muhammadali-k
- 13 skills
- 0 followers
- 4 hours ago last updated
- ▌ Route · muhammadali-k bundleRun an explicit Codex boss → worker → independent reviewer build loop. Use only when the user invokes `$route`, types `/route`, says “route this,” or explicitly requests the routed multi-agent loop. The root Codex agent owns the plan, permissions, integration, and final verdict; one worker implements in the authorized workspace; a fresh reviewer inspects the result against the plan; the worker fixes validated findings until the root approves or reports a bounded non-convergence. Works for code, analysis, extraction pipelines, and generated files. Do not invoke implicitly for ordinary tasks.
- ▌ Council · muhammadali-k bundleConvene seven distinct perspectives—Adversary, Strategist, Scientist, Visionary, Engineer, Philosopher, and Humanist—to debate a consequential decision, idea, or plan, then synthesize a clear position, calibrated confidence, three critical risks, five next steps, and a minority report. Use for genuine tradeoffs such as career, research, product, architecture, business, or creative strategy; also trigger on “convene the council” or “stress-test this decision.” Do not use for simple facts, quick how-to questions, trivial choices, grief, crisis, or acute emotional distress.
- ▌ Academic PPTX · muhammadali-k bundleCreate restrained, publication-style PowerPoint decks for journal clubs, lectures, grand rounds, research talks, proposal defenses, and other clinical or scholarly presentations. Use for scientific or academic audiences that need message-based titles, evidence-first visuals, citations, speaker notes, and a rendered visual-QA pass. Compose with the installed Presentations skill.
- ▌ Abstract Review · muhammadali-k bundlePeer-review a research abstract or manuscript in a Word (.docx) file and return real tracked changes, threaded comments, and a concise reviewer summary. Use for a first review or a re-review against prior comment threads; load the relevant profile for evidence syntheses, trials, observational studies, other clinical designs, or AI/ML/LLM work. Trigger on requests to review, mark up, track changes, assess a revision, or check a .docx against a named venue or reporting standard. Use this when the deliverable is a marked-up .docx; use manuscript-srma for drafting SR/MA/NMA prose without Word review markup. Do not use for PDF-only markup because tracked changes and threaded Word comments require DOCX.
- ▌ Manuscript Srma · muhammadali-k bundleDraft, revise, structure, or evaluate systematic-review, pairwise meta-analysis, and network meta-analysis manuscripts. Use for evidence-synthesis sections, structured abstracts, methods and statistics, GRADE or summary-of-findings content, PRISMA or SWiM reporting checks, journal adaptation, and optional living or interactive review reports.
- ▌ Itable Extraction · muhammadali-k bundleExtract clinical-trial or systematic-review publication data into a structured i-table or evidence workbook. Use when the user provides an Excel/CSV template or column list plus study PDFs/supplements and asks to populate trial characteristics, arms, endpoints, baseline data, efficacy, safety, or provenance. The skill learns column structure and value conventions from the template and examples, matches sources to study rows, uses independent source-bounded extraction and verification, and creates a new filled workbook with provenance and QC. Prefer outcomes-extraction for dedicated OS/DFS/RFS per-comparison HR tables.
- ▌ Manuscript Writing · muhammadali-k bundleDraft, organize, or revise Muhammad Ali Khan's own research manuscripts and conference abstracts in his academic voice and house organization. Use for clinical/epidemiology cohorts, AI/informatics and LLM-methods papers, and systematic reviews, pairwise meta-analyses, or network meta-analyses when the user asks to draft, continue, restructure, tighten, or make prose read like their prior work. Apply the bundled voice, section, quantitative-reporting, abstract, and skeleton-first/tables-first references. For evidence-synthesis reporting mechanics, compose with manuscript-srma. Do not use to mark up someone else's DOCX with tracked changes and comments; use abstract-review for that deliverable.
- ▌ Codex Working Style · muhammadali-k bundleAdapt prompts, skills, agent workflows, and working practices to Codex. Use when the user asks how Codex works, how to get better results from it, how to choose among Codex app/CLI/IDE/cloud/browser surfaces, or how to port Claude Code instructions, skills, subagents, browser workflows, or model- specific prompts to Codex. Also use to make a long-running research or build workflow more reliable through planning, bounded autonomy, parallel read-heavy subagents, independent verification, and artifact QA. Do not use for OpenAI API implementation details; use the current official OpenAI docs workflow for model IDs, parameters, pricing, availability, and other changing product facts.
- ▌ Lisr PDF Downloader · muhammadali-k bundleRetrieve and organize legally accessible article PDFs and supplements for LISR study IDs, resolve identifiers, use open-access sources or the user's visible institutional-library workflow, and produce an auditable status workbook. Use for systematic-review full-text collection; compose with the Browser and Spreadsheets skills and never intercept credentials or bypass access controls.
- ▌ Outcomes Extraction · muhammadali-k bundleExtract time-to-event clinical-trial outcomes into per-comparison OS, DFS/PFS, and RFS evidence tables. Use when the user provides outcome workbooks plus publications and needs treatment-vs-control hazard ratios with 95% CIs, events and denominators per arm, landmark event-free rates, arm names, endpoint mapping, and provenance. Handles overall-population multi-arm comparisons, HR inversion, figure-only estimates, and original-vs-follow-up coding through independent source-bounded extraction and verification. Produces new filled workbooks, provenance, and strict QC. Use itable-extraction for wide baseline/characteristics tables. Response and pCR templates are out of scope.
- ▌ Guideline Lit Review · muhammadali-k bundleDraft and insert clinical-guideline literature-review narrative from populated Summary of Findings or GRADE tables in an existing DOCX. Use for clinical-question sections that need a trial-count opening, numbered comparison prose, subtitle formatting, and control-arm footnotes while preserving every existing table and document style. Compose with the installed Documents skill.
- ▌ Study Question Tagging · muhammadali-k bundleAssign included studies to guideline or systematic-review clinical questions and create one spreadsheet per question. Workbook export retains supported styles/dimensions/hidden/gridlines and may drop AutoFilter/freeze metadata. Use for PICO/CQ tagging, evidence-to-question mapping, per-question study lists, or splitting an included-studies workbook by question. Inputs may include a guideline/manuscript, an included-studies sheet, and source publications. The skill applies population and randomized-comparison gatekeepers, supports many-to-many assignment, flags ambiguous calls, and produces new output files plus QC evidence. Use this instead of extraction skills when the deliverable is study membership by question rather than cell-level trial data or effect estimates.
- ▌ Residency Program Finder · muhammadali-k bundleResearch, verify, compare, and rank U.S. residency programs for an applicant profile, including current-cycle eligibility, visa policy, signaling, interview metrics, international-medical-school representation, medical-school-country ties, fellowships, and reach/target/safety tiers. Use for application lists, signal allocation, or vetting programs; compose with current web search and the Browser skill for signed-in or JavaScript pages.