prism-shadow
- 997 skills
- 0 followers
- 14 hours ago last updated
- ▌ Finance Ops Reporting 5 · prism-shadowSOP for Crescent Finance Ops branch reporting, CBA compensation forecasting, and theatre payroll control tasks against the remote Finance Ops API.
- ▌ Finance Ops Reporting 6 · prism-shadowSOP for Crescent Finance Ops branch reporting, CBA compensation forecasting, and theatre payroll control tasks against the remote Finance Ops API.
- ▌ Asteria Investment Office JSON 3 · prism-shadowProduce the Asteria Investment Office portfolio JSON deliverables (energy-credit trade packages, international equity correlation reviews, active allocation refreshes, fixed-income risk rebalances, and multi-asset committee decisions). Treat the shared Asteria HTTP environment as the authoritative book of record over any local payload, apply the documented policy thresholds, and emit answers that exactly match each task's answer_template (field names, enum value sets, rounding, id ordering). Use this whenever a prompt references Asteria portfolios (PF-*), bonds (BND_*), issuers (ISS_*), indices (IDX_*), opportunity sets, macro signals, or allocation policy.
- ▌ Asteria Investment Office JSON 4 · prism-shadowProduce committee-grade JSON answers for the Asteria Investment Office across five portfolio archetypes — (a) energy-credit trade packages, (b) international equity correlation reviews, (c) active allocation-view refreshes, (d) fixed-income risk rebalances, and (e) multi-asset committee decisions. Covers the exact endpoints to pull, the deterministic computation recipes (Pearson correlation on monthly simple returns, notional-weighted modified duration and YTM, HY allocation %, carry, concentration), the policy thresholds that drive views/conviction/constraint checks, and the output-schema conventions (field names, enum sets, rounding, id ordering) that the desk's answer templates require. Use whenever a task references an Asteria portfolio (PF-*), index (IDX_*), bond (BND_*), issuer (ISS_*), policy (POL_*), or an answer_template.json.
- ▌ Asteria Investment Office JSON Desk 2 · prism-shadowProduce committee-grade JSON for the Asteria Investment Office across five task archetypes: (a) energy-credit trade packages, (b) international equity correlation reviews, (c) active allocation view refreshes, (d) fixed-income risk rebalances, and (e) multi-asset committee decisions. Pulls every fact from the shared Asteria HTTP environment (the book of record), runs the exact quantitative recipes (Pearson correlation, weighted duration/YTM, HY %, view mapping), applies the policy thresholds and exclusion rules, and emits output that conforms exactly to the task's answer_template (field names, enum value sets, rounding, id ordering).
- ▌ Reflect 3 Attempt 01 27 · prism-shadowJudge-refined credit-risk / lending-committee SOP for the prismshadow credit-office API (rating re-derivation, CDFI scoring, concentration/DSCR stress, benchmark variance, segment posture).
- ▌ Reflect 3 Attempt 02 31 · prism-shadowFeedback-refined credit-risk / lending-committee SOP for the prismshadow credit office API (ratings, CDFI scoring, DSCR stress, concentration, segment posture).
- ▌ Reflect 3 Attempt 03 29 · prism-shadowValidated credit-risk / lending-committee SOP for the credit office environment (rating re-derivation, CDFI scoring, capacity/concentration, DSCR stress, CRE decisions, segment posture).
- ▌ Peopleops Console Lifecycle Control 2 · prism-shadowResolve PeopleOps Console HR lifecycle/leave/payroll/policy-case/recruitment/document/audit tasks by applying source-precedence, folder-readiness, notice-defect, and audit-scope rules and emitting the template's normalized business labels.
- ▌ Cedar Ridge Intake Reconciliation 7 · prism-shadow bundleSolve Cedar Ridge Intake Coordination Portal reconciliation tasks — the family of jobs that point at a shared healthcare intake portal (patients, referrals, transfers, charts, coverage, PBM, pharmacies, ICD codes, program candidates) and ask for ONE strict JSON object that follows a provided answer_template.json. Covers new-patient access verification, referral readiness audits, transfer/dialysis intake review, chronic-care enrollment panels, and referral-to-chart activation. Use whenever a task references the Cedar Ridge / intake-coordination portal, gives an answer_template with enum allowed_values and ordering rules, and wants patient/referral/transfer-level status derivation plus cohort summary counts.
- ▌ Ehr Governance Packet 8 · prism-shadow bundleProduce the normalized JSON deliverable for an EHR quality-governance task — duplicate-merge readiness packets, specialty referral coordination packets, care-transition handoff packets, duplicate-review + ServiceRequest QA, and referral-batch audits. Use when a prompt gives clinical/governance object IDs (patients, duplicate candidates, referrals, ServiceRequests, batches) plus an `input/payloads/answer_template.json`, and asks for normalized JSON that reconciles a read-only EHR/referral environment against that template. Read this before gathering data or writing the answer.
- ▌ Ehr Governance Packets 2 · prism-shadow bundleProduce normalized JSON for EHR quality-governance / care-coordination packet tasks against a read-only EHR "quality API": duplicate-chart merge-readiness packets, specialty referral coordination letters, care-transition/handoff packets, duplicate-review + service-request validation, and referral-batch audits. Use whenever a prompt hands you case objects (patient IDs, a duplicate candidate ID, a referral or referral-batch ID, a service-request ID, a recipient provider) plus an answer_template JSON schema and asks for a single normalized JSON object reconciling the chart, coding, evidence, provider contacts, and readiness/disposition. Triggers: "merge readiness", "referral coordination packet", "care transition packet", "duplicate review", "ServiceRequest quality", "referral audit", "normalized JSON conforming to answer_template".
- ▌ Clinic Protocol Decision Support 5 · prism-shadow bundleUse when a task asks you to prepare a structured, protocol-bound clinical decision-support result for a single synthetic-clinic case and return ONE JSON object that conforms to a provided answer template. Fits prompts that name a target case id (e.g. respiratory / pneumonia assessment, pediatric head-injury triage, potassium/electrolyte repletion, care-management routing, or an observation-window / lab-retrieval gate), point you at a read-only clinic runtime, and require enum/number/list fields with no prose. Covers how to read the template as a contract, pull the case bundle and the matching protocol, filter records to the authoritative in-scope set, apply protocol thresholds and formulas, and shape output so it scores well.
- ▌ Investigation Review Gap Analysis 2 · prism-shadow bundleProduce a single structured-JSON gap / defect / remediation analysis for a litigation or investigation matter, driven entirely by an "Investigation Review Hub" dataset and conforming to a task-provided answer_template.json. Use this whenever a task asks for a production gap analysis, a retention / litigation-hold gap review, a cross-system remediation dashboard, a production-readiness review, or a similar structured e-discovery deliverable whose evidence lives in a review hub exposing tables such as matters, subpoena_categories, production_stats, custodian_sources, review_documents, privilege_entries, qc_findings, retention_events, and remediation_actions.
- ▌ Investigation Review Hub Gap Analysis 9 · prism-shadow bundleProduce a structured JSON gap/remediation analysis for a litigation or investigation matter from an "Investigation Review Hub" style data source (matters, subpoena categories, productions, custodian sources, review documents, privilege entries, QC findings, retention events, remediation actions). Use when a task asks for a first-rolling-production gap analysis, retention/litigation-hold gap review, production-readiness review, or cross-system remediation dashboard, and the answer must conform to a provided answer_template.json. The core skill is separating the handful of MATERIAL escalated records from the surrounding realistic NOISE, then mapping them faithfully into the template's objects, metrics, enums, and ordering.
- ▌ Court Closeout Reconciliation 6 · prism-shadow bundlePrepare a court clerk closeout / field packet by reconciling local draft documents (finance-queue extracts, worksheets, hearing/closeout notes, intake sheets, petitions, form excerpts) against an authoritative Court Operations Portal, then emit ONE strict JSON object that matches a provided answer_template.json. Use for criminal sentencing closeouts, traffic-violation dispositions with payment plans, and financial/installment-petition packets (probation-referral, license-suspension, installment-order forms). Trigger whenever the inputs pair local "draft/carry-forward/queued" values with a portal/CMS plus an answer_template that lists required keys, enums, ordering rules, and currency/date formats.
- ▌ Court Closeout Reconciliation 7 · prism-shadow bundleProduce a clerk-ready court-operations closeout packet as a single structured JSON object matching a provided answer template, by reconciling local case materials (hearing/bench notes, clerk audit or supervisor memos, finance queue or worksheet extracts, financial petitions, and local form excerpts) against the authoritative court operations portal (system of record). Use for criminal sentencing/disposition closeouts, disposition registers, fee reconciliation, traffic-citation closeouts, installment/extended payment plans, probation referrals, and license-suspension orders. Triggers when a task gives target cases/citations/petitions plus mixed local documents and a portal, and asks for audit findings, corrected dispositions, fee/register totals, payment schedules, form/placeholder handling, or excluded-charge lists in a schema-constrained JSON.
- ▌ Licensing Review Decisions 3 · prism-shadow bundleProduce a strictly template-conformant JSON decision for a state licensing-review task (contractor application-batch eligibility, restricted liquor-license staff package, or alcohol renewal manual-review queue) driven by records in a shared licensing data environment. Use when a prompt casts you as a licensing/renewal examiner reviewing target ids and points you at a policy/rules table plus per-domain record tables, and asks for JSON matching an answer_template. Covers how to read the template, gather complete data, apply the governing policies, separate signal from distractors, and roll up a consistent summary.
- ▌ Licensing Review 8 · prism-shadow bundleSolve structured licensing / regulatory review tasks that read a prompt plus a strict JSON answer template, query a licensing data service (REST + a SQL endpoint), apply agency policy logic to specific target records, and emit only JSON matching the template. Covers three task families: contractor batch eligibility review, restricted liquor-license staff package, and alcohol renewal manual-review queue. Use when a task gives target IDs, points at /api/... endpoints, and supplies input/payloads/answer_template.json.
- ▌ Ma Deal Workbench 3 · prism-shadow bundleProduce structured JSON deliverables (issue registers, deviation matrices, committee escalation memos, closing/transition packages) from an M&A deal workbench API against a supplied answer template. Use whenever a task gives a deal_id, a workbench base URL, and an answer_template.json to conform to.
- ▌ Ma Deal Workbench Review 7 · prism-shadow bundleProduce structured JSON deliverables (issue registers, deviation matrices, committee escalation memos, closing/transition packages) from an M&A "deal workbench" web app plus an answer_template.json. Use whenever a task gives a deal ID, points at a workbench that serves deal, playbook, and policy records, and demands JSON conforming to a supplied template with fixed enums, stable record IDs, and integer-dollar / percent-point units.
- ▌ Asteria Fleet Data Quality Hub 3 · prism-shadow bundleSolve "Asteria Fleet Data Quality Hub" reconciliation/certification tasks: read a case_scope.json + answer_template.json + a runtime access file, query a shared read-only data hub, reconcile overlapping source snapshots into canonical records, normalize with reference tables, compute the requested counts/rollups/rankings and status decision, and return one JSON object matching the answer contract exactly. Use whenever a task references the Asteria Fleet Data Quality Hub, a "Fleet Data Quality Hub", contact/fuel/freight/ maintenance source reconciliation, canonical entity resolution, quarantine/normalization audits, or opaque IC/OR/FP/RB/SB/LD/MS/HR control codes.
- ▌ Fleet Data Quality Reconciliation 2 · prism-shadow bundleSolve "Asteria Fleet Data Quality Hub" reconciliation, cleanup, and certification tasks. Use when a task gives a prompt plus payloads/case_scope.json and payloads/answer_template.json and asks you to reconcile overlapping source snapshots for a collection (contacts / fuel / freight / maintenance) as of a business cutoff and emit one JSON object matching the answer contract (quality counts, duplicate/quarantine sets, normalized totals, focus rollups, rankings, opaque control codes, and a certification/close decision). Runtime connection details come from the task's own environment_access.md.
- ▌ Asteria Fleet Dq Reconciliation 2 · prism-shadow bundleSolve an Asteria "Fleet Data Quality Hub" reconciliation task. Use when a task gives you payloads/case_scope.json plus payloads/answer_template.json and asks you to reconcile overlapping source records from a read-only data hub (catalog, schema, SQL query, source-snapshot, contact/transaction/maintenance, and reference alias/conversion/fx interfaces) and return exactly one JSON object. Covers three task families: contact-master reconciliation, transaction normalization (fuel/freight), and maintenance-log integrity.
- ▌ Atlas Ops Reporting 6 · prism-shadow bundleUse when a task asks you to produce an operational reporting result written to answer.json for the "Atlas Commerce Operations" workplace — e.g. a fulfillment cutoff scorecard, a refund/settlement reconciliation, a carrier-quality correction, a warehouse-productivity review, a support-health review, or any similar request that pairs a business request-payload JSON with an answer_template JSON Schema and a governed SQL data service. It guides you to read both contracts, discover the real schema, translate business definitions into precise read-only SQL (eligibility windows, quantifiers, FX conversion, medians, active-time clocks, ordering/tie-breaks, rounding, status/risk bands), apply a minimal approved correction with an audit row through the controlled transaction interface when one is requested, and emit an answer that conforms exactly to the template.
- ▌ Pho Algorithmic Audit 7 · prism-shadow bundleSolve Public Health Observatory (PHO) "registered algorithmic audit" analysis tasks — the ones that hand you a prompt.txt plus payloads/analysis_request.json and payloads/answer_template.json and point you at a read-only web data portal (a "<TASK_ENV_BASE_URL>" placeholder; a Public Health Observatory / Observatory data portal with /catalog, /methodology, state_health, county_health, country_indicators, socioeconomic, and revisions datasets). Use it whenever the request asks for a publication/cohort audit followed by a fixed roster of ~6 statistical "modules" (fixed-effects or GMM jackknife, nested ridge/elastic-net cross-validation, wild cluster bootstrap-t, grouped split conformal, trajectory PCA + k-means stability, source/year perturbation or Shapley, mediation, sensitivity surfaces) and a gated PASS/FAIL decision or classification, returned as one strict JSON object conforming to the answer template.
- ▌ Pho Algorithmic Audit 8 · prism-shadow bundleSolve Public Health Observatory (PHO) "registered algorithmic audit" tasks: a prompt plus an analysis_request.json and answer_template.json that ask you to build cohorts from a read-only health/socioeconomic data portal and run a registered multi-module statistical audit (fixed-effects/GMM jackknife, nested ridge/elastic-net CV, wild cluster bootstrap-t, split conformal, trajectory PCA+k-means stability, source/feature perturbation) into one strict JSON object. Use when a task references the PHO portal, a six-module robustness/transport audit, registered final-release resolution, cohorts, and a controlled decision.
- ▌ Pho Registered Audit 4 · prism-shadow bundleSolve "Public Health Observatory" (PHO) registered algorithmic-audit tasks: a business prompt plus a formal analysis_request.json (protocol: cohorts, statistical modules, seeds/grids, robustness gates, decision rule) and a strict answer_template.json (output contract), backed by a read-only public-health data portal. Use this whenever a task hands you an analysis_request.json / answer_template.json pair that references a health-observatory Web portal and asks for one JSON object of resolved releases, cohorts, multi-module diagnostics, and a controlled decision. Covers state / county / country geographies and the recurring six-module audit anatomy (fixed-effects & jackknife, nested ridge / elastic-net CV, wild cluster bootstrap-t, grouped conformal, trajectory PCA + k-means + ARI, source/year perturbation & Shapley).
- ▌
- ▌
- ▌
- ▌
- ▌ Fewshot Attempt 01 29 · prism-shadowMedBridge Sales Ops — Quote, Reconciliation & Account Decision Packages
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Fewshot Attempt 03 30 · prism-shadowProcureOps Task Group Skill — Sourcing, Receiving, AP, and Change Control
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Fewshot Attempt 01 39 · prism-shadowPeople Lifecycle HRMS — Employee Lifecycle & Policy Operations SOP
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Fewshot Attempt 03 41 · prism-shadowInvestigation Review Hub — Structured Legal-Review JSON Deliverable
- ▌ Fewshot Attempt 01 45 · prism-shadowCourt Clerk Post-Hearing Reconciliation and Financial Packet Skill
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌