Docs & Writing

kumaran-is Skill

Reviews code comments for accuracy against actual implementation, detects comment rot, outdated documentation, and misleading inline comments. Use after refactoring, before PRs, or when comments might be stale.

kumaran-is Bundle

Full-stack system architecture skill for designing C4 diagrams, API contracts, sequence diagrams, deployment topologies, and ADRs. Use when designing new systems, choosing tech stacks, defining service boundaries, or producing architecture documentation before implementation starts.

kumaran-is Bundle

This skill should be used when creating API documentation, generating SDKs, or ensuring API contract compliance. It generates and maintains OpenAPI 3.1 specifications.

cowork-os Skill

Generate JSDoc/docstrings for functions

cowork-os Skill

Generate a concise status report from recent activity, tasks, commits, and conversations. Used by digital twin personas to prepare standup updates and progress summaries.

vishuwa2004 Bundle

Cache and reuse animated children once they slide into scrollback so terminal resets never occur.

openlabor Skill

Track and report key performance indicators

openlabor Skill

Build multi-slide carousel posts

openlabor Skill

Write technical documentation

nvidia-omniverse Bundle

Take one Blender prop through a concise SimReady workflow: preserve the source, author and validate it with the official SimReady add-on, check the supported OVRTX conversion boundary, run a native OVPhysX drop/contact test when appropriate, and prepare a portable USD handoff. Use when an artist wants an end-to-end physics-ready prop workflow rather than an infrastructure or validation-report project.

nvidia-omniverse Bundle

Design, implement, and run golden-image renderer comparison harnesses for graphics and viewer projects. Use when Codex needs to capture renderer output, compare Vulkan/OpenGL/Metal or other backends against golden images, refresh baselines, choose image-difference thresholds, wire tests into CI/CTest, handle display/GPU constraints, inspect visual diffs, or report residual risk for renderer correctness.

malekokour Bundle

Structures one compound's DDI package from in-vitro results, clinical studies, models, labels and literature under ICH M12 logic. It builds a source-linked enzyme/transporter inventory, assigns perpetrator/victim roles, carries each signal to an auditable terminus, and drafts management wording for review. Use it to assemble, review or gap-check DDI evidence, inventory enzyme/transporter characterization, check whether a clinical interaction study is triggered, or draft report, summary or label language. Example: "Assemble and gap-check the DDI evidence package for this compound under ICH M12." Do not use for programme-level development-plan routing, biological relevance, assay adequacy, clinical significance, untested-pathway importance, dose selection or adjustment, or as a substitute for a curated interaction database.

malekokour Bundle

Reviews a bioanalytical plan before samples are collected - which analytes will be measured, in what matrix, over what calibration range, and whether that range covers the concentrations the study will actually produce. It derives required analytes from the objectives before reading the plan, compares the lower limit against predicted terminal concentrations rather than peak, checks long-term stability against the interval to the last analysis rather than the first, and flags points where the plan requires a judgment it does not constrain. Use it for a draft plan, a calibration range check, or a reanalysis plan. Example: "Please a draft plan, a calibration range check." Do not use for the bioanalytical report and its validation results, for sampling times, for multi-analyte conjugate strategy, or to accept the method.

malekokour Bundle

Reviews the pharmacokinetic content of a draft clinical study report against its own synopsis, tables, figures and permitted source outputs, with bounded CSR-local PD/biomarker context and topline snapshot routes, producing a source-linked discrepancy register and QC memo. Use when someone asks to check or reconcile one CSR against its own NCA, statistical, protocol, SAP, PD/biomarker, or locked topline sources. Route multi-document or programme-thread work to reconcile-cross-document-facts. Do not use for reviewing a protocol before a study runs, verifying derivations themselves, clinical interpretation, or deciding which conflicting value is scientifically correct.

malekokour Bundle

Reviews an in-vitro drug-interaction package for completeness, internal consistency and decision-readiness. It inventories which enzymes and transporters were assessed and which were not, classifies every reported inhibition and induction parameter against thresholds transcribed from the guidance in force, sums fraction metabolised with an explicit unassigned remainder, and lists every signal above threshold that has no terminus. Use it to gap-check reaction phenotyping, transporter assessment or an in-vitro report before it supports a development decision. Example: "Please gap-check reaction phenotyping, transporter assessment or an in-vitro report before it supports a development decision." Do not use for clinical interaction studies, for management strategy or label wording, or to judge whether an interaction is clinically significant.

malekokour Bundle

Reviews the clinical pharmacology content of a study protocol or amendment — dose rationale, PK/PD sampling, bioanalysis, subject restrictions, embedded PK analysis, and consent-document consistency for PK/genomic procedures — producing a source-located open comment list for qualified review. Use when asked to review or comment on CP/PK protocol sections before a study runs, or to reconcile protocol/sample/consent versions and procedure presence. Do not use to judge consent adequacy, vulnerability or capacity, QC a completed study report, verify NCA derivations, or select, adjust, justify, or endorse a dose.

malekokour Bundle

Maintains a register of clinical pharmacology values and claims across a programme's document thread — protocol, CSR, Module 2.7.2, briefing documents and label — and supports bounded privacy structure, ethics-submission, topline snapshot, and PD/biomarker context tracing. Use when a request spans documents or studies over time, asks where a changed value propagates, or traces declared PD/biomarker fields, synthetic privacy structures, ethics records, or topline facts across a programme. Example: "Where does this changed clearance value propagate across the CSR, Module 2.7.2 and the draft label?" Do not use for participant records, legal/privacy compliance, ethics approval or response adequacy, checking one report against its own outputs, verifying an analysis, drafting source documents, clinical meaning, causality, benefit-risk, disclosure wording, commitments, or deciding which conflicting value is correct.

malekokour Bundle

Reviews stated exposure safety margins — the ratio between a nonclinical no-observed-adverse-effect exposure and a clinical exposure — for whether each margin's basis is stated, its two sides are comparable, and its arithmetic reconciles. Use this skill when someone asks to review, QC, or trace a safety margin, a DILI or organ-toxicity exposure margin, or an exposure-based safety statement — for example "check the hepatic margin in the IB against the tox report" or "does every stated margin say which exposure metric and species it uses". Do not use to decide whether a margin is adequate, to set an exposure cap or stopping rule, to select a dose, to interpret a safety signal, or to review the toxicology study itself.

malekokour Bundle

Reviews CTD Module 2.7.6 individual study synopses for completeness against their parent study reports and consistency with Module 2.7.1-2.7.4 summaries. Checks that every study in the clinical development programme has a synopsis, that each synopsis carries the ICH E3-mandated elements, and that key parameter values agree with the full report. Use when asked to QC synopses before filing. Do not use for full CSR review, for Module 5 placement, or to decide which studies to include.

malekokour Bundle

Assesses the completeness and internal consistency of a programme's special-population evidence strategy — renal impairment, hepatic impairment, paediatrics, pregnancy and lactation, elderly, and other defined sub-populations — against the programme's declared scope, the target product profile, and the guidance-anchored criteria that create study or analysis obligations for each population. Use this skill when someone asks whether the special-population strategy covers what a reviewer will expect, which populations still need characterisation, or whether the strategy documents are internally consistent. Example: "Please the special-population strategy covers what a reviewer will expect, which populations still need characterisation." Do not use for reviewing one organ-impairment study report, for demographic covariate assessment in a PopPK, for pharmacogenomic characterisation, or for any request to decide whether a waiver rationale is sufficient or to commit to a study.

malekokour Bundle

Assesses whether age, sex and body-size covariate effects on exposure are characterised, internally consistent, and traceable to their sources — the PopPK covariate analysis, any dedicated sub-study, the factor-coverage matrix and the labelling concept — and flags effects that are stated without a source, sourced but unstated, or stated inconsistently across documents. Use this skill when someone asks whether demographic covariates are adequately characterised for a programme, whether the age, weight or sex effects in a PopPK report match what the label says, or what demographic gaps remain before filing. Example: "Are age, weight and sex effects characterised for this compound?" Do not use for pharmacogenomic covariates, for renal or hepatic impairment, for drug-drug interactions, for selecting or adjusting a dose, or for any request to decide whether a covariate effect is clinically meaningful.

malekokour Bundle

Compares declared reporting periods across Development Safety Update Reports (DSURs) and US IND annual reports, flagging calendar gaps, same-format overlaps, and potential cross-format duplicate coverage while preserving the source status of every period. Use this skill when a regulatory or safety reviewer asks which reporting dates are covered, whether successive periodic reports leave a gap, or where a DSUR and an IND annual report cover the same dates. Example: "Please a regulatory or safety reviewer asks which reporting dates are covered." Do not use it to decide whether a DSUR satisfies 21 CFR 312.33, whether an IND filing obligation is met, or whether a safety conclusion is adequate.

malekokour Bundle

Compare supplied CCDS, CCSI, RSI, periodic-report, and regional-label reference safety lists and versioned change records, preserving list divergence with both locators. Use when a clinical pharmacologist or safety/labeling reviewer needs a mechanical reconciliation of reference safety information. Example: "Reconcile the CCDS, RSI and regional-label safety lists and preserve every divergence with locators." Do not use to decide whether a discrepancy requires a local label or RSI change, author binding label language, determine filing obligations, or characterise a safety signal.

malekokour Bundle

Prepares the exposure contribution to a safety signal review - whether an event tracks exposure, and what the available data could have shown either way. It justifies the exposure metric against the event mechanism rather than defaulting, counts affected subjects lacking PK data and states the bias direction since those cases are usually the sickest, reports stratum event counts before any rate because a rising percentage across two three and four events is not a relationship, and reports the observed exposure range alongside any negative finding so no relationship observed is distinguished from could not have observed one. Use it for a signal review or periodic safety discussion. Example: "Please a signal review or periodic safety discussion." Do not use for escalation decision packs, for submission exposure-safety sections, for nonclinical margins, for committee documentation, or to judge causality or recommend a dose change.

aiunlocked1412 Bundle

ออกแบบ slide ระดับมืออาชีพ — pitch deck (Guy Kawasaki 10-slide), exec summary, visual hierarchy

zhou210712 Skill

生成或训练法条概念记忆卡片——莱特纳式记忆桶，按科目的 Markdown 存储， 带自我评估的训练模式。当用户说"训练记忆卡片""根据[材料]制作记忆卡片" "考我卡片"或想记忆法条时使用。

zhou210712 Skill

从已完成的委托登记起草律师函——通过保密/自认风险/和解谈判姿态检查清单门禁， 输出 .docx，附发送后检查清单，并提供创建案件的选项。当用户说 "起草律师函"、"写[类型]函"或已完成委托登记准备转为可发送草案时使用。

bdambrosio Bundle

Read a PDF already on this machine. Returns a section index first, then any named section in full — the same way fetch-text reads a paper from a URL, for the case where the file is a local path instead. Use it when the user says they have downloaded or saved a document.

bdambrosio Bundle

Say something in Factorio game chat — visible to everyone on the server. Use to report what you're doing, flag blockers, answer the human, or announce before acting near someone else's work.

bdambrosio Bundle

Count words in text. Use to determine length of a document, e.g. to determine if it needs to be summarized before further use

bdambrosio Bundle

Extract markdown document structure and content from mixed/embedded text (NOT for converting plain text TO markdown)

bdambrosio Bundle

Collect system and cognitive health metrics. Returns a structured health report with status classifications (ok/warning/critical) for hardware, OS, and cognitive subsystems.

bdambrosio Bundle

Read a text, JSON, or PDF file under scenarios/<world_name>/fs and return a Note.

bdambrosio Bundle

Visible non-air blocks within radius R (default/max 7). Filtered by forward cone (yaw ±60°, pitch -60..+90) and line-of-sight. Does NOT report items.

bdambrosio Bundle

Extract bibliography/references from PDF files using GROBID and return a Collection of Notes (one per reference).

bdambrosio Bundle

Attempt exactly ONE adjacent navigation move forward and report the outcome. Atomic navigation operation suitable for composition.