prism-shadow

@prism-shadow source repo

997 skills
0 followers
12 hours ago last updated

▌
Northstar Payer Determination · prism-shadow bundle
Produce a structured Northstar Health Plan payer-operations determination by querying the shared read-only environment over the network and returning exactly one JSON object that conforms to the task's answer_template.json, including the standard basis_audit trail. Covers UM prior-authorization determinations, pharmacy appeal & manufacturer-assistance intake dispositions, payment-integrity claim repricing, peer-to-peer summaries, and UM-finance margin-queue analysis.

0
installs
▌
Clinic Protocol Cds · prism-shadow bundle
Produce a schema-conformant JSON clinical decision-support answer for a synthetic clinic case. Use whenever a task gives a case id, an answer_template.json contract, and access to the clinic runtime environment over HTTP. Drives the runtime API, applies the matching protocol, and emits exactly one JSON object that conforms to the template.

0
installs
▌
Licensing Board Structured Review · prism-shadow bundle
Structured licensing-board review tasks over a networked data environment. Fetch records from REST endpoints (contractor, liquor, and alcohol licensing plus policies/rules), apply the board's policy baseline, and return exactly one JSON object conforming to the task's answer_template.json. Covers contractor batch eligibility reviews, restricted liquor-license staff packages, and alcohol renewal manual-review queues. Read this BEFORE fetching any endpoint or drafting output.

0
installs
▌
Atlas Ops Scorecard · prism-shadow bundle
Analyze the Atlas Commerce Operations workplace and produce one JSON answer object that exactly conforms to a provided JSON-Schema answer template, using the live authenticated SQL/transaction service. Use for fulfillment, refund, carrier-quality, warehouse-productivity, support-health, and similar operations scorecard requests that ship a prompt, a *_request.json (scope + business definitions + decision rules), and an answer_template.json.

0
installs
▌
Pho Algorithmic Transport Audit · prism-shadow bundle
Solve Public Health Observatory registered algorithmic-transport audit requests — a prompt plus analysis_request.json and answer_template.json whose evidence comes only from the Observatory Web portal. Use whenever a PHO audit task asks you to resolve portal publications/cohorts, run a declared set of reproducible statistical audit modules (delete-cluster/jackknife fixed effects or GMM/mediation, nested ridge or elastic-net CV, restricted-null wild cluster bootstrap, grouped split conformal, trajectory PCA + deterministic k-means + stability, source/year/group perturbation, partial-R2 sensitivity), and return exactly one JSON object conforming to the template. Carries method only; binds every task-local value from the effective request and never carries solved values across invocations.

0
installs
▌
Work Portfolio Analysis · prism-shadow bundle
Produce JSON readouts (portfolio-mix, SLA-aging, or release-readiness) from a shared work-item portfolio environment exposed over REST + a restricted SQL endpoint. Use when a task points at a shared portfolio environment containing work items, mix targets, SLA policy, releases/milestones/blockers/dependencies and asks for a single JSON object matching a provided answer_template.json. Knows the environment's stale-field traps (mirror_status, legacy_category), primary-vs-duplicate-vs-cancelled record handling, the portfolio category classification convention, and the exact ordering/precision rules each template requires.

0
installs
▌
Engineering Portfolio Review · prism-shadow bundle
Analyze an engineering work-item portfolio against the shared portfolio environment (HTTP API + SQL endpoint; base URL and token live in environment_access.md). Use for portfolio-mix gap reviews, SLA aging/breach audits, and release-readiness assessments. Encodes the authoritative-status-over-mirror, primary-vs-duplicate, cancelled/distractor exclusion, 4-category resolution, stable ordering, and exact rounding rules so the single JSON answer matches the provided answer_template.json schema.

0
installs
▌
Northstar Payer Review · prism-shadow
Process Northstar Health Plan payer-operations review tasks (prior auth, appeals, payment integrity, P2P, margin queues) against the shared Northstar environment API, producing structured JSON determinations with full basis audit trails.

0
installs
▌
Cedar Ridge Intake · prism-shadow bundle
Answer Cedar Ridge Intake Coordination Portal tasks: read a task prompt plus its input/payloads/answer_template.json, query the read-only portal (REST + POST /query SQL) at the base URL in environment_access.md, apply the intake decision rules, and return ONE JSON object that exactly matches the template. Covers patient access verification, referral readiness audits, dialysis transfer reviews, program enrollment panels, and referral-to-chart activation. Use whenever a prompt points at the "Cedar Ridge Intake Coordination Portal" or a roster/batch/program id (e.g. NPI-*, ORTHO-*, PULM-*, DIAL-*, a program code) with an answer_template.json to fill.

0
installs
▌
Synthetic Clinic Protocol Answer · prism-shadow bundle
Produce the required JSON answer for a synthetic-clinic protocol-bound clinical decision-support task. Use when the input gives a target case id plus an answer_template.json and points at a read-only clinic runtime API (patients, cases, observations, medications, allergies, problems, imaging, care-registry, sdoh, protocols). Covers acute respiratory / CAP, pediatric head injury, potassium replacement, care-management routing, and observation-window retrieval cases. The skill teaches the procedure to fetch the record, select and apply the matching protocol at runtime, and emit one schema-conformant JSON object. It never contains task-specific answer values.

0
installs
▌
Investigation Review Gap Analysis · prism-shadow bundle
Produce a structured-JSON e-discovery gap / remediation dashboard for a legal-investigation matter by reading evidence from a running "Investigation Review Hub" API. Use when a task asks for a production gap analysis, retention/litigation-hold gap review, cross-system remediation dashboard, or production-readiness review for a subpoena/grand-jury/SEC/DOJ matter, and the answer must be a single JSON object conforming to a provided answer_template.json. Triggers: "Investigation Review Hub", "gap analysis", "remediation dashboard", "production readiness", "retention/litigation-hold gap", "privilege log gap", "custodian sources", matter IDs like MTR-*-GJ / MTR-*-SEC.

0
installs
▌
Court Ops Closeout · prism-shadow bundle
Prepare a court clerk closeout / financial packet (criminal sentencing register, traffic-violation payment plan, or post-sentencing installment & supervision order) by reconciling local case payloads against the Court Operations Portal REST API and emitting one JSON object that exactly matches a provided answer_template.json. Use when a task gives target case / citation / petition identifiers, local payloads (hearing notes, memos, worksheets, budgets, form excerpts), an answer_template.json, and a Court Operations Portal base URL (`<TASK_ENV_BASE_URL>` / `GDPEVO_ENV_BASE_URL`).

0
installs
▌
Court Closeout Packet · prism-shadow bundle
Produce a clerk-ready JSON closeout/disposition/financial packet for a court matter by reconciling local materials (hearing notes, audit memos, finance-queue or worksheet extracts, petition/budget summaries, form excerpts) against the read-only "Court Operations Portal" API, then emitting output that matches the task's answer_template.json exactly. Use for criminal sentencing closeouts, traffic-citation closeouts + payment plans, and post-sentencing/financial petition packets (installment orders, probation referrals, license-suspension orders). Triggers: a prompt that names target case/citation/petition ids, points at a portal base URL with GET /api endpoints, attaches payloads, and asks for one JSON object matching answer_template.json.

0
installs
▌
Licensing Review Batch · prism-shadow bundle
Produce structured JSON decisions for state licensing review tasks backed by the shared licensing data service (contractor application batches, restricted liquor license staff packages, and alcohol renewal manual-review queues). Use when a prompt asks you to review licensing records over a network environment and return JSON that must conform to an answer_template.json, especially when the prompt names contractor applications (C-*), liquor applications/locations (L-*/LOC-*), or alcohol licenses (AL-*), and lists /api/... endpoints plus POST /api/sql.

0
installs
▌
Ma Deal Workbench Analysis · prism-shadow bundle
Produce structured JSON transaction-analysis deliverables from the M&A deal workbench API — seller/buyer issue registers, SPA deviation matrices, closing and economics packages, carveout transition reviews, and M&A Committee escalation memos. Use whenever a task supplies a deal_id, a workbench base URL, and an answer_template.json to conform to.

0
installs
▌
Asteria Fleet Reconciliation · prism-shadow bundle
Solve Asteria Fleet "Data Quality Hub" reconciliation/certification tasks. Use when a task provides payloads/case_scope.json + payloads/answer_template.json and an environment_access.md pointing at a read-only Fleet Data Quality Hub, and asks for a reconciled/certified JSON audit of a contacts, fuel, freight, or maintenance collection (dedup overlapping source snapshots as of a cutoff, quarantine bad rows, normalize units & currency, resolve identities/categories, rank exceptions, assign opaque control codes, and decide a PASS/PASS_WITH_EXCEPTIONS/HOLD certification).

0
installs
▌
Portfolio Mix Sla Release Analysis · prism-shadow bundle
Answer engineering-portfolio review tasks that run against the shared read-only work-item API (endpoints + query token in environment_access.md). Covers three task families that share one data model: (A) quarterly portfolio-mix vs target, (B) reliability/security SLA aging & breach, and (C) release-readiness rollups. Use when a task asks for closed-work category mix, SLA overdue/aging/escalation, or a ship decision, and provides an answer_template.json to fill.

0
installs
▌
Reflect 3 Crm Support Console · prism-shadow
Resolve CRM support-console tasks (SCN_003) — ticket-batch classification, mobile-data triage, and enterprise export-complaint response packages — against a remote support-console API. Use when a task asks to classify service tickets / queue snapshots, triage mobile data cases, or build an enterprise export-failure response package and references a support console API.

0
installs
▌
Northstar Payer Determinations · prism-shadow bundle
Produces a correct structured-JSON determination for Northstar Health Plan payer-operations tasks — UM nurse authorization, pharmacy coverage appeal + manufacturer assistance, payment-integrity claim repricing, peer-to-peer (P2P) summary, and UM-finance margin-queue analysis — backed by records in the shared payer-operations environment. Use whenever a task gives a target business ID, a payer-operations role, a reporting date, and an answer_template.json, and asks you to return one JSON object conforming to that template.

0
installs
▌
Ehr Packet Generation · prism-shadow bundle
Produces normalized JSON packets/audits from a read-only EHR quality-governance and referral API — duplicate-chart merge packets, referral coordination packets, care-transition packets, duplicate-review + ServiceRequest validation, and batch referral audits. Read BEFORE fetching data or filling any answer template.

0
installs
▌
Ehr Referral Quality Packets · prism-shadow bundle
Produce normalized JSON "quality-governance packets" from a read-only EHR/referral API — duplicate-chart merge packets, referral coordination packets, care-transition packets, duplicate+service-request reviews, and batch referral audits. Read BEFORE producing any answer JSON for an EHR-quality or referral-coordination task that supplies an answer_template.json.

0
installs
▌
Licensing Board Review · prism-shadow bundle
Review and decide State licensing-board application batches (contractor eligibility, restricted liquor transfers, alcohol renewal queues) against a shared licensing data service. Use when the task involves contractor applications/bonds/insurance/violations, restricted liquor license staff packages, or alcohol renewal manual-review queues against a policies + records data service. Produces structured JSON decisions conforming to a per-task answer template.

0
installs
▌
Licensing Batch Review · prism-shadow bundle
Solve State licensing-board review tasks (contractor application eligibility, restricted liquor-license staff packages, alcohol renewal manual-review queues) against a shared licensing data environment. Use at the start of any task that reads a licensing/regulatory environment and returns a structured JSON decision package conforming to a provided answer template.

0
installs
▌
Asteria Fleet Data Quality Reconciliation · prism-shadow bundle
Solve Asteria Fleet Data Quality Hub reconciliation/certification tasks — reconcile overlapping source snapshots of fuel, freight, maintenance, and contact collections, compute quality/normalization metrics, infer opaque control codes, and emit the JSON certification answer. Read BEFORE acting on any task that names the "Asteria Fleet Data Quality Hub", mentions source-snapshot reconciliation, business cutoffs, canonical entities, quarantine, mismatch/unrecognized categories, channel readiness, or opaque Asteria control codes (IC/OR/FP, RB/SB/LD, MS/HR).

0
installs
▌
Atlas Commerce Ops Review · prism-shadow
Solve Atlas Commerce Operations cutoff-based analytical review tasks (fulfillment, refund, carrier, warehouse, support). Read request + template contracts literally, replay event history at a cutoff, dedup imported rows, and produce a JSON object that conforms exactly to the answer template.

0
installs
▌
Atlas Commerce Ops Scorecard · prism-shadow bundle
Solve Atlas Commerce Operations analytical scorecard, reconciliation, and data-correction requests against the authenticated workplace SQL service. Use when a task gives a business request JSON + an answer-template JSON and asks you to compute fulfillment, refund, carrier-quality, warehouse-productivity, or support-health metrics from the Atlas Operations database. Covers cohort scoping, snapshot-vs-event-history authority, raw/canonical fields, minor-unit money + FX, the controlled correction transaction, and the support active-time clock.

0
installs
▌
Pho Transportability Audit · prism-shadow bundle
Solve Public Health Observatory (PHO) reproducibility/transportability algorithmic-audit tasks. These tasks fetch surveillance + socioeconomic records from a read-only PHO data portal, resolve publication releases/cohorts under a strict evidence specification, run a set of registered statistical audit modules with exact reproducibility checkpoints (fixed seeds, PRNG streams, replicate counts, ordered arrays), apply controlled decision gates, and return one JSON object conforming to a per-task answer template. Invoke when a task references the PHO portal / a "six-module audit" / "transportability" / "publication cohort" / "robustness gates" / analysis_request.json + answer_template.json, or asks to audit whether an exposure-outcome signal survives controlled statistical gates.

0
installs
▌
Portfolio Work Review · prism-shadow bundle
Compute portfolio-mix, SLA-aging, and release-readiness reviews from a shared work-item environment. Use when a task asks for a closed-work portfolio mix vs target, an SLA breach/aging audit, or a release ship-readiness assessment, and points at a shared environment with work items, mix targets, SLA policy, releases, milestones, dependencies, and blockers.

0
installs
▌
Portfolio Engineering Audit · prism-shadow bundle
Entry instructions for solving portfolio-engineering audit tasks (work-item portfolio-mix reviews, SLA-aging audits, and release-readiness assessments) against the shared work-items environment. Use when you must produce a single JSON answer for one of these audit task types and want the validated field conventions for scope, classification, duplicates, authoritative-vs-stale fields, ordering, and precision.

0
installs
▌
Harborcrm Front Of Funnel · prism-shadow
End-to-end SOP for HarborCRM front-of-funnel CRM-marketing tasks — event sponsor/post-event handoff reconciliation, trade-show prospecting, and raw contact-import hygiene — over the read-only HarborCRM data API.

0
installs
▌
Peopleops Console Lifecycle Control · prism-shadow
Solve ERP HR "PeopleOps Console" lifecycle/leave/payroll/policy-case/recruitment/document/notice/audit tasks by cross-referencing the remote HTTP API and applying source-precedence, folder-readiness, notice-defect, and audit-scope business rules to emit normalized-label JSON.

0
installs
▌
Peopleops Console Case Resolution · prism-shadow
Resolve ERP HR "PeopleOps Console" lifecycle/leave/payroll/policy-case/recruitment/documents/messages/audit tasks by applying record-source precedence, folder/notice readiness gates, and scoped audit correlation, then emitting normalized enum labels.

0
installs
▌
Intake Coordination Portal Audit · prism-shadow bundle
Produce the required normalized JSON audit for a Cedar Ridge Intake Coordination Portal task — patient access verification, referral readiness / referral-to-chart activation, dialysis transfer review, or program enrollment panel. Use when a task points at an intake-coordination portal base URL plus an answer_template.json and asks for a batch/roster/program-level JSON report of statuses, blockers, reason codes, and cohort counts. Covers how to discover the data, apply the classification rules, and emit template-conformant JSON.

0
installs
▌
Intake Coordination Audit · prism-shadow bundle
Produce the required JSON for a Cedar Ridge Intake Coordination Portal structured-audit task — new-patient access verification, referral readiness audits, dialysis/transfer packet reviews, chronic-care program enrollment panels, and referral-to-chart activation. Use whenever a task gives a portal base URL plus an answer template (input/payloads/answer_template.json) and asks for a single JSON object of per-record findings and cohort/summary counts drawn from patients, coverage, PBM, pharmacies, referrals, transfers, documents, ICD codes, chart artifacts, program candidates, and facility capacity.

0
installs
▌
Payer Ops Case Determination · prism-shadow bundle
Produce a structured JSON determination for a Northstar-style health-plan "payer operations" case by reading the case's records out of the shared operations data environment and reasoning over policy criteria, evidence, and business rules. Use when a task asks for a JSON determination / disposition / repricing packet / summary for a prior-authorization, coverage-appeal, claim-payment-integrity, peer-to-peer, or finance/margin-queue work item, and gives you (a) a target business id, (b) access to a SQL-queryable operations environment, and (c) an answer_template that fixes the required output shape.

0
installs
▌
Payer Ops Determination · prism-shadow bundle
Use for Northstar-style payer-operations "structured determination" tasks: read a prompt plus task_context.json and answer_template.json, query a shared read-only payer-operations data environment (cases, members, plans, policies, criteria, documents, authorizations, appeals, drug trials, assistance screens, claims, payment benchmarks, P2P events, service-margin rows), apply the business rules, and return exactly one strict JSON object matching the template — including a basis_audit trail. Covers prior-authorization nurse determinations, pharmacy coverage appeals + manufacturer-assistance intake, claim repricing/benchmark validation, peer-to-peer (P2P) final summaries, and finance margin-queue analyses.

0
installs
▌
Payer Ops Structured Determination · prism-shadow bundle
Produce the exact structured JSON deliverable for a Northstar-style payer-operations task by reading a shared read-only case environment. Use this when a task hands you a target business ID (a case, appeal, claim, peer-to-peer event, or finance queue), a read-only operations environment (a SQL query endpoint plus business GET endpoints), and a JSON answer template to fill. Covers prior-authorization / UM nurse determinations, coverage-exception appeals with manufacturer-assistance intake, claim repricing against rate benchmarks, peer-to-peer closures, and margin-queue analysis.

0
installs
▌
Ehr Governance Packets · prism-shadow bundle
Produce normalized JSON for EHR / referral quality-governance tasks against a read-only EHR environment: duplicate-chart merge-readiness packets, specialty referral coordination packets, care-transition handoff packets, ServiceRequest quality checks, and referral-batch audits. Use whenever a prompt asks you to gather patient / duplicate-candidate / referral / ServiceRequest / provider / ICD-10 / service-code evidence and return one JSON object that conforms to a supplied answer_template.json. Triggers: "merge readiness packet", "referral coordination packet", "care transition packet", "duplicate review", "ServiceRequest quality", "referral batch audit", "normalized JSON conforming to input/payloads/answer_template.json".

0
installs
▌
Clinic Protocol JSON Assessment · prism-shadow bundle
Use when a task asks for a protocol-bound clinical decision-support result over a synthetic FHIR-like clinic runtime and requires returning a single strict-schema JSON object that conforms to a provided answer_template.json (e.g. respiratory/CAP triage, pediatric head-injury triage, potassium repletion, care-management routing, or observation-window retrieval). Covers how to read the record, apply the matching protocol, filter distractors, and emit exactly the required JSON. Not for free-text clinical advice or tasks without a fixed answer template.

0
installs
▌
Clinic Protocol Structured Response · prism-shadow bundle
Produce a single strict-JSON answer for protocol-bound clinical decision-support tasks against a synthetic FHIR-like clinic runtime. Use when a task gives a target case id, points to a runtime clinic environment (patients, cases, observations, medications, allergies, problems, imaging, registry, SDOH, protocols) plus a separately-listed access description, and asks for a JSON object conforming to an answer_template.json (e.g. respiratory/CAP triage, pediatric head-injury/concussion, electrolyte repletion, care-management routing, or observation-window retrieval).

0
installs
▌
Investigation Hub Production Gap Analysis · prism-shadow bundle
Produce a structured-JSON litigation e-discovery gap / production-readiness / remediation analysis for an investigation matter whose evidence lives in a read-only "Investigation Review Hub". Use when a task gives a matter_id, points at a review hub as the source of record, and asks for a JSON object conforming to a provided answer_template.json (critical findings, category statuses, retention/communication gaps, privilege corrections, top risks, metrics, prioritized actions, etc.). Covers subpoena/grand-jury/SEC/DOJ production reviews across custodian collection, preservation/retention loss, privilege logging, third-party waiver, and QC/responsiveness coding.

0
installs
▌
Court Clerk Closeout Reconciliation · prism-shadow bundle
Prepare a structured JSON closeout/register/field-packet for a court clerk by reconciling messy local materials (bench/hearing notes, clerk worksheets, finance-queue extracts, petition & budget summaries, form excerpts) against the authoritative court-operations records the task exposes (case, charge, docket, citation, fee-schedule, payment-policy, form, and financial-petition records). Use for criminal sentencing closeouts, traffic-violation dispositions with payment plans, and post-sentencing field packets (probation-referral / license suspension / installment-order forms). Trigger words: closeout, disposition register, reconcile, audit findings, fee reconciliation, payment plan / installment order, sentencing packet, clerk worksheet, hearing/bench notes.

0
installs
▌
Licensing Board Structured Decisions · prism-shadow bundle
Solve State Licensing Board / regulatory "structured decision" tasks that ask for a JSON answer conforming to a provided input/payloads/answer_template.json, built by reading a licensing data service (policies/rules plus contractor, liquor, or alcohol-renewal datasets, usually with a read-only SQL endpoint). Use for contractor batch eligibility reviews, restricted liquor-license staff packages, and alcohol renewal manual-review queues. Triggers: a prompt that assigns a licensing-examiner / staff-review role, lists GET endpoints under /api/... plus an answer template, and asks for determinations, deficiency/risk codes, control/obligation codes, verification gaps, monitoring plans, or a ranked review queue.

0
installs
▌
Ma Workbench JSON Deliverables · prism-shadow bundle
Produce structured JSON legal work product (issue registers, deviation matrices, committee escalation memos, closing/transition packages) from a read-only M&A deal workbench containing deal records, draft terms, playbook rules, policy thresholds, benchmarks, risk estimates, cap tables, consents, employees, material contracts, regulatory records, diligence findings, notes, and documents. Use whenever a prompt names a deal ID, points at a deal workbench, and requires an answer conforming to a supplied answer template.

0
installs
▌
Atlas Ops Analytical Scorecard · prism-shadow
Use when a task delivers a business "scorecard", "reconciliation", "review", "backlog", or "correction" as three files — a prompt, a request-policy JSON (scope, business definitions, rollups, tie-breaks, rounding, status rules), and an answer_template.json — to be computed against an authenticated, read-only SQL workplace/operations database and written as one JSON object to answer.json. Covers eligibility cohorts, "effective/canonical" entity reduction, exact UTC windows, rate/rounding rules, worst/top-N ordering with tie-breaks, ordered status-rule cascades, and single-row canonical corrections with an audit record.

0
installs
▌
Ops Request Scorecard · prism-shadow bundle
Use when a task provides an operations "request" JSON (business scope, metric and classification definitions) plus a strict answer_template JSON Schema and asks you to compute exact figures from an authenticated operations database and write them to answer.json. Covers cutoff/window-based scorecards, refund and money reconciliations, warehouse/support productivity and SLA reviews, and minimal canonical data-correction tasks. Turns a prose business spec into precise, schema-exact numeric answers derived from the live records.

0
installs
▌
Task Group 009 Fewshot Attempt 01 · prism-shadow
SOP for Crescent Finance Ops API reporting tasks. Use when a task provides environment_access.json, request_memo.json, and answer_template.json for branch or regional finance reporting, ensemble compensation summaries or forecasts, or touring production weekly payroll reviews.

0
installs
▌
Task Group 009 Fewshot Attempt 02 · prism-shadow
SOP for Crescent Finance Ops benchmark tasks involving branch and regional management reporting, current-year and forecast compensation summaries, and weekly payroll reviews using local Finance Ops API payloads. Use when Codex must read task prompt/payloads, fetch allowed Finance Ops API endpoints, compute finance, compensation, payroll, ranking, rounding, and answer-template JSON fields, while avoiding restricted test outputs, notes, evaluator files, and environment internals.

0
installs
▌
Task Group 009 Fewshot Attempt 03 · prism-shadow
Transferable SOP for Crescent Arts Collective Finance Ops API tasks in task_group_009 requiring branch close reporting, regional finance reporting, current-year ensemble compensation summaries, compensation forecasts, or touring theatre payroll/CBA review. Use when Codex must read input payloads, query the localhost Finance Ops API, calculate rounded JSON outputs, rank branches or regions, apply roster/scenario compensation rules, or compute payroll premiums, guarantees, vacation, substitute adjustments, and conflict flags.

0
installs
▌
Task Group 012 Fewshot Attempt 01 · prism-shadow
Use for Northwind PeopleOps Console tasks that require reconciling employee leave, payroll assignment, onboarding closeout, remote-work case folders/notices, recruitment outcomes, audit evidence, and JSON answers that must match an answer_template with normalized enum labels.

0
installs
▌
Task Group 012 Fewshot Attempt 02 · prism-shadow
Execute Northwind PeopleOps Console verification tasks involving onboarding closeout, leave source precedence, payroll assignment readiness, policy-case folder and notice controls, and recruitment reconciliation. Use when a task asks Codex to inspect the local PeopleOps web/API environment and return normalized JSON matching an answer_template.

0
installs
▌
Task Group 012 Fewshot Attempt 03 · prism-shadow
Use for Northwind PeopleOps Console tasks that require reconciling HR lifecycle records, leave/payroll source precedence, recruitment outcomes, folder/notice readiness, audit evidence, and writing evaluator-ready answer.json files from a provided answer_template.json.

0
installs
▌
Medbridge Sales Ops · prism-shadow
Produce account-ready JSON decision packages from the MedBridge Sales Ops API (CRM, quotes, freight/logistics, milestone receivables). Use this skill WHENEVER a task asks you to verify customer/quote/RFQ/opportunity records against a MedBridge Sales Ops API (base like http://127.0.0.1:<PORT>) and emit JSON matching an answer_template.json — including: catalog-tier quote pricing and EXW totals; EXW-plus-freight transport comparisons with route/border risk, freight validity and reconfirmation, and a recommended mode; module-only (IEHK / kit) indicative quotes; and opportunity-to-invoice-to-payment-to-revenue-journal reconciliation with outstanding balance, revenue recognition state, and CRM follow-up routing (collection, event/voucher invitation). Trigger even when the user only says "quote decision package", "freight comparison", "engagement / account reconciliation", "revenue recognition check", or names a MedBridge quote/RFQ/ opportunity ID (Q-*, RFQ-*, OPP-*), and never freelance the business rules below.

0
installs
▌
Crm Support Ticket Resolution · prism-shadow bundle
Resolve CRM support-console tasks against the shared read-only support API and emit JSON that conforms to the task's answer_template.json. Use this skill whenever a task asks you to act as a support analyst / contact-center lead / queue-quality analyst / enterprise support lead and to classify, route, or decide outcomes for service tickets, mobile cases, mobile-data worklists, or enterprise export incidents from support-console records. Triggers include: resolving a batch of offline/service tickets, choosing the next support operation for mobile/line cases, classifying a queue before SLA handoff, computing data-refuel charges, or preparing an enterprise export-complaint response package (root cause, failure window, SLA credit, owners, channel, evidence folder, report title, share permissions). Apply it even when the prompt does not name "support console" explicitly but references tickets, accounts, outages, diagnostics, lines, devices, plans, bills, cases, or enterprise incidents/export-runs and wants a struc

0
installs
▌
Erp Finance Close Tasks · prism-shadow bundle
Executable playbook for the shared ERP finance JSON API (claims, AP bills, payments, vendors, compliance, prepaids, GL, close logs). Use this whenever a task asks you to make a finance close/release decision from this API and return a JSON answer matching a provided answer_template.json — including reimbursement-to-AP close, expense-claim batch triage, vendor onboarding / intake compliance release, prepaid-to-GL amortization reconciliation, stale AP snapshot reconciliation, AP payment release after vendor account-change events, and month-end exception reporting. Trigger this skill even when the prompt only mentions "claim IDs", "business IDs", "AP batch", "prepaid close", "onboarding decision", "release posture", "aging", or "answer_template" without naming the workflow explicitly. It encodes the exact field definitions, decision enums, and rounding/sorting rules these graders check.

0
installs
▌
Erp Finance Close API · prism-shadow
Solve ERP finance close, AP, and vendor-compliance review tasks that read from the shared task_group_005 ERP finance JSON API (base http://127.0.0.1:8029). Use this WHENEVER a task asks you to decide claim/AP/reimbursement close status, compute AP open balances or aging, reconcile a stale AP snapshot, run a prepaid-to-GL close (straight-line amortization, GL variance), make vendor onboarding / intake compliance release calls (UBO counts, hard-stop flags), decide AP payment release after vendor account-change events, or produce month-end exception reports — and the answer must conform to an answer_template.json. Triggers include mentions of claims (CLM-*), AP bills (AP-*), payments, vendors/business IDs (BUS-*, VEN-*), compliance (PEP/sanctions/UBO/license/bank/tax/risk), prepaids (PPD-*), GL balances, close logs, "batch_status", "release posture", "reportable UBO", "hard_stop_flags", "variance_flag", or any instruction to return JSON matching a finance answer template. Use it even if the prompt cites a differ

0
installs
▌
Erp Finance Close Reviewer · prism-shadow
Executable playbook for the task_group_005 ERP finance JSON API: reimbursement-to-AP close reviews, vendor onboarding/intake compliance release, prepaid-to-GL close reconciliation, stale AP-snapshot reconciliation, AP payment release after vendor account changes, and month-end exception reporting. Use this whenever a task references expense claims, AP bills/payments/aging, vendor onboarding or compliance gates (profile/ownership/registry/screening/bank/risk), prepaid amortization vs GL balances, close logs, or asks for a JSON answer matching an answer_template against this ERP API — even if the prompt only mentions "the shared finance API", a batch of claim IDs, or a batch of business IDs. It encodes the exact field definitions, decision rules, enum values, rounding, sorting, and pitfalls (stale snapshots, voided bills, amount/vendor mismatches, non-unique bill IDs, cleared-vs-processing payments) needed to reproduce the official answers.

0
installs
▌
Procureops Erp Answers · prism-shadow bundle
Produce the required JSON answer for ProcureOps ERP "Procurement Supplier and Receiving Control" tasks: sourcing nomination readiness, receiving/AP three-way reconciliation, AP close hold/release queues, contract + budget change-control decisions, and AP release/chargeback netting. Use this whenever a task points at the ProcureOps API (a localhost service exposing /programs, /suppliers, /contracts, /purchase_orders, /receipts, /ap/invoices, /ap/payments, /approval_events, /budget_snapshots, /vendor_risk_events) and asks for a JSON answer matching an answer_template.json, even if the prompt only says "nomination packet", "receiving closeout", "AP close", "change control decision file", "release file", "budget headroom", "vendor risk", or "reconciliation". Treat the live API as the source of truth over any local memo/export. Reach for this skill before hand-rolling any procurement/AP/ERP computation.

0
installs
▌
Procureops Control Answers · prism-shadow bundle
Produce the required JSON answer for ProcureOps ERP "Procurement Supplier and Receiving Control" tasks: sourcing nomination readiness packets, receiving/AP three-way reconciliation, AP close hold/release decisions, contract change-control decision files, budget/contract headroom checks, vendor-risk scoping, and AP release/chargeback netting. Use this skill WHENEVER a task references the ProcureOps API (a localhost service exposing /programs, /suppliers, /contracts, /purchase_orders, /receipts, /ap/invoices, /ap/payments, /approval_events, /budget_snapshots, /vendor_risk_events), asks you to fill an answer_template.json against ERP records, or mentions nomination, receiving control, AP hold/release, three-way match, chargeback, budget headroom, or supplier-risk-as-of-date — even if the words "ProcureOps" or "ERP" are not used but a localhost procurement API plus a JSON answer template are involved.

0
installs
▌
Northwind Erp Ops · prism-shadow bundle
Solve Northwind Components ERP operations tasks against the shared read-only ERP HTTP API: expedite/dispatch-control decisions, mixed-warehouse allocation and transfer decisions, kit/BOM replenishment packages (transfers + purchase requisitions), supplier incident scorecards, and supplier quality-hold / replenishment-control reviews. Use this skill whenever a task references the Northwind ERP, a wave (e.g. TRAIN_*), an allocation or expedite "desk", a "memo"/"scorecard request"/"review memo" plus an answer_template.json, BOM/kit builds, supplier incidents or RMAs, shipping quotes, or asks for a structured JSON decision file driven by live ERP records. Apply it even when the task only hints at these (e.g. "classify these orders", "which POs to hold", "Q1 supplier scorecard") because the business rules, effective-stock formula, API usage, and output conventions are shared and non-obvious.

0
installs
▌
Private Wealth Advisory · prism-shadow bundle
Produce the structured JSON planning output for private-wealth / estate advisory tasks that query the read-only advisory API (clients, source-documents, retirement-accounts, life-insurance, trust-candidates, policies/tax, rmd-factors) and return an answer matching a given answer_template.json. Use this skill whenever a task asks you to act as a private wealth / estate / tax advisory analyst and emit a JSON object for any of these families: Roth conversion + RMD tax summary (roth_conversion_rmd), ILIT / Crummey funding cycle (ilit_crummey_implementation), GRAT vs CRAT trust comparison (trust_comparison), or an integrated estate-liquidity action plan (estate_liquidity_action_plan). Triggers include mentions of Roth conversions, required minimum distributions, ILIT/Crummey notices, gift-tax annual exclusion, GRAT, CRAT, estate-tax exemption or exposure, liquidity gaps, or "conforms to answer_template.json" against an advisory API. Apply it even when the request only gives a client ID and a request memo.

0
installs
▌
Asteria Investment Office · prism-shadow
Produce strict-JSON deliverables for the Asteria Investment Office (CIO / credit desk) task family: energy/fixed-income credit trade packages, international equity correlation reviews, cross-asset active-allocation view refreshes, fixed-income risk rebalances, multi-asset risk-board reconciliations, and committee combined-decision files. Use whenever a task references the Asteria shared environment / book-of-record, a PF-* portfolio, an answer_template.json output contract, allocation views, index correlations, energy-credit trades, watchlist/HY constraints, or active-allocation rationale codes. The environment is a read-only HTTP/JSON API; outputs must follow the provided answer_template exactly (enums, ordering, rounding).

0
installs
▌
Asteria Investment Office Tasks · prism-shadow
Solve Asteria Investment Office (CIO / credit desk) JSON tasks: energy/fixed-income credit trade packages, international equity correlation reviews, cross-asset active allocation view refreshes, fixed-income risk rebalances, and combined committee decision files. Use when a prompt references the Asteria shared environment, a PF-* portfolio, an answer_template.json output contract, opportunity-set allocation views (UW/N/OW), index correlation reviews, or energy-credit trade strategy. Covers which HTTP API endpoints to call, exact computation formulas and rounding, controlled enum mapping, current-environment-over-stale-payload precedence, and constraint checks.

0
installs
▌
Credit Committee Packets · prism-shadow bundle
Produce committee-ready JSON answers for the shared "credit office" lending-committee task family (bank branches and credit-union segments served by the HTTP API at http://127.0.0.1:8003). Use this skill whenever a prompt asks you to prepare a JSON deliverable for a Credit Risk Committee / lending committee about a branch_id or segment_id and one of these jobs: re-derive/migrate loan risk ratings, build a watch-list stress packet (+200bp DSCR stress, CDFI risk classes, workout queue), allocate pending applications against quarterly lending capacity with concentration flags and decline reason codes, compare competing CRE applications with weighted scoring, or write a credit-union segment posture page from NCUA benchmarks. Trigger on terms like rating migration, NPA benchmark, material downgrade, watch-list, adverse-rated, CDFI risk class, DSCR stress, lending capacity allocation, concentration ceiling, sector breach, decline reason codes, CRE weighted score, segment posture, escalation triggers — even when the

0
installs
▌
Peopleops Console Review · prism-shadow bundle
Answer PeopleOps Console HR-lifecycle review/control tasks against the local JSON API: onboarding closeout, leave source-precedence, payroll/accrual readiness, document-folder readiness and formal-notice quality, recruitment reconciliation, and audit-scope decisions. Use this whenever a task points at an "HR portal / PeopleOps Console" and asks you to determine the authoritative record, exclude draft/superseded/losing records, check folder readiness, judge notice quality/defects, pick the controlling/supporting audit event, gate approval vs closeout, or sum recruitment cost — and to emit JSON matching a given answer_template.json with normalized business-label enums. Trigger it even when the prompt only names an employee/case/opening ID and asks for a "control result", "next action", "precedence", "readiness", or "reconciliation".

0
installs
▌
Clinic Protocol Answer · prism-shadow bundle
Produce a protocol-bound clinical decision-support JSON answer for a synthetic clinic case served by a read-only FHIR-like runtime API. Use this whenever a task names a target case id (e.g. CASE-RESP-102, CASE-HEAD-207, CASE-K-303, CASE-CM-411, CASE-LAB-518), points at a runtime environment via GDPEVO_ENV_BASE_URL / <TASK_ENV_BASE_URL>, and asks for a single JSON object that conforms to an input/payloads/answer_template.json. Covers respiratory/CAP assessment, pediatric head-injury triage, potassium replacement, care-management routing, observation-window retrieval, and similar template-driven answers with controlled enums, numeric-precision fields, evidence_ids, and safety_checks.

0
installs
▌
Task Group 011 Fewshot Attempt 03 · prism-shadow
Produce committee-ready JSON answers for credit-office API tasks involving branch loan regrades, lending allocation decisions, CRE application comparisons, watch-list stress packets, and credit-union segment posture reviews. Use when a prompt provides a credit office public API base URL, branch_id or segment_id, and an answer_template.json with required fields, enum choices, ordering, and precision rules.

0
installs
▌
Task Group 002 Fewshot Attempt 01 · prism-shadow
Use this skill for MedBridge Sales Ops input/output tasks that require reading a prompt and answer_template.json, calling the shared local API, and returning account-ready JSON for quote pricing, freight decisions, RFQs, milestone reconciliation, revenue recognition, event invitations, or voucher controls. Trigger whenever the task mentions MedBridge Sales Ops, quote/RFQ decisions, product catalog tiers, freight options, opportunity reconciliation, invoices, payments, revenue journals, events, vouchers, or asks for JSON matching an input template.

0
installs
▌
Task Group 002 Fewshot Attempt 02 · prism-shadow
Use this skill for MedBridge Sales Ops input/output tasks that ask for account-ready JSON from a local API, especially quote revisions, module RFQs, freight comparisons, opportunity reconciliation, milestone invoices, revenue recognition, event invitations, and voucher controls. Trigger whenever a task mentions MedBridge Sales Ops, API_BASE_URL/BASE_URL, quote/RFQ/customer/catalog/freight/policy verification, or CRM opportunity/invoice/payment/revenue/event reconciliation; the answer must be valid JSON matching the provided input answer_template.

0
installs
▌
Task Group 002 Fewshot Attempt 03 · prism-shadow
Use this skill for MedBridge Sales Ops evaluation tasks that ask for account-ready JSON from a local API and an input/payloads/answer_template.json file. It covers quote/RFQ pricing, freight decisions, customer payment policies, opportunity milestone reconciliation, revenue recognition, invoice follow-ups, events, and vouchers. Always use this when the task mentions MedBridge Sales Ops, API_BASE_URL or BASE_URL, quote/RFQ IDs, freight options, opportunities, milestones, revenue journals, or JSON matching an answer template.

0
installs
▌
Task Group 003 Fewshot Attempt 03 · prism-shadow
Use this for task_group_003 support-console tasks involving wireline service tickets, mobile support cases, or enterprise export incidents. It gives API lookup steps, routing rules, output-field meanings, and pitfalls learned from training inputs and answers.

0
installs
▌
Task Group 011 Fewshot Attempt 02 · prism-shadow
Produce strict JSON answers for credit-office committee tasks using only public API data and the provided answer_template.json. Use for branch loan regrades, watch-list stress packets, pending-application allocations, competing CRE decisions, and credit-union segment posture recommendations that require policies, branch or segment metrics, FDIC/NCUA benchmarks, controlled enums, sorted lists, and reconciled numeric totals.

0
installs
▌
Task Group 011 Fewshot Attempt 01 · prism-shadow
Prepare strict committee-ready JSON answers for task_group_011 credit-office input/output evaluation tasks using only the provided prompt, answer_template.json, and public credit-office API endpoints. Use when a task asks for branch rating migration, lending allocation, credit-union segment posture, watch-list stress/workout queues, or competing CRE application recommendations with controlled enums, ordered lists, rounded numeric fields, and no narrative outside JSON.

0
installs
▌
Task Group 010 Fewshot Attempt 01 · prism-shadow
Solve PanofyBench task_group_010 Asteria Investment Office input-output tasks that require reading local request/template JSON, using the public Asteria API at http://127.0.0.1:8036 as the current book of record, computing portfolio credit metrics, index correlations, active allocation views, and returning only schema-conforming JSON.

0
installs
▌
Task Group 010 Fewshot Attempt 02 · prism-shadow
Generate JSON answers for Asteria Investment Office portfolio-risk tasks using the public Asteria API. Use when prompts ask for credit trade or rebalance packages, equity correlation reviews, active allocation views, or committee decision JSON based on portfolios, bonds, issuers, policies, index levels, prior views, and macro signals.

0
installs
▌
Task Group 003 Fewshot Attempt 01 · prism-shadow
Use this skill for task_group_003 support-console tasks that require producing answer.json from ticket batches, mobile support case queues, mobile data worklists, or enterprise export complaints. It gives the API lookup order, routing rules, output field meanings, and common pitfalls learned from official input/output examples.

0
installs
▌
Task Group 004 Fewshot Attempt 02 · prism-shadow
Use this skill whenever a task asks for ApexCloud CRM, ApexCloud Retention Operations API, renewal risk, retention action boards, QBR metrics packets, receivables and pipeline reviews, or churn export validation. It guides API collection, source precedence, controlled labels, ranking, precision, and JSON-only output for ApexCloud customer success and retention analytics.

0
installs
▌
Task Group 004 Fewshot Attempt 03 · prism-shadow
Use for ApexCloud CRM retention analytics tasks that call the ApexCloud Retention Operations API and must return strict JSON for renewal risk queues, QBR metrics packets, receivables and pipeline reviews, churn validation/ranking, or high-touch retention action boards. Captures reusable endpoint usage, source-of-truth choices, data hygiene rules, controlled enum mappings, policy-code conventions, and output formatting pitfalls.

0
installs
▌
Task Group 001 Fewshot Attempt 01 · prism-shadow
Produce HarborCRM JSON answers for evaluation tasks that provide prompts, answer_template.json files, and HarborCRM API data. Use when reconciling event sponsorships, badge leads, campaign members, finance invoices, trade-show prospecting, or import batch hygiene into exact JSON output schemas with controlled enums, counts, dates, and CRM actions.

0
installs
▌
Task Group 001 Fewshot Attempt 02 · prism-shadow
HarborCRM JSON handoff procedures for tasks that ask Codex to use HarborCRM API data and an answer template to prepare event sponsor reconciliation, badge and campaign-member handoffs, trade-show prospecting summaries, or CRM import batch cleanup. Use when outputs must be JSON-only, template-shaped, policy-aware, sorted, normalized, and reconciled against HarborCRM accounts, contacts, opportunities, invoices, campaign members, exhibitors, or suppression records.

0
installs
▌
Task Group 001 Fewshot Attempt 03 · prism-shadow
HarborCRM JSON-output procedures for event sponsor/lead reconciliation, tradeshow prospecting, and CRM import-batch cleanup using HarborCRM API data and answer templates. Use when a task asks Codex to produce structured JSON from HarborCRM events, sponsor packages/orders, badges, invoices, CRM accounts/contacts/opportunities, campaign members, tradeshow exhibitors/meeting interest, import batches/raw contacts/suppression, or policy metadata.

0
installs
▌
Task Group 004 Fewshot Attempt 01 · prism-shadow
Build ApexCloud CRM retention analytics outputs from the ApexCloud Retention Operations API and strict JSON answer templates. Use for tasks involving renewal risk queues, QBR metrics packets, receivables and pipeline operations reviews, churn model validation, candidate outreach ranking, high-touch retention action boards, or any ApexCloud CRM retention workflow requiring controlled labels, policy codes, deterministic rounding, and JSON-only output.

0
installs
▌
Task Group 005 Fewshot Attempt 01 · prism-shadow
Solve task_group_005 finance/API JSON-output tasks involving reimbursement AP close, stale AP snapshots, prepaid close reconciliation, vendor onboarding controls, and account-change payment release risk reviews.

0
installs
▌
Task Group 005 Fewshot Attempt 02 · prism-shadow
Solve PanofyBench task_group_005 finance/API fewshot tasks for reimbursement/AP close, stale AP batch refresh, vendor onboarding/release risk, prepaid close reconciliation, and account-change payment release. Use when Codex must read local scope/template payloads, query the shared ERP/compliance API, apply finance-control rules, and return strict JSON matching an answer_template.json.

0
installs
▌
Task Group 005 Fewshot Attempt 03 · prism-shadow
Solve PanofyBench task_group_005 ERP, AP, prepaid close, vendor onboarding, and account-change release tasks by using the shared JSON API and returning schema-exact JSON outputs.

0
installs
▌
Task Group 006 Fewshot Attempt 01 · prism-shadow
Solve ProcureOps procurement, receiving, AP close, change-control, and AP release benchmark tasks by combining task-local payload anchors with the ProcureOps API and returning exact JSON matching the provided answer template.

0
installs
▌
Task Group 006 Fewshot Attempt 02 · prism-shadow
Solve ProcureOps fewshot benchmark tasks that require reading task-local payloads, querying the ProcureOps API, reconciling procurement/AP/receiving records, and returning only schema-conformant JSON.

0
installs
▌
Task Group 006 Fewshot Attempt 03 · prism-shadow
Solve ProcureOps procurement, receiving, AP close, change-control, and release-decision tasks that provide local input payloads plus a shared ProcureOps API, returning strict JSON matching the task answer template.

0
installs
▌
Task Group 007 Fewshot Attempt 01 · prism-shadow
Use for Northwind Components ERP decision tasks that require JSON outputs for order expedition, kit replenishment, supplier incident scorecards, allocation transfer decisions, or procurement quality holds using the local shared API.

0
installs
▌
Task Group 007 Fewshot Attempt 02 · prism-shadow
Use for Northwind Components ERP tasks that require JSON answers for dispatch expedite queues, warehouse allocation and transfer waves, kit replenishment planning, supplier incident scorecards, or procurement quality-hold reviews using the local ERP API.

0
installs
▌
Task Group 007 Fewshot Attempt 03 · prism-shadow
Use for Northwind Components ERP decision tasks that require JSON answers built from task memos/templates plus the shared ERP API, including expedite dispatch, transfer allocation, kit replenishment, supplier incident scorecards, and procurement quality holds.

0
installs
▌
Task Group 008 Fewshot Attempt 01 · prism-shadow
Solve private wealth advisory input/output tasks that require reading a request memo and answer template, querying the local advisory API, resolving conflicting client sources, calculating Roth/RMD, ILIT Crummey, GRAT/CRAT, and estate-liquidity outputs, and returning strict JSON.

0
installs
▌
Task Group 008 Fewshot Attempt 02 · prism-shadow
Solve private wealth advisory benchmark tasks that ask for structured JSON planning outputs using the advisory API, local request memo, and answer template. Use for Roth conversion/RMD summaries, ILIT Crummey funding cycles, GRAT versus CRAT comparisons, and combined estate liquidity action plans where source records may conflict.

0
installs
▌
Task Group 008 Fewshot Attempt 03 · prism-shadow
Solve private-wealth advisory input/output JSON tasks that require reading a local request memo and answer template, querying the advisory API, resolving conflicting client sources, and computing Roth/RMD, ILIT Crummey, GRAT/CRAT, or estate-liquidity planning outputs.

0
installs
▌
Task Group 003 Fewshot Attempt 02 · prism-shadow
Use this skill when solving task_group_003 support-console tasks involving residential service tickets, mobile support cases, mobile-data recovery worklists, or enterprise export-complaint response packages. It gives the learned fewshot rules, API lookup sequence, JSON field definitions, summary counting rules, and common pitfalls for this task group.

0
installs
▌
Task Group 010 Fewshot Attempt 03 · prism-shadow
Solve PanofyBench task_group_010 Asteria Investment Office input-output tasks. Use when producing JSON answers from local request payloads and the public Asteria API at http://127.0.0.1:8036 for credit trade packages, fixed-income risk rotations, equity index correlations, allocation views, and multi-asset committee files.

0
installs
▌
Verify LLM Vendors · prism-shadow bundle
Run the Verify LLM Vendors benchmark using the PyPI-installed `agent-vendor-verifier` CLI; before each test run validate that config.yaml is complete, ask the user for any missing required config values, then read config and confirm with the user the list of models, vendors and baseline from config plus test-file-path, config-file-path, vendor-concurrency, request-concurrency, retries, timeout; before running, check whether `agent-vendor-verifier` is installed and install it from PyPI if missing; when the user asks to add or update a benchmark test plan, ask for model name, model id, vendor, api key, provider if needed, and write the entry into config.yaml; generate or edit config.yaml; check whether runs succeeded via summary.json; aggregate or report run data and final results. Use when the user wants to run the tool-call validation benchmark, add or update test plans, create or change benchmark config, inspect benchmark outcomes, verify success from summary files, or get a consolidated view of metrics (suc

0
installs

997 published skills · page 10 of 10