Menu
Skills in this repository
SkillsMP has collected 1,021 skills from protosphinx/sphinxstack. Open a skill to review its source and details.
protosphinx/sphinxstackShowing 40 of 1,021 collected skills.
Put a whole college application season into one tracker. Every deadline, requirement, and document per school, with what is missing visible. Use when they say "I'm applying to college and drowning" or deadlines are near and nothing is written down.
Archive a finished production with verified masters, sources, project files, metadata, rights, checksums, retention, and restore evidence. Use when a completed media project must remain reproducible, reusable, or defensible.
Prepare a compensation request using verified contribution, role scope, internal process, and current market evidence. Use when someone wants a raise without reducing the conversation to one external salary number.
Ask for an informational interview with a truthful connection, focused learning goal, bounded time, and no-pressure decline. Use when learning about work from someone’s experience.
Request specific, actionable workplace feedback and convert it into tested improvement. Use when learning a role, completing work, or preparing for a review.
Get recommendation letters asked for the right way. Picks recommenders, preps the brag sheet, and drafts the ask in the person's own words. Use when they say "who should I ask for a recommendation", "help me ask my teacher", or an application requires letters.
Assess stakeholder trust risk through evidence, impacts, scenarios, and response options. Use when a decision, failure, claim, controversy, partner, or information gap could change whether people rely on an organization.
Assess shared supplier dependencies, common-mode exposure, substitution limits, and exit feasibility. Use when apparently diverse vendors, services, regions, or contracts may fail through one hidden dependency.
Audit a build pipeline for source provenance, dependency integrity, isolated execution, secrets, artifact reproducibility, signing, promotion, and evidence. Use when release trust depends on CI or build infrastructure.
Audit a complex form across task flow, fields, conditional logic, validation, accessibility, save and resume, privacy, review, submission, and recovery. Use when users complete consequential multi-step information.
Audit a course for accessibility across materials, platforms, teaching, assessment, communication, accommodations, and learner journeys. Use when barriers must be found and repaired before or during delivery.
Audit a data export for authority, scope, schema, completeness, minimization, security, delivery, retention, and recipient use. Use when sensitive or important data leaves a source system through a file, API, report, or transfer.
Audit a digital asset library for identity, duplicates, metadata, rights, consent, accessibility, quality, lineage, access, retention, and retrieval. Use when a media collection is difficult to trust or reuse.
Audit a feature store for provenance, point-in-time correctness, online-offline parity, freshness, access, reuse, monitoring, and decision impact. Use when machine-learning features support consequential models.
Audit an end-to-end hiring process for job relevance, consistent treatment, accessibility, subgroup outcomes, data quality, and effective remediation. Use when an organization must evaluate whether recruiting and selection practices create unjustified…
Audit a logging pipeline for source completeness, structure, loss, ordering, privacy, access, retention, integrity, cost, and retrieval. Use when logs support operations, security, compliance, or incident evidence.
Audit and restore a resume after identity fraud through claimant proof, account and document preservation, false-claim separation, public-surface correction, employer communication, and safe recovery. Use when someone else may have applied, published, or…
Audit a resume for language, structure, evidence, and disclosure choices that create avoidable bias or erase identity. Use when improving fair presentation without falsifying the candidate's history.
Audit a serverless runtime for isolation, identity, secrets, networking, lifecycle, concurrency, limits, deployment, observability, and recovery. Use when functions or edge code handle consequential workloads.
Audit a third-party web script for purpose, provenance, loading, permissions, data flow, consent, security, performance, accessibility, failure, updates, and removal. Use when external JavaScript can affect users or page trust.
Audit a vendor exit plan for assets, data, access, dependencies, continuity, rights, transition, deletion, verification, cost, and accountable acceptance. Use when replacing or ending a material supplier relationship.
Audit web analytics for event meaning, consent, identity, payload quality, duplication, loss, attribution, governance, and report reconciliation. Use when metrics are untrusted, tracking changes, or privacy and decision risks need review.
Audit a website across real user journeys, content, accessibility, performance, search, analytics, security basics, and operational health, then produce a prioritized repair backlog. Use when someone asks for a website audit, wants to improve an existing…
Audit accessibility across a large digital estate using representative coverage and human evidence. Use when many pages, templates, components, journeys, documents, or teams need risk-based findings, remediation, and verification.
Audit an academic CV for public appointment through identity, output status, contribution, credential, grant, teaching, conflict, correction, and disclosure review. Use when scholarly claims will support a senior appointment, election, award, or public…
Audit automated hiring tools for job relevance, validity, subgroup harm, governance, and recourse. Use when screening, ranking, matching, assessment, interview, or monitoring automation influences employment opportunity.
Audit an executive resume and biography for public disclosure through independent claim verification, conflict and identity checks, privacy, legal review, discrepancy handling, and correction readiness. Use when leadership credentials will appear in filings,…
Measure a dataset's completeness, validity, uniqueness, consistency, timeliness, lineage, and fitness for a named decision, then prioritize repair by impact. Use when reports conflict, a migration needs a baseline, model inputs are suspect, or someone asks…
Audit feature flags for purpose, ownership, state coverage, exposure, stale code, operational risk, and safe removal. Use when a flag inventory has grown, ownership is unclear, or rollout controls may no longer match production behavior.
Find, classify, and review recurring charges using statements, receipts, contracts, and actual use. Use when reducing spend or preventing unwanted renewals.
Audit third-party browser scripts for purpose, data access, execution power, performance, consent, integrity, and removal. Use when external code runs in a site's origin or user journey.
Add real sign-in to their app. Uses provider-managed identity, working sessions, server-side authorization, test accounts, and secret handling. Never roll your own password storage. Use when an app needs accounts, when data should be private per user, or when…
Write a script that completes a repetitive task they actually do. Covers input, output, dry runs, logs, scheduling, and a safe off switch. Use when they mention a repetitive task, ask "can I automate this", or want a script that runs by itself.
Build and deploy their first small server. Covers a few real endpoints, frontend requests, current host limits, server-side secrets, and failure handling. Use when a frontend needs a hidden key, when they ask "what is a backend", or when localStorage stops…
Write and publish one blog post on something the person knows. Their words, workshopped, live at a URL by the end of the sitting. Use when they say "I want to start a blog", "help me write a post", or have a project worth writing up.
Put the person's colors, fonts, and usage rules on one page. Then prove the kit works by restyling one real artifact. Use when they say "make my stuff look consistent", "brand guidelines", or their site, slides, and posts all look unrelated.
Build a small browser extension for their own browsing problem. Manifest, content script, storage, loaded unpacked and used in their daily browser. Use when they complain about a website's behavior, want to change how a page looks or works, or ask "how are…
Build a budget from the person's real income and spending. Lives in a spreadsheet with a monthly review that keeps it honest. Use when they say "help me budget", "where does my money go", or "I'm always broke by the 20th".
Build a capital budget that compares alternatives through incremental cash flows, risk, capacity, dependencies, and post-investment accountability. Use when deciding whether, when, or how to fund equipment, facilities, technology, or other long-lived…
Build a change-data-capture pipeline with source position, event identity, schema history, snapshots, ordering, tombstones, idempotency, reconciliation, and recovery. Use when downstream state must follow database changes.