en un clic
acrossai-abilities-manager
acrossai-abilities-manager contient 32 skills collectées depuis acrossai-co, avec une couverture métier par dépôt et des pages de détail sur le site.
Skills dans ce dépôt
Prioritize official @wordpress packages over external dependencies. Detect React conflicts, use aliasing, and validate package usage.
Apply approved architecture refactors by updating plan and task artifacts directly.
Perform a framework-agnostic architecture review validating implementation against spec.md, plan.md, tasks.md, and the governance and architecture constitutions.
Perform an architecture-aware verification gate validating implementation against spec.md, plan.md, tasks.md, and the Architecture Constitution.
Run a single architecture workflow that prefers memory-first context and can incorporate security review when available.
Run implementation with memory context, then review the produced implementation against security and architecture constraints.
Orchestrate a governed planning workflow that coordinates flash-mem, Security Review, and Architecture Guard validation.
Generate or validate implementation tasks with memory context, security constraints, and architecture refactor/migration awareness.
Initialize or refine the project governance and architecture constitutions for Architecture Guard.
Detect framework-agnostic architecture violations in plans, tasks, and implementation summaries.
Audit memory quality, index integrity, freshness, and synthesis hygiene.
Capture durable knowledge and architecture decisions from current or provided diffs.
Propose human-approved durable lessons and matching index updates from completed work.
Initialize layered memory, synthesis, and spec starter files in a target repo.
Turn a high-signal audit finding into a tracker-ready follow-up for GitHub, GitLab, Jira, or another issue system.
Use index-first retrieval to synthesize constraints and gate planning on conflicts.
Compare estimated token usage between full memory reads and optimized synthesis.
Apply approved security follow-up items into Spec-Kit planning artifacts
Performs broader or full-system security review across the codebase. Recommended for milestone reviews, release reviews, or major architecture validation.
Reviews security risks introduced by the current branch or implementation changes. Recommended for normal feature development workflows.
Export security review findings as a formal Executive and Technical Pentest Report.
Create remediation plans or technical-debt tasks from security review findings
Initialize or update the Security Constitution for the project.
Security review of Spec-Kit plan artifacts and supporting design docs
Security review of staged changes only (git diff --cached)
Security review of Spec-Kit task artifacts and implementation sequencing
Use when developing WordPress (Gutenberg) blocks: block.json metadata, register_block_type(_from_metadata), attributes/serialization, supports, dynamic rendering (render.php/render_callback), deprecations/migrations, viewScript vs viewScriptModule, and @wordpress/scripts/@wordpress/create-block build and test workflows.
Use when developing WordPress block themes: theme.json (global settings/styles), templates and template parts, patterns, style variations, and Site Editor troubleshooting (style hierarchy, overrides, caching).
Use when investigating or improving WordPress performance (backend-only agent): profiling and measurement (WP-CLI profile/doctor, Server-Timing, Query Monitor via REST headers), database/query optimization, autoloaded options, object caching, cron, HTTP API calls, and safe verification.
Use when configuring, running, or fixing PHPStan static analysis in WordPress projects (plugins/themes/sites): phpstan.neon setup, baselines, WordPress-specific typing, and handling third-party plugin classes.
Use for all development work on plugins built with WPBoilerplate/wordpress-plugin-boilerplate: hooks via the Loader singleton, PSR-4 namespace layout, security baseline (nonces/capabilities/escaping), settings API, REST endpoints, lifecycle, i18n, multisite, performance, and the @wordpress/scripts build pipeline.
Use when you need a deterministic inspection of a WordPress repository (plugin/theme/block theme/WP core/Gutenberg/full site) including tooling/tests/version hints, and a structured JSON report to guide workflows and guardrails.