is useful for issue/PR/repository/code discovery. Use scripts/github_repo_research.py when repository-level candidates or reusable projects are relevant. The helpers authenticate with GITHUB_TOKEN or GH_TOKEN when set, then fall back to gh auth token from the local GitHub CLI session; do not paste or persist tokens in prompts, files, logs, or memory. If GitHub returns 403/429, read the emitted rate-limit context before retrying or reducing search breadth.

Search Strategy

• Start narrow: exact error string, exception class, CLI output, package + method name, config key, or stack trace fragment.
• Add constraints: package/framework version, language, platform, deployment target, bundler, database, auth provider, or runtime.
• Search surfaces in this order when relevant: issues/PRs/discussions, merged fixes, release notes/changelog, examples/templates, source code, then repository-level candidates.
• For implementation blockers without an error, search for the desired capability plus framework/runtime/API names.
• For public platform data needs such as trends, hot lists, topic search, or engagement metrics, do not start with visual browser scraping. First look for reusable public endpoints, open-source crawlers, archived datasets, and API field evidence; then verify the chosen source with a minimal real request and clearly separate anonymous hot-list data from logged-in search/topic data.
• For reusable project discovery, search repositories sorted by Stars, then deep-read only candidates that match the local problem. Record Stars, forks, language, license, activity, and basic content.
• Demote matches that are old, version-mismatched, archived, unresolved, speculative, or based only on user guesses.
• Use Stars/forks as supporting maturity context and tie-breakers among similarly fitting repositories. They are not proof that a solution applies.
• For security, auth, payments, infrastructure, or production operations, cross-check open-source findings against current official docs or repositories when facts may have changed.

Evidence Standard

For each serious evidence item, identify:

• exact match: same error, behavior, API, version, environment, or workflow;
• evidence strength: maintainer confirmation, merged PR, released fix, reproducible code example, test fixture, or repeated independent reports;
• applicability: what conditions must match locally for the solution to apply;
• implementation value: patch, config, API usage, dependency version, workflow, test, or operational pattern worth adapting;
• project basics when a repository is a candidate: name, URL, Stars, forks, language, license, activity, basic content, fit rationale, and adaptation cost;
• risk: stale version, unresolved issue, unsafe workaround, license concern, security/privacy impact, deployment mismatch, or overbroad change.

Output Contract

When this skill materially affects the answer, include:

• local problem profile: goal, symptom/error, versions/environment, and local constraints;
• search path: queries or discovery methods used, plus GitHub surfaces searched;
• project candidates when a GitHub project itself is relevant: repo link, Stars, forks, language, license, activity, basic content, match rationale, and how it can be used locally;
• key evidence: links to issues, PRs, code, examples, releases, or repos, with match rationale;
• recommended solution: what to reuse directly, what to adapt locally, what to avoid copying, and why it fits;
• rejected or risky options: why they do not apply or need caution;
• verification standard: test, build, reproduction command, real request, or manual check required to confirm the fix;
• confidence label when evidence is weak or no strong GitHub solution was found.

When repository-level solutions are relevant, include a compact project table. For pure issue/PR/code fixes, the table is optional, but include repository context if it affects trust or applicability.

Do not answer with only links, Stars, or popularity rankings. Do not write "common GitHub pattern" without linked evidence. Do not let external examples override local constraints.

For website, SaaS, landing-page, theme, or frontend-template candidate research, include both the repository URL and the live preview/demo URL for every serious candidate. If no preview is available or verified, state that explicitly and downgrade the candidate.

Safety Boundaries

• Prefer reading patterns and reusing existing public interfaces over copying code. If code reuse is necessary, check the license and keep attribution/obligation risks visible.
• Avoid large rewrites of an existing GitHub solution. Keep its proven flow intact and make only the local adaptations required for the user's problem.
• Avoid large verbatim excerpts from repositories, READMEs, issues, PRs, or documentation.
• Do not save GitHub tokens, cookies, private repository contents, or credentials in outputs, logs, skills, or memory.
• If network access is unavailable, state that GitHub research could not be performed and mark the recommendation as local-only.