Claude Skills by hmj1026

Full-stack diagnostic for agent and LLM applications — audits the 12-layer agent stack for wrapper regression, memory pollution, tool-discipline failures, hidden repair loops, and rendering corruption. Use when: shipping an agent/LLM feature, an agent degrades after adding wrapper/memory/tool layers, the same model works in the playground but breaks in your wrapper, or debugging agent behavior >15 min with no root cause. Not for: general code debugging, code review, or security scanning (use ...

Delegates git smart commit to agy-cli''s dhpk-git-smart-commit skill, offloading commit batching to Antigravity. Not for: a single simple commit, or when agy-cli is unavailable. Output: grouped commits created by agy-cli plus a git log summary.

Use when offloading a precise self-contained mechanical task to the agy CLI when available. Require target files, intent, and verification command; keep output in the agy-fast-worker subagent. Not for ambiguity, conversation-dependent work, or default fast-worker use. Output: verified edited files or honest BLOCKED evidence.

Code review using Codex MCP. Use when: PR review, code audit, or a second opinion on changes. Not for: document review (use dhpk-doc-review), security-specific audit (use dhpk-security-review), or test coverage review (use dhpk-test-review). Output: severity-ranked findings with file:line evidence, a reviewer-degradation state, and a fail-closed merge gate.

Claude Code config health check + plugin sync: audits .claude/ structure, checks naming, verifies hook setup, detects plugin version drift, and syncs installed assets. Not for: skill quality (use dhpk-skill-health-audit), code review (use dhpk-change-review). Output: health report + fix recommendations.

Trigger: explicit provider-qualified CLI dispatch-context construction and launcher execution. Avoid: direct adapter invocation or implicit role, mode, path, or authority derivation. Output: immutable dhpk.cli.context.v1 evidence or BLOCKED diagnostics.

Internal Codex and AGY CLI transport that validates an already-attested request and produces a contained terminal receipt; it never selects roles or accepts direct user invocation.

Explore an unfamiliar codebase with a focused symbol/flow trace, optionally run an independent second perspective, or request a depth-controlled explanation. Use when: tracing execution, understanding architecture, or diagnosing a code path. Not for: change review, security audit, or implementation. Output: evidence-backed flow findings with explicit gaps.

Codex architecture consulting, including bounded adversarial option convergence. Use when: designing features, evaluating architecture, comparing options, or running independent proposal and critique rounds. Not for: implementation (use dhpk-codex-implement), code review (use dhpk-change-review). Output: architecture advice + design recommendations.

Use when CODEX=on and a self-contained bulk task or blind second opinion should go to the GPT-5.6 family through one-shot codex exec: gpt-5.6-sol/high for read-only or gpt-5.6-luna/xhigh for workspace-write. Not for context-dependent or iterative work, or structured MCP codex-* review loops. Output: the bounded, redacted codex exec result.

Implement features via Codex MCP. Use when: writing new code from specs, implementing features, Codex-driven development. Not for: code review (use dhpk-change-review), architecture advice (use dhpk-codex-architect). Output: implemented code + review loop.

Composer-published package contract review. Use when: deciding semver, auditing public API or composer.json, validating Laravel package discovery, or coordinating a package release. Not for: everyday application code, language idioms, or Laravel-specific authoring mechanics. Output: a contract verdict, audited manifest, or release gate backed by the package-contract reference.

Create, update, or scan per-task request tickets for progress tracking. These are date-prefixed non-lifecycle docs under requests/, NOT feature-level requirements (use /dhpk:deep-analyze for those). Use when: tracking task progress, updating completion status, scanning incomplete requests, checking request status dashboard. Not for: feature-level problem-space analysis (use /dhpk:deep-analyze for 1-requirements.md lifecycle doc), tech specs (use dhpk-tech-spec), code implementation (use dhpk-...

Creates a new Claude Code skill, or refactors an existing one to dhpk conventions (lean SKILL.md + progressive disclosure, trigger-rich description, validation gate), from a request to "create a skill", "make a skill", "refactor this skill", or to capture a workflow as a reusable skill. Not for: writing a slash command (use command-creator) or auditing skill quality only (use /check-skill). Output: a validated skill package with an explicit diff summary and routing/verification evidence.

Compares Claude-first configuration across Codex, Antigravity, AGY native plugins, and Cursor to align cross-platform skills, commands, agents, hooks, or orchestration. Produces reviewable plans, OpenSpec tasks, dry-run/apply reports, and a configured-platform PASS/FAIL/BLOCKED validation gate (NOT_CONFIGURED/SKIP_INCOMPATIBLE stay visible without failing it; legacy PARTIAL is a deprecated compat field). Not for reverse sync, single-platform edits, or missing Claude source.

Cross-project deploy file-list generator (schema=v1). Use when: building a deploy/release checklist from git history, listing which files to ship for a deploy, 部署清單, deploy list/checklist. Scope via --anchor (in-code markers), --deploy-commits (pinned commits), or whole base..head; filters dev-only paths (tests, docs, CI, AI harness) and groups by ecosystem preset (php-yii, laravel, node, python, generic, or a custom preset). Not for: plain commit lookup (git log), raw diffs (git diff), or ac...

Portable single-entry router for dhpk work across Claude, Cursor, and Codex. Not for: bypassing a target invocation class, duplicating execution-policy, or editing external /opsx:* packages. Output: one typed route result and a terminal PASS, BLOCKED, UNAVAILABLE, or explicit-required stop.

Document review via Codex MCP. Use when: reviewing .md docs, tech spec audit, document quality check. Not for: code review (use dhpk-change-review), test review (use dhpk-test-review). Output: 5-dimension rating table + gate.

End-of-task self-check for substantive repository changes. Use after the final Edit/Write before replying or smart-commit, especially for source, SQL/repository/migration, auth/crypto/money/upload, high-volume-table, frontend/template-script, harness, policy, or documentation changes. Not for trivial typo-only edits or research/planning with no pending commit. Output: a gated wrap-up reply with changed files, verification, and risks/open questions.

Execution-policy router for dhpk software-engineering work. Use when choosing a task flow or OpenSpec route at kickoff, checking post-edit reviewer obligations, recovering from an anti-loop stop, or shaping a blocked/completion reply. Not for: substantial-change classification (use dhpk-adaptive-dev-workflow), an investigation already underway (use dhpk-root-cause-investigation), pure code tracing, or mid-workflow execution. Output: one next route plus the required gates and completion shape.

FastAPI + SQLAlchemy 2.0 async patterns + review checklist: routers, Depends DI, Pydantic schemas, session/transaction discipline, Alembic safety, auth/CORS/errors. Use when writing or reviewing FastAPI routes, async repositories, or migrations. Not for non-web Python. Output: layered, transaction-safe API.

Feasibility analysis from first principles. Use when: evaluating solutions before dhpk-tech-spec, comparing approaches, risk assessment. Not for: implementation (use dhpk-adaptive-dev-workflow in feature mode), architecture advice (use dhpk-codex-architect). Output: quantitative comparison + recommendation.

Feature verification (READ-ONLY, P0-P5). Use when: verifying feature behavior after deployment, validating API responses, diagnosing production issues, post-deploy smoke test. Not for: modifying data (use dhpk-adaptive-dev-workflow in feature mode), code review (use dhpk-change-review), writing tests (use dhpk-tdd-workflow), security audit (use dhpk-security-review). Output: a P0-P5 verification report with pass/fail evidence per check.

Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use dhpk-codebase-exploration), issue analysis (use dhpk-issue-analyze). Output: history trace + root cause report.

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。

Run GitNexus CLI commands (analyze, status, clean, wiki, list). Use when: indexing or re-indexing a repo, checking index freshness, generating a wiki, listing indexed repos. Not for: querying the graph (use dhpk-gitnexus-exploring), tool/schema reference (use dhpk-gitnexus-guide). Output: the npx gitnexus command to run + next step.

Trace bugs and errors through the GitNexus knowledge graph. Use when: debugging a failure, tracing an error to its origin, finding callers of a suspect symbol, investigating unexpected behavior. Not for: general architecture understanding (use dhpk-gitnexus-exploring), change blast-radius (use dhpk-gitnexus-impact-analysis), CLI/index ops (use dhpk-gitnexus-cli). Output: a root-cause hypothesis with the call chain + files to inspect.

Explore and understand a codebase via the GitNexus knowledge graph. Use when: asking how code works, understanding architecture, tracing execution flows, or exploring unfamiliar code. Not for: blast-radius of a change (use dhpk-gitnexus-impact-analysis), bug tracing (use dhpk-gitnexus-debugging), CLI/index ops (use dhpk-gitnexus-cli). Output: a code-flow explanation grounded in graph queries + the files to read.

Reference for GitNexus MCP tools, resources, and graph schema. Use when: asking what GitNexus tools exist, how to query the graph, or for MCP resource / schema reference. Not for: CLI commands (use dhpk-gitnexus-cli), task flows (use dhpk-gitnexus-exploring / dhpk-gitnexus-debugging / dhpk-gitnexus-impact-analysis / dhpk-gitnexus-refactoring). Output: the right tool / resource / skill to use next.

Assess the blast radius of a code change via the GitNexus graph. Use when: asking what breaks if you change X, who depends on a symbol, or for a pre-commit safety check. Not for: understanding how code works (use dhpk-gitnexus-exploring), bug tracing (use dhpk-gitnexus-debugging), performing the rename/refactor (use dhpk-gitnexus-refactoring). Output: a depth-ranked dependents list + risk level.

Safely rename, extract, split, move, or restructure code using the GitNexus graph + coordinated rename. Use when: renaming a symbol across files, extracting a module, splitting a function/service, moving code. Not for: understanding code (use dhpk-gitnexus-exploring), pre-change risk only (use dhpk-gitnexus-impact-analysis), bug tracing (use dhpk-gitnexus-debugging). Output: an ordered refactor plan + verified multi-file edits.

Audits Claude Code context-window token consumption across agents, skills, MCP, rules, and CLAUDE.md; produces prioritized token-savings fixes. Use when: context feels bloated, after adding components, or checking headroom. Not for: trimming harness structure (use dhpk-harness-revise), backfilling .claude/ (use dhpk-harness-fill), or checking hook/plugin health (use dhpk-claude-health). Output: budget report + ranked fixes.

Explore-driven meta-workflow SSOT: 5-phase parallel inventory → fill in .claude/ infrastructure. Backfills .claude/skills/agents/rules + per-layer CLAUDE.md in one shot (≤3 Explore agents in parallel per round) when explicitly invoked via /dhpk:dhpk-harness-fill. Not for: single-file patches (use Edit), specific symbol lookups (use cx definition / gitnexus_impact), PR review (route through the sentinel chain to the matching reviewer agent). Output: list of created / modified files + conventio...

Trims and validates the project harness (.claude/ or .codex/) for a harness audit request, after major rule additions, or as periodic maintenance. Detects the active environment and ensures consistency, hygiene, and trigger preservation. Not for: business code review. Output: inventory snapshot, gap list with severity, proposed fixes, validation results.

Generate iOS/macOS asset-catalog imagesets (1x/2x/3x PNG + Contents.json) from SF Symbols (Apple-native, offline, macOS) or the Iconify API (275k+ open-source icons, online). Use when adding icons to an Xcode asset catalog, replacing placeholder glyphs, or searching for an icon that matches a project''s style. Not for general SwiftUI design, arbitrary raster editing, or production code changes. Output: an imageset path plus generated PNG and Contents.json verification. Part of the xcode-tooli...

Use when iOS SDK guidance is needed for privacy-sensitive persistence, CryptoKit/Keychain, OCR, camera, biometrics, notifications, HealthKit, or privacy manifests. Requires swift. Not for SwiftUI composition or pure Swift language work. Output: SDK-specific implementation or review guidance with privacy and verification gates.

GitHub Issue and PR review thread deep analysis with Codex blind verdict. Use when: analyzing issue root cause, classifying problems, investigation planning, triaging PR review comments for actionability. Not for: fixing bugs (use dhpk-adaptive-dev-workflow in bug mode), code exploration (use dhpk-codebase-exploration). Output: classified analysis + verdict assessment + investigation strategy.

ESLint/TypeScript configuration guidance for tier selection, global-list synchronization, static gates, or frontend-review consistency. Use when editing eslint.config.js or tsconfig.json, adding globals, or planning lint migration. Not for ordinary JS logic. Output: a tier decision and verification evidence.

Progressive `// @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...

Laravel 10.x (February 2023) signature features and the breaking-change traps from 9 → 10. Use when writing or reviewing code in a Laravel 10 project, or in a package whose composer constraint includes ^10.0. Covers native return types throughout the app skeleton, invokable validation rules via the ValidationRule contract, the Process facade for shell invocation, the Pest-as-default test option, and the Predis 2.x default. Not for application business logic — load when touching the app skelet...

Use when working on Laravel 11 routing and migration guidance for ^11 projects, bootstrap/app.php, middleware, casts, rate limiting, and 10→11 upgrades. Not for ordinary business logic; use `dhpk-php-runtime-router` for family selection and shared Laravel routing. Output: version-specific traps and verification gates.

Laravel 5.4 (February 2017) signature features and breaking-change traps from 5.3 → 5.4. Use when writing or reviewing Laravel 5.4 code or a package constrained to 5.4.*. Covers Blade components, route model binding, middleware groups, markdown mailables, and the Elixir → Mix transition. Not for application business logic; use `dhpk-php-runtime-router` for family selection and shared Laravel routing. Output: version-specific guidance, migration traps, and verification gates.

Laravel 6.x (LTS, Sep 2019) signature features and the breaking-change traps from 5.8 → 6.0. Use when writing or reviewing code in a Laravel 6 project, or in a package whose composer constraint includes ^6.0. Covers job middleware, lazy collections, the Str/Arr helper migration, the strict-semver shift, and the deprecations Laravel 6 removed from 5.x. Not for application business logic — load when working on framework-touching code (service providers, jobs, model attributes) or planning a 5.8...

Laravel 7.x (March 2020) signature features and the breaking-change traps from 6 → 7. Use when writing or reviewing code in a Laravel 7 project, or in a package whose composer constraint includes ^7.0. Covers the new HTTP client facade, custom Eloquent casts via the CastsAttributes interface, the Blade x-component overhaul, Symfony 5 upgrade implications, and route-model-binding-by-key. Not for application business logic — load when touching framework code (HTTP calls, casts, Blade components...

Laravel 8.x (September 2020) signature features and the breaking-change traps from 7 → 8. Use when writing or reviewing code in a Laravel 8 project, or in a package whose composer constraint includes ^8.0. Covers the factory class rewrite (HasFactory trait), Jetstream/Fortify scaffolding split, job batching, queueable closures, the app/Models/ relocation, dynamic Blade components, migration squashing, and the Tailwind-by-default switch. Not for application business logic — load when touching ...

Laravel 9.x (February 2022) signature features and the breaking-change traps from 8 → 9. Use when writing or reviewing code in a Laravel 9 project, or in a package whose composer constraint includes ^9.0. Covers anonymous migrations, the Symfony 6 upgrade, Symfony Mailer replacing Swift Mailer, Flysystem 3 breaking changes (visibility / exception API), PHP 8.0 floor, query builder improvements, enum casts, and the new Ignition error page. Not for application business logic — load when touchin...

Laravel Mix 5 (^5.0.9) signature features and the webpack 4 era build traps. Use when editing webpack.mix.js, the resources/assets/ asset sources, or the package.json npm build scripts in a Laravel 5.4 / Mix 5 project, or diagnosing why a dev/watch/prod build fails on a newer Node. Covers the entry/output mapping, mix() versioning + manifest, the dev/watch/hot/prod script ladder, the Elixir heritage, and the legacy-OpenSSL flag. Not for application or Vue component logic — load when working o...

Cross-version Laravel package authoring. Use when: designing a service provider, facade, version-conditional binding, publishable artifact, discovery contract, or package compatibility surface. Not for: application code, one-major API details, Composer release hygiene, or deep Testbench matrix mechanics. Output: an authoring decision or package design with provider, facade, publishing, discovery, and compatibility gates.

Orchestra Testbench matrix mechanics for Laravel packages spanning multiple majors. Use when: choosing Testbench pins, defining PHP × Laravel cells, building the shared TestCase, provisioning per-cell databases, running prefer-lowest, or validating package discovery. Not for: single-major packages, application test suites, Laravel package authoring outside the matrix, or semver decisions. Output: a per-cell CI matrix, TestCase design, and evidence-backed test gate.

Write characterization tests for untested legacy code to lock current behavior before refactoring. Use when users want to safely refactor legacy controllers/models/services, add regression safety nets, or prepare code for extraction. Trigger words: characterization test, lock behavior, legacy test, safe refactor, 行為鎖定, 特徵測試, 安全重構. Not for: greenfield code, already well-tested modules, or pure bug fixes. Output: characterization test files + coverage delta report.