Medication Reconciliation
aipoch/medical-research-skills
Compare patient pre-admission medication lists with inpatient orders to automatically identify omitted or duplicated medications and improve medication safety.
Structure a pharmacist's medication therapy review so it finds the problems worth escalating and documents them in a form a prescriber will act on.
MITAuto-check passed
Install Medication Therapy Review
$ npx skills add mohitagw15856/pm-claude-skills --skill medication-therapy-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mohitagw15856/pm-claude-skills medication-therapy-review --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/medication-therapy-review .claude/skills/medication-therapy-review && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "medication-therapy-review" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/medication-therapy-review into .claude/skills/medication-therapy-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medication-therapy-review", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/medication-therapy-reviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mohitagw15856/pm-claude-skills --skill medication-therapy-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mohitagw15856/pm-claude-skills medication-therapy-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/medication-therapy-review .agents/skills/medication-therapy-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "medication-therapy-review" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/medication-therapy-review into .agents/skills/medication-therapy-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medication-therapy-review", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill medication-therapy-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mohitagw15856/pm-claude-skills medication-therapy-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/medication-therapy-review .cursor/skills/medication-therapy-review && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "medication-therapy-review" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/medication-therapy-review into .cursor/skills/medication-therapy-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medication-therapy-review", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mohitagw15856/pm-claude-skills.git --path skills/medication-therapy-review--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mohitagw15856/pm-claude-skills --skill medication-therapy-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mohitagw15856/pm-claude-skills medication-therapy-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/medication-therapy-review .gemini/skills/medication-therapy-review && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "medication-therapy-review" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/medication-therapy-review into .gemini/skills/medication-therapy-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medication-therapy-review", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mohitagw15856/pm-claude-skills medication-therapy-reviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mohitagw15856/pm-claude-skills --skill medication-therapy-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/medication-therapy-review .github/skills/medication-therapy-review && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "medication-therapy-review" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/medication-therapy-review into .github/skills/medication-therapy-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medication-therapy-review", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill medication-therapy-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mohitagw15856/pm-claude-skills medication-therapy-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/medication-therapy-review .opencode/skills/medication-therapy-review && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "medication-therapy-review" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/medication-therapy-review into .opencode/skills/medication-therapy-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medication-therapy-review", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
medication-therapy-review- GitHub stars
- 1.4k
- Token cost
- ~1.6k tokens
- SKILL.md length
- 780 words
- Files
- 2 (incl. references)
- Skills in repo
- 1,348
- Repo updated
- First seen
- Licence
- MIT
At a glance
Structure a pharmacist's medication therapy review so it finds the problems worth escalating and documents them in a form a prescriber will act on.
- Works in 6 steps: Reconcile before assessing. Compare the… → Ask what they have stopped. Patients… → Classify every problem into a type.… → …
- Asked to conduct a medication review
- SKILL.md covers What This Skill Produces, Required Inputs, Framework: Reconcile,… and Deeper Material, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Medication Therapy Review is an agent skill from mohitagw15856/pm-claude-skills. Structure a pharmacist's medication therapy review so it finds the problems worth escalating and documents them in a form a prescriber will act on. Use when asked to conduct a medication review, run an MTM or MUR, deprescribing review, or polypharmacy assessment, or to prepare a review for a patient on many medicines. Produces the medication list reconciled, the drug-therapy-problem list classified and prioritised, the patient-goal alignment, the prescriber recommendations with rationale, and the follow-up plan…
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/worked-example.md`).
The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.
When your agent uses it
- Asked to conduct a medication review
- Deprescribing review
- Polypharmacy assessment
- Prepare a review for a patient on many medicines
Example prompts
- “/medication-therapy-review”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Reconcile before assessing. Compare the record against what the patient describes taking. Every review that skips this assesses a fiction.
- Ask what they have stopped. Patients under-report discontinuation, and a stopped medicine explains more findings than any lab value.
- Classify every problem into a type. Indication without therapy · therapy without indication · ineffective drug · dose too low · adverse…
- Look hardest at the seams. Multiple prescribers, recent discharge, and specialist additions are where duplication, interaction, and…
- Prioritise by harm potential. The anticoagulant interaction outranks the vitamin nobody needs.
- Write each recommendation as one action. A prescriber acts on 'consider stopping X because Y'; they do not act on a paragraph of context.
What it can do on your machine
Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Medication Therapy Review loads about 1.6k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 172 tokens; SKILL.md has 780 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 780 words, ~1,622 tokens.
Download SKILL.mdSave it as
.claude/skills/medication-therapy-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- medication-therapy-review
- description
- Structure a pharmacist's medication therapy review so it finds the problems worth escalating and documents them in a form a prescriber will act on. Use when asked to conduct a medication review, run an MTM or MUR, deprescribing review, or polypharmacy assessment, or to prepare a review for a patient on many medicines. Produces the medication list reconciled, the drug-therapy-problem list classified and prioritised, the patient-goal alignment, the prescriber recommendations with rationale, and the follow-up plan. A documentation and reasoning framework for a licensed pharmacist; it makes no clinical determination and recommends no specific drug or dose.
Medication Therapy Review
A medication review that lists twelve drugs and concludes 'continue as prescribed' helped nobody. The value is in the problems found — the duplicate therapy, the drug with no active indication, the one the patient stopped taking three months ago and never mentioned — and in writing them up so a busy prescriber can act in under a minute. This structures the hunt and the write-up.
What This Skill Produces
- A reconciled medication list — prescribed, over-the-counter, herbal, and what the patient is actually taking, which is rarely the same list
- A classified drug-therapy-problem list — indication without therapy, therapy without indication, wrong drug, dose too high or low, adverse reaction, adherence
- Prioritisation — by potential for harm, not by ease of fixing
- Prescriber-facing recommendations — each with the finding, the rationale, and a specific proposed action
- Patient-goal alignment — what the patient actually wants from their medicines, which frequently differs from the guideline
- The follow-up plan — what to monitor, who does it, and when
Required Inputs
Ask for these if not provided:
- The medication list — prescribed, OTC, herbal and supplements, with doses and start dates
- What the patient actually takes — including doses skipped, halved, or stopped, and why
- The clinical context — active conditions, relevant lab values, renal and hepatic function, allergies, recent hospitalisations
- The patient's goals and constraints — cost, swallowing difficulty, dosing burden, side effects they will not tolerate
- Who prescribes what — multiple prescribers are where duplication and gaps hide
Framework: Reconcile, Classify, Prioritise by Harm
- Reconcile before assessing. Compare the record against what the patient describes taking. Every review that skips this assesses a fiction.
- Ask what they have stopped. Patients under-report discontinuation, and a stopped medicine explains more findings than any lab value.
- Classify every problem into a type. Indication without therapy · therapy without indication · ineffective drug · dose too low · adverse reaction · dose too high · adherence. Naming the category is what makes the list actionable.
- Look hardest at the seams. Multiple prescribers, recent discharge, and specialist additions are where duplication, interaction, and orphaned therapy accumulate.
- Prioritise by harm potential. The anticoagulant interaction outranks the vitamin nobody needs.
- Write each recommendation as one action. A prescriber acts on 'consider stopping X because Y'; they do not act on a paragraph of context.
Deeper Material
references/worked-example.md— eleven medicines, three prescribers, and a post-fall referral where four of six problems live in the gap between the record and what the patient actually takes. Read it when the shape of a good output is unclear, or to calibrate how specific the entries should be.
Output Format
Show full SKILL.md (353 more words)Show less
Medication review: [patient] · [date] · [pharmacist]
Reconciliation: [n] on record · [n] actually taking · discrepancies: [list, with what the patient reports]
Drug therapy problems
| # | Problem | Type | Medicines involved | Potential harm | Recommendation |
|---|---|---|---|---|---|
| 1 | [finding] | [category] | [drugs] | [high/med/low + why] | [one specific proposed action] |
Patient goals: [what they said they want — fewer tablets, no drowsiness, lower cost] · Conflicts with current regimen: [where]
Recommendations to prescriber — highest harm first
- [Finding]. Rationale: [why, referencing the specific clinical context]. Proposed: [the action].
Monitoring & follow-up: [what to check · who · when]
Discussed with patient: [what was explained, what they agreed to, what they declined]
A structured reasoning and documentation framework for a licensed pharmacist. It does not diagnose, does not determine appropriateness for an individual patient, and recommends no specific drug, dose, or change. All recommendations require the prescriber's clinical judgement, and interaction and dosing decisions must be checked against current, validated references and local scope-of-practice rules.
Quality Checks
- The list was reconciled against what the patient reports taking, not just the record
- Discontinued and self-adjusted medicines were actively asked about
- Every problem is classified into a named type
- Prioritisation is by potential harm, not by how easy the fix is
- Each recommendation states finding, rationale and one specific proposed action
- The patient's own goals are recorded and conflicts named
- Nothing asserts a clinical determination reserved to the prescriber
Anti-Patterns
- Reviewing the record instead of the patient. The gap between the two is the whole finding.
- Listing without classifying. An unclassified list is a summary, not a review.
- Leading with the easy wins. A prescriber who reads three trivial items first stops reading.
- Recommendations without rationale. 'Stop amlodipine' with no reason will be ignored, correctly.
- Ignoring what the patient wants. A regimen the patient will not take is not a better regimen.
- Asserting an interaction from memory. Check a current reference every time; this is exactly where confident errors do harm.
Example Trigger Phrases
- "Structure a medication review for a patient on eleven medicines"
- "Help me write up an MTM for the prescriber"
- "Run a polypharmacy assessment"
- "How do I document a deprescribing recommendation?"
- "Prepare a medication use review for this patient"
© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (references) in skills/medication-therapy-review of mohitagw15856/pm-claude-skills.
- SKILL.md
- references/worked-example.md
Open the folder on GitHubat commit 1cbf1f0
Compare with similar skills
Medication Therapy Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Medication Therapy Review this skillmohitagw15856/pm-claude-skills | 1.4k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Medication Reconciliationaipoch/medical-research-skills | 1.9k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Medical Specialty BriefsFreedomIntelligence/OpenClaw-Medical-Skills | 3.1k | — | ~798 | Automated safety check: Pass | None | |
| Medical Entity ExtractorFreedomIntelligence/OpenClaw-Medical-Skills | 3.1k | 1 repos | ~969 | Automated safety check: Pass | MIT | |
| Writing MedicalNorman-bury/research-writing-skill | 3.4k | — | ~614 | Automated safety check: Pass | MIT | |
| Medical Translationaipoch/medical-research-skills | 1.9k | — | ~2k | Automated safety check: Pass | MIT |
Similar skills
Medical Specialty Briefs
FreedomIntelligence/OpenClaw-Medical-Skills
Generate daily or on-demand medical research briefs for any medical specialty.
Medical Entity Extractor
FreedomIntelligence/OpenClaw-Medical-Skills
Extract medical entities (symptoms, medications, lab values, diagnoses) from patient messages.
Writing Medical
Norman-bury/research-writing-skill
A skill your agent uses when writing medical, biological, or clinical research papers - provides IMRaD structure and reporting guidelines
Medical Translation
aipoch/medical-research-skills
Use medical translation for academic writing workflows that need structured execution, explicit assumptions, and clear output boundaries.
Medical Case Interpreter
aipoch/medical-research-skills
Generates compliant medical case report articles for WeChat.
More from mohitagw15856/pm-claude-skills
All 1,348 skills in this repoCar Tco
mohitagw15856/pm-claude-skills
Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…
Cs Health Scorecard
mohitagw15856/pm-claude-skills
Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.
Exit Waterfall
mohitagw15856/pm-claude-skills
Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.
Feature Prioritisation
mohitagw15856/pm-claude-skills
Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.
Fire Number
mohitagw15856/pm-claude-skills
Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.
Freelance Rate
mohitagw15856/pm-claude-skills
Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.
Questions about Medication Therapy Review
What does Medication Therapy Review do?
Structure a pharmacist's medication therapy review so it finds the problems worth escalating and documents them in a form a prescriber will act on. Medication Therapy Review is an agent skill from mohitagw15856/pm-claude-skills. Structure a pharmacist's medication therapy review so it finds the problems worth escalating and documents them in a form a prescriber will act on.
When should I use Medication Therapy Review?
Medication Therapy Review fits situations like: asked to conduct a medication review; deprescribing review; polypharmacy assessment; prepare a review for a patient on many medicines.
How do I install Medication Therapy Review in Claude Code?
Run `npx skills add mohitagw15856/pm-claude-skills --skill medication-therapy-review -a claude-code`. Or copy the skill folder (skills/medication-therapy-review in mohitagw15856/pm-claude-skills) into .claude/skills/medication-therapy-review in your project. Claude Code loads it when a task matches its description.
How do I install Medication Therapy Review in Codex?
Run `npx skills add mohitagw15856/pm-claude-skills --skill medication-therapy-review -a codex`. Or copy the skill folder (skills/medication-therapy-review in mohitagw15856/pm-claude-skills) into .agents/skills/medication-therapy-review in your project. Codex loads it when a task matches its description.
Can I use Medication Therapy Review in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill medication-therapy-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/medication-therapy-review, .gemini/skills/medication-therapy-review, .github/skills/medication-therapy-review and .opencode/skills/medication-therapy-review in your project.
What does Medication Therapy Review need to run?
SKILL.md names no scripts, command-line tools or credentials: Medication Therapy Review is instructions for the agent only.
Does Medication Therapy Review access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Medication Therapy Review safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Medication Therapy Review use?
Medication Therapy Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Medication Therapy Review use?
About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.3k tokens, read only when the agent opens those files.
What are the alternatives to Medication Therapy Review?
Skills that share tags, products or a category with Medication Therapy Review: Medication Reconciliation (aipoch/medical-research-skills, 1.9k stars), Medical Specialty Briefs (FreedomIntelligence/OpenClaw-Medical-Skills, 3.1k stars), Medical Entity Extractor (FreedomIntelligence/OpenClaw-Medical-Skills, 3.1k stars) and Writing Medical (Norman-bury/research-writing-skill, 3.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Medication Therapy Review?
mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.
Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.