Agent skill

Prescription Refusal To Fill

by mohitagw15856 in mohitagw15856/pm-claude-skills

Handle a prescription you are not going to dispense — the professional judgement recorded, the patient conversation, the prescriber contact, and the continuity of care that stops a refusal becoming…

MITAuto-check passed

Install Prescription Refusal To Fill

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill prescription-refusal-to-fill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills prescription-refusal-to-fill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/prescription-refusal-to-fill .claude/skills/prescription-refusal-to-fill && rm -rf skills-src

Use ~/.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/

Facts

Skill name
prescription-refusal-to-fill
GitHub stars
1.4k
Token cost
~1.6k tokens
SKILL.md length
855 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Handle a prescription you are not going to dispense — the professional judgement recorded, the patient conversation, the prescriber contact, and the continuity of care that stops a refusal becoming…

  • Works in 7 steps: Separate the concern from the… → Verify before you decline. A call to the… → Move the conversation somewhere private.… → …
  • Asked how to refuse to fill a prescription
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: Judgement, Privacy,… and Output Format, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Prescription Refusal To Fill is an agent skill from mohitagw15856/pm-claude-skills. Handle a prescription you are not going to dispense — the professional judgement recorded, the patient conversation, the prescriber contact, and the continuity of care that stops a refusal becoming abandonment. Use when asked how to refuse to fill a prescription, decline to dispense, handle a suspected forgery or early refill, or document a corresponding-responsibility decision. Produces the decision record, the conversation script, the prescriber contact, the continuity step, and the escalation path. Legal…

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

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 how to refuse to fill a prescription
  • Decline to dispense
  • Handle a suspected forgery
  • Document a corresponding-responsibility decision

Example prompts

  • “/prescription-refusal-to-fill”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Separate the concern from the conclusion. 'The quantity is inconsistent with the last dispensing' is a finding. 'This patient is…
  2. Verify before you decline. A call to the prescriber resolves a large share of these, and an unverified refusal is the one that becomes a…
  3. Move the conversation somewhere private. A refusal delivered within earshot of a queue is a dignity failure regardless of whether the…
  4. Decline in the first person, without accusation. 'I am not able to dispense this today' owns the decision. 'You are not allowed' assigns…
  5. Do not create a clinical cliff. Where abrupt discontinuation carries real risk, that risk is part of your decision and your referral, not…
  6. Give them somewhere to go. Prescriber, another pharmacy, urgent care — a refusal with no next step is abandonment.
  7. Escalate on the right axis. Safeguarding, regulatory reporting, and law enforcement are separate paths with separate thresholds; know…

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

Prescription Refusal To Fill loads about 1.6k tokens when it runs. Until then it costs about 147 tokens; SKILL.md has 855 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~147
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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). 855 words, ~1,638 tokens.

Download SKILL.mdSave it as .claude/skills/prescription-refusal-to-fill/SKILL.md (or your agent's skills folder).
name
prescription-refusal-to-fill
description
Handle a prescription you are not going to dispense — the professional judgement recorded, the patient conversation, the prescriber contact, and the continuity of care that stops a refusal becoming abandonment. Use when asked how to refuse to fill a prescription, decline to dispense, handle a suspected forgery or early refill, or document a corresponding-responsibility decision. Produces the decision record, the conversation script, the prescriber contact, the continuity step, and the escalation path. Legal obligations vary by jurisdiction; verify yours.

Declining to Dispense

Refusing to dispense is one of the few things a pharmacist does that is simultaneously a clinical act, a legal act, and a deeply personal moment for the patient standing at the counter. Done badly it is an accusation delivered in public. This separates the judgement from the delivery: what you decided and why, how you say it without humiliating anyone, and what you do next so the patient is not simply abandoned.

What This Skill Produces

  • The decision record — the basis for declining, stated as professional judgement rather than suspicion
  • The patient conversation — wording that declines without accusing, in a setting that preserves privacy
  • The prescriber contact — what to ask and what to record from the answer
  • The continuity-of-care step — what happens to the patient next, which is the part most often skipped
  • The escalation path — when this becomes a safeguarding, regulatory, or law-enforcement matter rather than a professional one
  • The internal record — what the team needs so the next shift is not blindsided

Required Inputs

Ask for these if not provided:

  • The prescription and the concern — what was presented and what specifically prompted the decision
  • What you checked — prescriber verification, dispensing history, monitoring programme if available, and what each showed
  • The patient interaction so far — what they said, and whether they have been told anything yet
  • The clinical picture — legitimate therapeutic need, whether abrupt discontinuation carries risk, and any known dependency
  • Your obligations — your jurisdiction's rules on refusal, referral, transfer, and reporting, which vary substantially

Framework: Judgement, Privacy, Continuity

  1. Separate the concern from the conclusion. 'The quantity is inconsistent with the last dispensing' is a finding. 'This patient is drug-seeking' is a conclusion you probably cannot support and should not record.
  2. Verify before you decline. A call to the prescriber resolves a large share of these, and an unverified refusal is the one that becomes a complaint.
  3. Move the conversation somewhere private. A refusal delivered within earshot of a queue is a dignity failure regardless of whether the decision was right.
  4. Decline in the first person, without accusation. 'I am not able to dispense this today' owns the decision. 'You are not allowed' assigns blame.
  5. Do not create a clinical cliff. Where abrupt discontinuation carries real risk, that risk is part of your decision and your referral, not an afterthought.
  6. Give them somewhere to go. Prescriber, another pharmacy, urgent care — a refusal with no next step is abandonment.
  7. Escalate on the right axis. Safeguarding, regulatory reporting, and law enforcement are separate paths with separate thresholds; know which one you are on.

Output Format

Show full SKILL.md (420 more words)Show less
Decision not to dispense: [date] · [pharmacist]

Presented: [medicine, quantity, prescriber, date on the prescription]

Concern: [the specific finding — stated as an observation, not a characterisation of the patient]

Checks performed: prescriber verification [outcome] · dispensing history [what it showed] · monitoring programme [checked Y/N, outcome] · prescription authenticity [what was examined]

Clinical considerations: [legitimate therapeutic need · risk of abrupt discontinuation · known dependency or pain condition]

Decision: not dispensed · Basis: [professional judgement, one sentence, defensible on the record]

Patient conversation: held [in private / at counter] · said: [wording used] · patient response: [recorded factually]

Continuity of care: [prescriber contacted / patient referred to X / prescription returned or retained per local rules / urgent care advised]

Escalation: ☐ None ☐ Safeguarding ☐ Regulator ☐ Law enforcement — [basis and to whom]

Team note: [what the next shift needs to know]

A professional-conduct and documentation framework only. The decision to dispense or decline, and every legal obligation attached to it — including whether a prescription may be retained, what must be reported, and to whom — are governed by your jurisdiction's law and your regulator's standards. Verify those before acting; they differ sharply between jurisdictions.

Quality Checks

  • The concern is recorded as an observation, not as a characterisation of the patient
  • Verification with the prescriber was attempted before declining, where possible
  • The conversation happened somewhere the patient could not be overheard
  • The wording owns the decision rather than accusing the patient
  • Risk from abrupt discontinuation was considered and is recorded
  • The patient was given a specific next step
  • Escalation, if any, went down the correct path with a stated basis

Anti-Patterns

  • Declining in front of a queue. Even a correct decision becomes a complaint and a humiliation.
  • Recording a suspicion as a fact. 'Appeared to be seeking' is unsupportable and will be read back to you.
  • Refusing without verifying. The prescriber call resolves many of these and protects the rest.
  • Ignoring discontinuation risk. Some refusals create a genuine clinical emergency; that has to be part of the decision.
  • No next step. A patient sent away with nothing is the version of this that causes harm.
  • Confusing the escalation paths. Reporting to the wrong body, or to none, both cause problems.
  • Not telling the team. The next shift dispenses it and the whole judgement is undone.

Example Trigger Phrases

  • "How do I refuse to fill this prescription properly?"
  • "I think this prescription is forged — what do I do?"
  • "Patient is asking for an early refill on a controlled drug"
  • "How do I document a decision not to dispense?"
  • "What do I say to the patient when I decline?"

© 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

Just SKILL.md in skills/prescription-refusal-to-fill of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Prescription Refusal To Fill 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.

Prescription Refusal To Fill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prescription Refusal To Fill this skillmohitagw15856/pm-claude-skills1.4k—~1.6kAutomated safety check: PassMIT
Error Handlingaffaan-m/ECC277k1 repos~2.7kAutomated safety check: PassMIT
Gosickn33/agentic-awesome-skills47k1 repos~1.5kAutomated safety check: PassMIT
Error Handlingthedaviddias/Front-End-Checklist74k—~416Automated safety check: PassMIT
Error Handlingaffaan-m/ECC276k—~2.4kAutomated safety check: PassMIT
Python Error Handlingwshobson/agents40k—~1.5kAutomated safety check: PassMIT

Similar skills

  • Error Handling

    affaan-m/ECC

    Patterns for robust error handling across TypeScript, Python, and Go.

    277k GitHub starsUsed in 1 repo~2.7k tokens
    DevelopmentAuto-check passed
  • Go

    sickn33/agentic-awesome-skills

    Language-specific super-code guidelines for go. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~1.5k tokens
    DevelopmentAuto-check passed
  • Error Handling

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing scripts, client components, bundles, or runtime behavior related to Implement proper error handling.

    74k GitHub stars~416 tokensUpdated 5 days ago
    DevelopmentAuto-check passed
  • Error Handling

    affaan-m/ECC

    TypeScript、Python、Goにわたる堅牢なエラー処理のパターン。型付きエラー、エラー境界、リトライ、サーキットブレーカー、ユーザー向けエラーメッセージをカバーします。

    276k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Python Error Handling

    wshobson/agents

    Python error handling patterns including input validation, exception hierarchies, and partial failure handling.

    40k GitHub stars~1.5k tokensUpdated 6 days ago
    DevelopmentAuto-check passed
  • Official

    Covers handling Go's context.Context idiomatically in fp-go code: reading and scoping context through operators, timeouts, cancellation and converting ctx-first functions.

    2k GitHub stars~4.2k tokensUpdated today
    DevelopmentAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car 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…

    1.4k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated 2 days ago
    Auto-check passed
  • 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.

    1.4k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated 2 days ago
    Auto-check passed
  • 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.

    1.4k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • 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.

    1.4k GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed

Questions about Prescription Refusal To Fill

What does Prescription Refusal To Fill do?

Handle a prescription you are not going to dispense — the professional judgement recorded, the patient conversation, the prescriber contact, and the continuity of care that stops a refusal becoming…. Prescription Refusal To Fill is an agent skill from mohitagw15856/pm-claude-skills. Handle a prescription you are not going to dispense — the professional judgement recorded, the patient conversation, the prescriber contact, and the continuity of care that stops a refusal becoming abandonment.

When should I use Prescription Refusal To Fill?

Prescription Refusal To Fill fits situations like: asked how to refuse to fill a prescription; decline to dispense; handle a suspected forgery; document a corresponding-responsibility decision.

How do I install Prescription Refusal To Fill in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill prescription-refusal-to-fill -a claude-code`. Or copy the skill folder (skills/prescription-refusal-to-fill in mohitagw15856/pm-claude-skills) into .claude/skills/prescription-refusal-to-fill in your project. Claude Code loads it when a task matches its description.

How do I install Prescription Refusal To Fill in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill prescription-refusal-to-fill -a codex`. Or copy the skill folder (skills/prescription-refusal-to-fill in mohitagw15856/pm-claude-skills) into .agents/skills/prescription-refusal-to-fill in your project. Codex loads it when a task matches its description.

Can I use Prescription Refusal To Fill 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 prescription-refusal-to-fill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prescription-refusal-to-fill, .gemini/skills/prescription-refusal-to-fill, .github/skills/prescription-refusal-to-fill and .opencode/skills/prescription-refusal-to-fill in your project.

What does Prescription Refusal To Fill need to run?

SKILL.md names no scripts, command-line tools or credentials: Prescription Refusal To Fill is instructions for the agent only.

Does Prescription Refusal To Fill 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 Prescription Refusal To Fill 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 Prescription Refusal To Fill use?

Prescription Refusal To Fill 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 Prescription Refusal To Fill use?

About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Prescription Refusal To Fill?

Skills that share tags, products or a category with Prescription Refusal To Fill: Error Handling (affaan-m/ECC, 277k stars), Go (sickn33/agentic-awesome-skills, 47k stars), Error Handling (thedaviddias/Front-End-Checklist, 74k stars) and Error Handling (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prescription Refusal To Fill?

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.