Menu
What can this toolkit do? Full list of available capabilities and data queries. Advanced reference for power users.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | accelerate-abilities-reference |
| description | What can this toolkit do? Full list of available capabilities and data queries. Advanced reference for power users. |
| license | MIT |
| category | reference |
| parent | accelerate |
This is the internal reference for every Accelerate capability the toolkit can access. Use it when:
Present the list to users in plain English, grouped by purpose. Do not show ability names, parameter names, or schemas unless the user explicitly asks for the technical detail (e.g., "I'm a developer, show me the raw list").
When a user asks "what can you do", respond with something like:
I can help with four main things on your Accelerate site:
Understanding what's happening Weekly / monthly / real-time performance reports, top content, traffic sources, engagement metrics (bounce rate, time on page, scroll depth), trending content, concurrent visitors, underperformance diagnosis, content comparison across time periods, author performance, taxonomy breakdown.
Running A/B tests Propose test ideas grounded in your data, create tests with multiple variants, monitor live tests, declare winners, pause or stop tests, check experiment results with statistical confidence.
Personalising content Define audience segments (by referrer, UTM, location, device, behaviour), attach personalised versions of reusable blocks to audiences, update or review existing audiences.
Analysing campaigns and attribution UTM campaign performance, source breakdown, first-touch vs last-touch attribution, landing page analysis, channel comparison.
What do you want to dig into?
Offer to route them into the right specialised skill from there.
Every capability below is invoked via mcp__wordpress__mcp-adapter-execute-ability with the ability name and an input object matching the schema. Required inputs are bold.
accelerate/get-performance-summary โ site, block, post, or experiment metrics. Inputs: entity_type (site|block|post|experiment, default site), entity_id, date_range_preset (1h|4h|12h|24h|7d|30d|90d), date_range, granularity, segment.accelerate/get-post-performance โ detailed metrics for one post. Inputs: post_id, date_range.accelerate/get-top-content โ best-performing content. Inputs: type, limit (1โ50, default 10), date_range.accelerate/get-content-diff โ period-over-period comparison. Inputs: post_ids, current_period, comparison_period.accelerate/get-traffic-breakdown โ breakdown by country / browser / os / referrer. Inputs: dimension (default country), date_range, limit.accelerate/get-taxonomy-performance โ performance by category / tag / taxonomy. Inputs: taxonomy (default category), date_range, limit. Output includes underserved_score.accelerate/get-site-context โ site design system (colours, typography, spacing, blocks). Inputs: include_blocks (default false).accelerate/get-engagement-metrics โ bounce rate, time on page, scroll depth, recirculation, return visitor rate, exit pages. Inputs: entity_type (site|post), entity_id, date_range.accelerate/list-active-experiments โ running tests and personalisation rules. Inputs: type (all|abtest|personalization), post_id.accelerate/list-experiments โ historical and active experiments with pagination, status / type / date / annotation filters. Use this for "every experiment ever", not just live ones. Inputs: status (all|active|running|completed|paused|draft), type (all|abtest|personalization), date_range, subject_post_id, annotation_key, annotation_value, page, per_page (1โ100, default 50). Returns paginated experiments with total and pages.accelerate/get-audience-segments โ defined audiences. Inputs: include_estimates.accelerate/get-audience-fields โ available targeting fields. Inputs: refresh.accelerate/get-author-performance โ metrics for one or all authors. Inputs: author_id, date_range, limit, order_by (views|conversions|conversion_rate|posts_count).accelerate/get-author-content โ posts by an author with metrics. Inputs: author_id, date_range, order_by, limit.accelerate/search-content โ find content by title / URL / text. Inputs: query, search_in, post_type, limit.accelerate/get-concurrent-visitors โ live visitor count with polling guidance. Inputs: post_id, active_window_minutes (1โ15, default 5), include_breakdown.accelerate/get-trending-content โ content ranked by velocity (rising / flat / falling). Inputs: window (1h|4h|12h|24h, default 1h), metric (views|conversions|visitors), content_type, limit, min_threshold.accelerate/get-attribution-comparison โ first-touch vs last-touch breakdown with insights (best introducer / closer / most undervalued). Inputs: date_range, conversion_goal.accelerate/get-source-breakdown โ traffic by source / medium / campaign / referrer_domain. Inputs: date_range, group_by, limit.accelerate/get-utm-performance โ UTM metrics by campaign / source / medium / term / content. Inputs: date_range, group_by, campaign.accelerate/get-landing-pages โ top entry pages. Inputs: date_range, limit.accelerate/get-variants โ inspect a block's current variants. Inputs: block_id. (Read-only.)accelerate/add-variant โ add one variant to a block. Inputs: block_id, content, title, percentage, audience_id.accelerate/update-variant โ modify an existing variant. Inputs: block_id, variant_index, content, title, percentage, audience_id.accelerate/remove-variant โ delete a variant. Inputs: block_id, variant_index. Destructive.accelerate/create-ab-test โ create a multi-variant test on a block. Inputs: block_id, variants (min 2), hypothesis, goal (engagement|click_any_link|submit_form), traffic_percentage.accelerate/set-block-goal โ set a block's success metric. Inputs: block_id, goal.accelerate/set-traffic-percentage โ adjust how much traffic enters the experiment. Inputs: block_id, percentage.accelerate/get-experiment-results โ full statistical results with winner recommendation. Inputs: block_id, refresh.accelerate/stop-experiment โ pause / resume / stop / declare winner. Inputs: block_id, action (pause|resume|stop|declare_winner), winner_variant_index (required for declare_winner).accelerate/create-audience โ define an audience. Inputs: title, rules, description.accelerate/update-audience โ modify an existing audience. Inputs: audience_id, title, description, rules.accelerate/create-personalization-rule โ attach personalised content to a block for an audience. Inputs: block_id, audience_id, personalized_content, fallback_content.accelerate/broadcast-content โ push blocks site-wide. Inputs: block_ids, title. Destructive.accelerate/query-events โ raw event queries with custom filters. Inputs: filters, fields, date_range, limit, offset.accelerate/get-event-schema โ available event fields. Inputs: refresh.accelerate/aggregate โ custom aggregations with flexible dimensions and metrics. Inputs: metrics, dimensions, filters, date_range, limit.accelerate/export-events โ full event dump for a date. Inputs: date (YYYY-MM-DD), format (json|csv). Admin only.accelerate/get-export-status โ check availability of exported data. Inputs: date.can_view_analytics. Writing requires can_create_experiments. Broadcasts and exports require can_manage_experiments. If a call fails with a permission error, tell the user their WordPress account needs the right capability and suggest they check with their site admin.Design a new on-brand version of a block or a fresh section โ "make me a variant of the hero", "design a new pricing section", "compose an on-brand version", "give me a bolder hero". Produces ready-to-use content; offers to put it in a test but never forces one. NOT for running or tracking an A/B test (use accelerate-test) or a multi-round optimization loop (use accelerate-evolve).
Improve a block over multiple rounds โ "keep improving my hero", "run an optimization loop on the homepage", "autopilot the waitlist block", "evolve this section until it stops getting better". Each round fields bold new challengers, tests them, harvests the winner, and builds the next round on it. NOT for a single A/B test (use accelerate-test) or a one-off variant (use accelerate-design).
Connect the toolkit to your WordPress site. Set up credentials, generate an application password. Also triggered when the site connection is missing.
Improve a landing page. Make it convert better. What should I change on my homepage? Optimise a specific page with data-grounded recommendations and A/B test hand-off. Recommends WHAT to change across a page; NOT for composing a specific new version of one block โ use accelerate-design for that.
Any question about a WordPress site โ analytics, traffic, bounce rate, conversions, A/B tests, landing pages, audiences, personalization, campaigns, content performance, what to improve, how the site is doing. Routes to the right workflow.
A/B test lifecycle โ plan, create, monitor, review, or end a test. What should I test? Set up a split test. How is my test doing? Is there a winner? Stop or declare a winner. NOT for composing a single on-brand variant without a test (use accelerate-design) or running a multi-round optimization loop (use accelerate-evolve).