All authors
Claude Skills by hmj1026
github.com/hmj1026111 skills0 installs78 views
- Dhpk Swift LanguageSwift language guidance for concurrency, optionals, value/reference design, property wrappers, and errors across Swift 5.10/6. Use for .swift implementation or review. Not for SwiftUI composition or iOS SDK APIs. Output: compatibility and verification decisions.Votes: 0GitHub stars: 2
- Dhpk Swift Test StrategyiOS testing strategy for Swift Testing, XCTest, UI automation, async actors, and RED-first coverage. Use when writing or reviewing iOS tests or choosing test targets. Not for non-test app code. Requires swift. Output: RED-first tests and a three-layer coverage plan.Votes: 0GitHub stars: 2
- Dhpk Swiftui ArchitectureSwiftUI architecture guidance for MVVM, Observation, navigation, state ownership, Combine, and UIKit interop. Use when building screens, view models, or routes. Requires swift. Not for iOS SDK APIs or pure Swift language work. Output: architecture and verification guidance.Votes: 0GitHub stars: 2
- Dhpk Vue 2 NotesVue 2 (^2.5.17, Options API era) component structure and the reactivity caveats that bite when mutating reactive state. Use when writing or reviewing .vue single-file components in a Vue 2 project (resources/assets/js), or a codebase whose package.json pins vue ^2.5.x. Covers the data() / computed / methods / watch + lifecycle shape, props-down + $emit events-up, vue-loader SFC compilation, the Vue.set / array-mutation traps, and @vue/test-utils 1.x + vue-jest 3 testing. Not for Vue 3 or 2.7 ...Votes: 0GitHub stars: 2
- Dhpk Xcode Build ToolingXcode / SwiftLint / xcodebuild / Swift Package Manager tooling — SwiftLint rule-tier strategy and per-package .swiftlint.yml, xcodebuild -scheme/-destination build & test vs swift build / swift test for SPM packages, and scheme / code-signing notes for a no-iCloud capability set. Use when configuring SwiftLint, deciding how to build/test an iOS app or SPM package from the CLI, interpreting the module's post-edit SwiftLint hook or pre-commit build gate, or setting up CI build commands. Not for...Votes: 0GitHub stars: 2
- LaravelLaravel framework guidance across 5.4, 6, 7, 8, 9, 10, 11, and optional Mix 5. Use when implementing or reviewing framework-touching Laravel code, planning an upgrade, or debugging a version-specific build. Not for Symfony, Yii, or frontend-only work; use dhpk-php-runtime-router for runtime selection. Output: one selected Laravel or Mix reference, compatibility constraints, and verification gates.Votes: 0GitHub stars: 2
- PhpunitUse when writing, reviewing, or migrating PHPUnit 9, 10, or 11 tests, resolving a project version, or choosing assertion, metadata, provider, mock, hook, runner, or coverage APIs. Not for PHPUnit 5/6/7-only suites, everyday assertion writing without a version decision, or Laravel routing. Output: selected version boundary, applicable reference, migration guidance, and verification evidence.Votes: 0GitHub stars: 2
- Change VerdictRead-only verdicts for code changes, pull requests, security, tests, documents, or change risk. Use when judging an existing change or evidence set. Not for implementing fixes, generating tests, editing documents, clearing gates, or architecture-only design. Output: evidence-backed findings, degradation state, and READY, BLOCKED, or INCONCLUSIVE.Votes: 0GitHub stars: 2
- Code TraceTrace unfamiliar code, diagnose a reproducible failure, investigate history, or select one code-navigation tool. Use when evidence must follow symbols, callers, data flow, regressions, or tool choice. Not for implementing a confirmed fix, reviewing a proposed diff, or plain-text/document search. Output: an evidence-backed trace, root-cause state, history report, or executable tool route.Votes: 0GitHub stars: 2
- Flow DriveExplicit-only implementation workflow for a confirmed specification or OpenSpec change whose target and acceptance contract are settled. Not for route selection, proposal authoring, review, debugging without a confirmed cause, or release. Output: ordered implementation and verification evidence, or an explicit blocker.Votes: 0GitHub stars: 2
- Flow GuideRead-only workflow guidance and bounded routing. Use when work needs a route, policy lookup, next action, closeout gate, or Codex usage help. Not for implementation, review, code tracing, or skill authoring. Output: one typed report with evidence and a clear handoff.Votes: 0GitHub stars: 2
- Harness GovernGovern a project harness through one explicit health, budget, fill, revise, or cross-platform sync mode for structure, context cost, missing infrastructure, safe trimming, or Claude-first parity. Not for application code or ordinary skill authoring. Output: mode-specific evidence, dry-run or applied-change state, and a terminal gate.Votes: 0GitHub stars: 2
- Skill ForgeCreate or refactor an agent skill, or distill repeated principles into rules after explicit authoring or maintenance invocation. Not for: skill audits, searching only, one-off rule edits, slash commands, or application code review. Output: a validated skill package or an approval-ready rules candidate report.Votes: 0GitHub stars: 2
- Skill ScopeRoute skill-governance work to health, judge, stocktake, or scout mode. Use when: auditing skill quality, comparing many skills, or searching before authoring. Not for: authoring a skill, editing a rule, or reviewing application code. Output: one mode-specific report with evidence and a clear gate.Votes: 0GitHub stars: 2
- Change VerdictRead-only verdicts for code changes, pull requests, security, tests, documents, or change risk. Use when judging an existing change or evidence set. Not for implementing fixes, generating tests, editing documents, clearing gates, or architecture-only design. Output: evidence-backed findings, degradation state, and READY, BLOCKED, or INCONCLUSIVE.Votes: 0GitHub stars: 2
- Code TraceTrace unfamiliar code, diagnose a reproducible failure, investigate history, or select one code-navigation tool. Use when evidence must follow symbols, callers, data flow, regressions, or tool choice. Not for implementing a confirmed fix, reviewing a proposed diff, or plain-text/document search. Output: an evidence-backed trace, root-cause state, history report, or executable tool route.Votes: 0GitHub stars: 2
- Flow DriveExplicit-only implementation workflow for a confirmed specification or OpenSpec change whose target and acceptance contract are settled. Not for route selection, proposal authoring, review, debugging without a confirmed cause, or release. Output: ordered implementation and verification evidence, or an explicit blocker.Votes: 0GitHub stars: 2
- Flow GuideRead-only workflow guidance and bounded routing. Use when work needs a route, policy lookup, next action, closeout gate, or Codex usage help. Not for implementation, review, code tracing, or skill authoring. Output: one typed report with evidence and a clear handoff.Votes: 0GitHub stars: 2
- Change VerdictRead-only verdicts for code changes, pull requests, security, tests, documents, or change risk. Use when judging an existing change or evidence set. Not for implementing fixes, generating tests, editing documents, clearing gates, or architecture-only design. Output: evidence-backed findings, degradation state, and READY, BLOCKED, or INCONCLUSIVE.Votes: 0GitHub stars: 2
- Code TraceTrace unfamiliar code, diagnose a reproducible failure, investigate history, or select one code-navigation tool. Use when evidence must follow symbols, callers, data flow, regressions, or tool choice. Not for implementing a confirmed fix, reviewing a proposed diff, or plain-text/document search. Output: an evidence-backed trace, root-cause state, history report, or executable tool route.Votes: 0GitHub stars: 2
- Flow DriveExplicit-only implementation workflow for a confirmed specification or OpenSpec change whose target and acceptance contract are settled. Not for route selection, proposal authoring, review, debugging without a confirmed cause, or release. Output: ordered implementation and verification evidence, or an explicit blocker.Votes: 0GitHub stars: 2
- Flow GuideRead-only workflow guidance and bounded routing. Use when work needs a route, policy lookup, next action, closeout gate, or Codex usage help. Not for implementation, review, code tracing, or skill authoring. Output: one typed report with evidence and a clear handoff.Votes: 0GitHub stars: 2
- Js Static Check StrategyProgressive `// @ts-check` per-leaf rollout playbook for legacy JS bundles. Covers the three-list legacy-globals sync (ESLint globals / TypeScript ambient .d.ts / JSDoc typedef), tsconfig exclude strategy for type-check-resistant files, leaf classification (typedef-widening-fixable vs permanent-exclude), line-anchored progress-grep traps, and Phase-2 exit-gate semantics. Use when planning a per-leaf cleanup PR, introducing a new leaf-level global, editing tsconfig''s exclude list, interpretin...Votes: 0GitHub stars: 2
- Matrix Cell OnboardChecklist + procedure for adding a new PHP / Laravel / PHPUnit / Monolog cell to a multi-major library''s CI matrix. Use when extending support to a new runtime version (e.g. "add PHP 8.3 + Laravel 12"), bumping a dep major (e.g. "Monolog 4 came out, plan the cell"), or restoring a dropped cell. Not for patch-only changes that do not alter the support matrix. Output: a cell plan with composer, workflow, polyfill, Testbench, and focused-test gates. Cross-checks `composer.json` constraints, `.g...Votes: 0GitHub stars: 2
- Code SimplifyUse when cleaning changed code for reuse, simplicity, efficiency, and the right abstraction level without changing behavior. Not for correctness review, broad redesign, or unbounded cleanup. Output: four-angle findings, applied/skipped changes, and baseline/final test evidence with degraded status when needed.Votes: 0GitHub stars: 2
- Create PrCreate a GitHub pull request from a pushed branch with ticket-aware title and body generation. Not for: committing, pushing, merging, releasing, or editing an existing PR. Output: a dry-run gh pr create command by default, or the created PR URL after explicit execution.Votes: 0GitHub stars: 2
- Dep AuditAudit dependency security risks with an evidence-only verdict and an explicitly separate fix operation. Use for dependency vulnerability review. Not for: implicit upgrades, general code review, or treating a successful fix command as clearance. Output: audit findings, optional fix status, and a read-only security verdict.Votes: 0GitHub stars: 2
- Doc RefactorUse when refactoring one bounded Markdown document while preserving its facts, policy, frontmatter, and route semantics. Not for cross-file policy changes, generated projections, or broad documentation audits. Output: the refactored path, line-count comparison, preserved-fact summary, and PASS, NOT_RUN, or BLOCKED validation.Votes: 0GitHub stars: 2
- Git Smart Commit將雜亂的 git 變更依邏輯分群、逐批提交,適用於需要把多項變更拆成多個邏輯一致 commit 的情境。Not for: 單一小變更或只需要一個 commit（直接 commit 即可）。Output: 可直接執行的分組提交計畫與 commit 指令。Votes: 0GitHub stars: 2
- Git WorktreeManage Git worktree lifecycle with exact native git targets, branch/path validation, and dirty-worktree safety. Covers adding, listing, removing, and pruning worktrees. Not for: branch merging, broad cleanup, or removing or pruning without confirmation. Output: exact commands plus resulting worktree status.Votes: 0GitHub stars: 2
- Harness AuditRun the deterministic repository harness audit and return its prioritized scorecard. Use when measuring harness health for a repository or scoped harness area. Not for: changing harness files, inventing scoring dimensions, or replacing harness governance. Output: script-owned score, findings, failed checks, top actions, and suggested skills.Votes: 0GitHub stars: 2
- Harness SetupConfigure or inspect the dhpk harness, or install selected host assets. Not for: ordinary harness audits, application changes, or silent credential/configuration changes. Output: a host-specific setup report with preserved-file, receipt, and terminal evidence.Votes: 0GitHub stars: 2
- Merge PrepPrepare a read-only branch merge analysis with native git merge-tree conflict detection and copy-pasteable manual commands. Use when deciding whether to merge one branch into another. Not for: checkout, merge, rebase, conflict edits, or branch mutation. Output: commits, files, conflicts, evidence, and manual commands.Votes: 0GitHub stars: 2
- Opsx Apply ResumeSave and resume a long-running OpenSpec apply session from a live worktree, preserving optional gates and host-specific handoff artifacts. Not for: starting a new proposal, changing the external OpenSpec workflow, or treating a commit as a prerequisite. Output: a saved/resumed handoff report with lifecycle and next-action evidence.Votes: 0GitHub stars: 2
- Pr SummarySummarize accessible open GitHub pull requests from structured gh JSON, filtering bots and grouping results by ticket. Use for a read-only PR status report. Not for: changing PR state, reviewing code, merging, or closing PRs. Output: grouped Markdown written to /tmp/pr-summary.md and displayed for copying.Votes: 0GitHub stars: 2
- PrecommitRun the deterministic pre-commit pipeline in fast or full mode through the packaged runner. Use when handing off repository changes. Not for: ad hoc replacement checks, dependency audits, or read-only verification. Output: runner-owned changed-file reporting and final verdict.Votes: 0GitHub stars: 2
- Project BriefUse when converting one readable technical specification into a PM or CTO executive brief. Not for editing the source specification or preserving implementation detail. Output: a saved executive-summary path and retained unresolved decisions.Votes: 0GitHub stars: 2
- Proposal AnalyzeUse when turning an initial proposal or proposal file into an evidence-backed implementation roadmap. Not for applying an approved OpenSpec change or writing OpenSpec artifacts. Output: validated assumptions, code-research summary, roadmap, alternatives, risks, and immediate actions.Votes: 0GitHub stars: 2
- Release CreatorCuts a new release of a software project or plugin, coordinating release configuration, version files, changelog, validation, and the fixed git/PR/tag/CI sequence. Not for: PHP package publication or ordinary commits. Output: a validated release preparation or publication result with the human merge gate preserved.Votes: 0GitHub stars: 2
- Repo VerifyRun a repository verification loop with runner-first execution, deterministic stages, and explicit PASS/FAIL/SKIP output. Use for fast or full validation of a consumer repository. Not for: mutation, fixing failures, dependency remediation, or merge approval. Output: runner summary or a complete fallback stage table.Votes: 0GitHub stars: 2
- Review PendingDelegate the current diff or explicitly selected files to an available code-reviewer and relay its report. Use for a read-only pending-change review. Not for: implementing findings, clearing a merge gate, or silently substituting another reviewer. Output: the reviewer report, or UNAVAILABLE when code-reviewer is absent.Votes: 0GitHub stars: 2
- Spec MineUse when extracting one capability’s behavioral baseline from a brownfield codebase into openspec/specs/<capability>/spec.md. Not for mining every module, refactoring, or applying a change. Output: the spec path, capability, Last verified commit, deferred files, or UNAVAILABLE when the required spec-miner role is not registered.Votes: 0GitHub stars: 2
- Tdd WorkflowFramework-agnostic test-driven development guidance for behavior-first unit and integration tests, test scaffolds, and minimal RED-GREEN-REFACTOR changes. Use when building a feature or fixing a bug test-first, writing a test scaffold, or reviewing test seams and mocks; reuse adequate test-first evidence and settled ownership. Not for: Playwright journey authoring or pure documentation or rename work. Explicit tdd-guide requirements remain binding. Output: a failing-test proof, minimal implem...Votes: 0GitHub stars: 2
- Ui Ux VerifyRead-only verification of one rendered page against one OpenSpec UI specification. Use when: checking a page against a spec, auditing a controller/action render, or reviewing UI content, structure, and behavior. Not for: E2E journey authoring, application edits, data mutation, or a runtime API smoke test. Output: one severity-ranked audit report with APPROVE, WARNING, BLOCK, or UNAVAILABLE evidence.Votes: 0GitHub stars: 2
- Update CodemapsUse after a structural change or for an explicit architecture-document refresh. Not for rewriting application source or updating user documentation outside codemaps. Output: changed $PROJECT_DIR/docs/CODEMAPS paths, scan metadata, diff percentage, and PASS, BLOCKED, or confirmation-required status.Votes: 0GitHub stars: 2
- Update DocsUse when a live route, setup, distribution, configuration, or bounded workflow change makes user or agent documentation stale. Not for source/test edits, codemap-only refreshes, policy review, or external-library research. Output: an evidence-backed document update report with PASS, NOT_RUN, BLOCKED, or Need Human handoff.Votes: 0GitHub stars: 2
- Create PrCreate a GitHub pull request from a pushed branch with ticket-aware title and body generation. Not for: committing, pushing, merging, releasing, or editing an existing PR. Output: a dry-run gh pr create command by default, or the created PR URL after explicit execution.Votes: 0GitHub stars: 2
- Harness SetupConfigure or inspect the dhpk harness, initialize its optional Review Gate, or install selected host assets. Not for: ordinary harness audits, application changes, or silent credential/configuration changes. Output: a host-specific setup report with preserved-file, receipt, and terminal evidence.Votes: 0GitHub stars: 2
- Proposal AnalyzeUse when turning an initial proposal or proposal file into an evidence-backed implementation roadmap. Not for applying an approved OpenSpec change or writing OpenSpec artifacts. Output: validated assumptions, code-research summary, roadmap, alternatives, risks, and immediate actions.Votes: 0GitHub stars: 2
- Tdd WorkflowFramework-agnostic test-driven development guidance for behavior-first unit and integration tests, test scaffolds, and minimal RED-GREEN-REFACTOR changes. Use when building a feature or fixing a bug test-first, writing a test scaffold, or reviewing test seams and mocks. Not for: Playwright journey authoring, pure documentation or rename work, or replacing dhpk''s tdd-guide dispatch. Output: a failing-test proof, minimal implementation/test change, scoped verification, and a concise TDD report.Votes: 0GitHub stars: 2