Delegate a task to another AI IDE's CLI (codex / claude / opencode / cursor-agent) through an isolated-context subagent. Use when the user says delegate to <ide>, have <ide> do <task>, or offload to <ide>. For one-shot relay use `ai-ide-runner`.

Draw and edit Mermaid diagrams in Markdown. Use when the user wants to visualize processes, flows or sequences, or asks for a diagram. Load it before writing any Mermaid block, even when you know the syntax — that is why it gets skipped.

Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this spreadsheet", "sanity check this", "debug model", "model check", "model won't balance", "something's off in my model", "model review".

Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this spreadsheet", "sanity check this", "debug model", "model check", "model won't balance", "something's off in my model", "model review".

Use this skill to finalize a release. It stamps the [Unreleased] changelog section with a version and date, runs bumpversion to update all version files, and creates the release commit and tag. Only run this when you're ready to ship.

Retrieve probabilistic forecasts and their scorecard context. Use when the user asks what World Monitor is forecasting, how probabilities shifted, or how calibrated the forecasts are.

Plan or restructure website hierarchy, navigation, URL patterns, breadcrumbs, and internal linking. Use when mapping pages, sections, and site structure, but not for XML sitemap auditing or schema markup.

Analyze a GitHub pull request for risk level and generate concrete QA recommendations. Accepts a PR URL or "owner/repo#number" reference. Uses `gh` CLI to fetch the diff and metadata, computes blast radius, scores six risk dimensions, and returns a structured JSON risk assessment. Use when the user invokes /qa-analysis:qa-analysis with a GitHub PR URL or reference, or asks for a PR risk assessment, QA recommendations, or "what should I test?" for a given pull request.

All-in-one project configuration and health management. Sets up new projects (settings.local.json, CLAUDE.md, .gitignore), audits existing projects (permissions, context quality, MCP coverage, leaked secrets, stale docs), tidies accumulated cruft, captures session learnings, and adds permission presets. Uses sub-agents for heavy analysis to keep main context clean. Trigger with 'project health', 'check project', 'setup project', 'kickoff', 'bootstrap', 'tidy permissions', 'clean settings', 'capture learnings', 'audit context', 'add python permissions', or 'init project'.

Manage Harness Feature Flags (FME / Split.io) via MCP. List flags by workspace, get flag details, create flags, kill or restore flags per environment, archive or unarchive flags, and delete flags. Use when asked to create a feature flag, kill/restore a flag, list flags, check flag status, enable or disable a feature, or manage feature rollouts. Trigger phrases: feature flag, kill switch, restore flag, create flag, feature rollout, archive flag, FME flag.

Use when tfgen check fails with RENDERER_SHAPE_UNSUPPORTED set of object, or RENDERER_OUTPUT_INVALID on a dotted OpenAPI component like notification_center.ConnectorConfigField. Fix collectionConv and modelTypeName, not the generated files.

Stores a DAG definition once and re-runs it by name, instead of pasting the definition into every run. Use when the user wants to save a DAG, run a saved one, or schedule the same multi-agent graph repeatedly.

Delegate noisy investigation to one or more subagents so the orchestrator's context stays clean, then work from the distilled answer. Use this skill whenever answering a question would require reading many files, long logs, large diffs, or wide codebase surveys — i.e. when producing the answer generates far more noise than the answer itself. Use it for "how does X work", "where is Y used", "what's the root cause of Z", "summarize this PR/log" style questions, and reach for it liberally before reading a pile of files inline.

Type design in TypeScript: discriminated unions, branded types, narrowing, exhaustiveness and boundary validation. Use when modelling domain types, tightening strictness or generics, removing `as` casts, or migrating code to stricter types.

How to test a change: test first, what to cover, what to mock, and the anti-patterns that let tests pass without proving anything. Use when writing or planning tests, mocking a dependency, fixing a flaky test, or checking coverage.

Security rules for authentication, authorization, data access policies, input handling, headers and CSP, secrets and scheduled routes. Use when building an auth flow, adding an endpoint or handler, writing access policies, setting security headers, handling user input, or auditing security.

Branch names, commit messages, pushing and opening a pull request, and working with the task tracker. Use when branching, committing, pushing or opening a PR.

Plan and execute off-page SEO including link building, digital PR, brand mentions, citation building, and external authority signals. Use this skill whenever the user wants to build backlinks, plan a digital PR campaign, list local citations, run guest post outreach, develop linkable assets, recover lost links, or audit a backlink profile for risk. Triggers on link building, backlinks, digital PR, brand mentions, citation building, guest post, outreach, linkable asset, broken link building, HARO, podcast outreach, off-page SEO, anchor text, link velocity, toxic backlinks, disavow. Also triggers when the user is trying to grow domain authority or earn coverage.

Audit existing content across a site to decide what to keep, update, merge, redirect, or delete. Use this skill whenever the user wants to audit existing content, fix content decay, resolve keyword cannibalization, prune underperforming pages, prioritize content updates, or apply a keep/update/merge/redirect/delete framework to a content library. Triggers on content audit, content decay, content refresh, cannibalization, keyword cannibalization, prune content, delete pages, redirect old pages, content inventory, what to keep, what to update, content scorecard, evergreen refresh. Also triggers when traffic is dropping site-wide and the cause might be content quality, even if 'audit' is not said explicitly.

Master orchestrator for a full SEO audit suite powered by the Ahrefs MCP. Use this skill when running a comprehensive SEO audit, scoping a quarterly health check, doing pre-acquisition SEO due diligence, or post-migration verification. Triggers on full SEO audit, comprehensive SEO review, SEO health check, audit my site, SEO due diligence, audit suite, comprehensive audit, end-to-end SEO. Also triggers when a stakeholder wants the complete picture rather than a single-dimension audit.