Results for “ref”

[omh] Oversized or tangled UI component: behavior-preserving refactor of UI code - preview the full change plan first, apply as a second explicit step, and work impact-ordered from state architecture down to naming polish. Use when the user says: frontend-refactor, front-refactor, frontend refactor, refactor this component, refactor the component, refactor my component, component refactor, react refactor.

The English summary is being prepared. Showing the original description.

Automating post-sandbox-refresh cleanup via the `SandboxPostCopy` interface — the Apex class that runs ONCE after a sandbox refresh or clone completes, before users can log in. Used to mask emails, deactivate users, scrub integration endpoints, disable scheduled jobs, and reapply per-environment configuration the metadata copy doesn't carry. Covers the interface contract (`runApexClass` setting, `SandboxContext` parameter, single-execution semantics), the email-masking pattern that stops sandbox tests emailing production addresses, and the refresh runbook checklist. NOT for choosing sandbox type or refresh cadence — use admin/sandbox-strategy. NOT for re-seeding reference data after a refresh — use data/sandbox-refresh-data-strategies. Trigger keywords: SandboxPostCopy, runApexClass, SandboxContext, Test.testSandboxPostCopyScript, RunAsAutoProcUser, Automated Process user, CronTrigger, System.abortJob, sandbox email masking, post-refresh runbook.

The English summary is being prepared. Showing the original description.

Search academic references for a manuscript and export them to a verified refs CSV, then optionally hand off to cec-sheet. Claims are decomposed into conditions that define when to stop; references are found by keyword search (Mode A targeted / Mode B agentic via Codex CLI, run as two independent search routes) and by citation chaining (Mode C — backward refs, forward citations, similar articles, same author, and reference lists of OA full text/PDF, imozuru-style). All paths end in bundled deterministic tools (scripts/pubmed_search.py, scripts/citation_chain.py) that fetch bibliography live from PubMed, so PMIDs are never fabricated, and each supporting sentence is machine-verified verbatim against the fetched abstract. Triggers: "論文検索", "文献検索", "文脈検索", "コンテキスト検索", "原稿の引用を探して", "原典を探して", "芋づる", "引用をたどって", "被引用", "孫引き", "refs.csv", "codex-refs", "/codex-refs".

The English summary is being prepared. Showing the original description.

Use Ahrefs through Composio to research keywords, inspect backlinks, review organic search rankings, and track domain metrics over time. Compare SEO performance across competitors or site sections with batch analysis of up to 100 URLs.

• Inspecting backlinks and referring domains
• Finding keyword ideas with search volume and difficulty
• Comparing organic search rankings across dates

Clean messy tabular data through OpenRefine using command-line operations. Import files, inspect rows, apply reusable JSON transformation histories, and export cleaned CSV or TSV data, with session support for undoing and redoing changes.

• Remove extra spaces from names in a CSV file
• Reuse the same cleaning steps on another dataset
• Inspect sample rows before and after transformation

Design or improve customer referral and affiliate programs. Plan rewards, sharing methods, recruitment, and launch steps, then assess referral performance and costs to identify improvements, including measures to reduce abuse.

• Planning a customer referral program
• Designing affiliate commissions and recruitment
• Reviewing referral performance and acquisition costs

Plan refactoring with dependency analysis, which shows how code parts rely on each other. Find candidates and unreferenced code, preview and apply renames, and compare the resulting impact with the original plan.

• Finding refactoring candidates and unreferenced code
• Previewing edits before applying a rename
• Checking affected dependencies and execution paths

Use Ahrefs through Composio to research keywords, inspect backlinks, review organic search rankings, and track domain metrics over time. Compare SEO performance across competitors or site sections with batch analysis of up to 100 URLs.

• Inspecting backlinks and referring domains
• Finding keyword ideas with search volume and difficulty
• Comparing organic search rankings across dates

Draft an English referee report for an economics or finance paper, with a findings summary, specific numbered critiques, and a letter to the editor. Choose the recommendation, review depth, and three to eight comments.

• Drafting a referee report for an economics or finance paper
• Examining causal claims and robustness of research findings
• Choosing review depth and the number of comments

Use when one image must be composed from several reference pictures through the Scenario MCP server, each lending one thing: the character from one, the place, pose, style, light, palette, material, outfit, or layout from others. Also when a reference leaks into the result (its object, colors, or face showing where it should not) or a reference's role is ignored. Keywords: multi-reference, reference roles, combine references, style reference, pose reference, give each picture a job.

The English summary is being prepared. Showing the original description.

Run multiple Reforge-guided section-refactor lanes in parallel, each in its own worktree/branch off origin/main, with a score-blind adversarial review panel gating every commit, one draft PR per section. Use when the user wants to reduce Reforge surface/internal score across several sections at once via architecturally-correct deletions (dead surface, entity-leak removal, cross-section consumers moved onto the public contract) — not by relocation, parameter bags, or accessibility-dodging. Wraps the per-lane process in .codex/skills/humans-refactor. Triggers: 'refactor swarm', 'parallel section refactors', 'run reforge refactor on Users/Tickets/...', 'burn down surface score across sections'. Has an intensity dial (light|standard|deep) and a workflow|solo execution mode to trade token burn against autonomy per unit of output.

The English summary is being prepared. Showing the original description.

Create a desktop landing page wireframe, a simple layout made of grey boxes, with numbered markers and a matching specification panel. The result shows page structure alongside short implementation and user experience notes.

• Planning a desktop landing page layout
• Sharing implementation notes with developers
• Reviewing navigation, hero, and feature placement

Improve existing code through repeated cycles of testing, implementation, and refactoring. The skill covers performance bottlenecks, error recovery, code coverage, and documentation, helping developers refine behavior and structure while keeping tests passing.

• Refactoring existing code while keeping tests passing
• Adding tests before implementing expected behavior
• Investigating slow database access and cache usage

Review slow page loads and choose resource hints, browser instructions that start loading or connecting earlier. Use measurements to identify bottlenecks, then recommend preload, preconnect, prefetch, or dns-prefetch for important assets and likely next-page resources.

• Reviewing slow loading of prominent images and fonts
• Preparing connections to external services
• Prefetching resources for likely next-page visits

Review Referrer-Policy settings to limit sensitive URL details shared when visitors follow external links. Check response headers and pages containing private parameters, suggest suitable policy values, and explain how to verify the resulting browser behavior.

• Checking privacy settings on password reset pages
• Reviewing server and CDN response headers
• Comparing policies for pages with sensitive URLs

Review HTML and JSX links that open new tabs, identify missing rel attributes, and add protective values. The skill also explains how these values prevent changes to the original tab and control referral information.

• Reviewing links that open in new tabs
• Fixing missing rel attributes in JSX
• Understanding noopener and noreferrer

Manage Zotero reference libraries through Python: search, create, update, and delete references, organize collections and tags, upload PDF attachments, and export citation data. Guidance covers both remote libraries and access through a running local Zotero app.

• Searching references in a Zotero library
• Organizing references with collections and tags
• Uploading PDF attachments to references

Choose a game engine and version, record the choice in project configuration, and prepare reference documents for newer releases. The skill also supports refreshing those references and guiding migration between engine versions.

• Choose an engine and version for a new game
• Record the engine version in project configuration
• Refresh references for newer engine releases

Audit multilingual and regional websites for hreflang errors, the annotations that connect language versions. Generate corrected tags or sitemaps, and check for missing translations, inconsistent local formats, and content that needs cultural adaptation.

• Check language and region annotations before a multilingual launch
• Generate a sitemap connecting pages across regional domains
• Find missing or outdated translations across language versions

Search ClinVar and NCBI Variation for genetic variants, or look up records using VCV, RCV, SCV, and RefSNP identifiers. Get concise summaries, check identifier mappings, and save full JSON responses when needed.

• Searching ClinVar for a genetic variant
• Looking up VCV, RCV, SCV, or RefSNP records
• Checking mappings between variant identifiers

Create original brand campaign visuals from a supplied reference. Adjust how closely concepts share its visual language, develop distinct brands within one family, and check names, composition, and differences from signature reference elements.

• Develop original campaign visuals from a reference image
• Create distinct brands with a shared visual direction
• Bring an existing concept closer to its reference

Check academic references for existence, accurate publication details, and support for the claims being cited. This guide explains how to verify sources, obtain bibliography entries, and flag references that cannot be confirmed.

• Checking references suggested by AI
• Verifying authors, titles, and publication years
• Checking whether a paper supports a cited claim

Run a five-stage finishing workflow for a drafted LaTeX paper: polish, revise, adapt its structure to a target journal, polish again, and verify references. Receive updated files, stage backups, a reference audit spreadsheet, and a final report.

• Running a complete finishing workflow on a first draft
• Adapting a paper's structure to a target journal
• Auditing references after manuscript revisions

Build a wiki from source code, with architecture diagrams, module explanations, process flows, and task guides. Adjust coverage for internal or public readers, then use recorded Git commits to refresh pages affected by code changes.

• Create a wiki explaining a codebase's structure
• Document end-to-end flows with diagrams
• Prepare documentation for internal or public readers