New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Call Motivational Interviewing Fidelity Auditor

by CALLE-AI in CALLE-AI/awesome-phone-call-agents

Offline experimental CALL-E helper that codes agent turns in health-behavior calls against MITI-4.2.1-inspired lexical categories (reflections, open questions, permission-gated advice…

MITAuto-check passed

Install Call Motivational Interviewing Fidelity Auditor

skills CLI
$ npx skills add CALLE-AI/awesome-phone-call-agents --skill call-motivational-interviewing-fidelity-auditor -a claude-code

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

GitHub CLI
$ gh skill install CALLE-AI/awesome-phone-call-agents call-motivational-interviewing-fidelity-auditor --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/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/call-motivational-interviewing-fidelity-auditor .claude/skills/call-motivational-interviewing-fidelity-auditor && 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
call-motivational-interviewing-fidelity-auditor
GitHub stars
107
Token cost
~2.1k tokens
SKILL.md length
1,014 words
Files
10 (incl. scripts, references)
Skills in repo
101
Repo updated
First seen
Licence
MIT

At a glance

Offline experimental CALL-E helper that codes agent turns in health-behavior calls against MITI-4.2.1-inspired lexical categories (reflections, open questions, permission-gated advice…

  • Works in 4 steps: Mask first. Any 7+-digit run (separators… → Classify each agent sentence. First… → Change-talk gate. Callee turns are… → …
  • SKILL.md covers When To Use, When Not To Use, Verdicts and How It Works, plus 5 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Call Motivational Interviewing Fidelity Auditor is an agent skill from CALLE-AI/awesome-phone-call-agents. Offline experimental CALL-E helper that codes agent turns in health-behavior calls against MITI-4.2.1-inspired lexical categories (reflections, open questions, permission-gated advice, confrontation) and grades MI adherence, abstaining honestly when no change talk is present; not certified MI coding, a clinical judgment, or authorization to act.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `references/example-call-result-nonadherent.json`, `references/example-call-result-not-mi.json` and `references/example-call-result-partial.json`).

The repository describes itself as: Portable phone-call Agent Skills, apps, examples, adapters, and scheduler recipes for AI agents. The licence is MIT.

Example prompts

  • “/call-motivational-interviewing-fidelity-auditor”

Requirements

  • Python 3

Workflow steps

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

  1. Mask first. Any 7+-digit run (separators included) is masked in
  2. Classify each agent sentence. First match wins, in precedence
  3. Change-talk gate. Callee turns are scanned for DARN-flavored
  4. Verdict + ratios. Priority NOT_MI_CALL > NON_ADHERENT >

What it can do on your machine

Read from SKILL.md and the folder at commit 38d4118. 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

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • motivationalinterviewing.org
    • aclanthology.org

    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

Call Motivational Interviewing Fidelity Auditor loads about 2.1k tokens when it runs, and up to ~5.5k if it reads all its reference files. Until then it costs about 99 tokens; SKILL.md has 1,014 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~99
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.5k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from CALLE-AI/awesome-phone-call-agents at commit 38d4118, republished under its MIT licence (© CALLE-AI). 1,014 words, ~2,081 tokens.

Download SKILL.mdSave it as .claude/skills/call-motivational-interviewing-fidelity-auditor/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
call-motivational-interviewing-fidelity-auditor
description
Offline experimental CALL-E helper that codes agent turns in health-behavior calls against MITI-4.2.1-inspired lexical categories (reflections, open questions, permission-gated advice, confrontation) and grades MI adherence, abstaining honestly when no change talk is present; not certified MI coding, a clinical judgment, or authorization to act.
license
MIT
research
arXiv:2403.15737

call-motivational-interviewing-fidelity-auditor

Behavior-change calls deserve the same fidelity scrutiny clinicians get. Counts first, verdict second, honesty always.

This repo is full of health-call applications - refill reminders, adherence callbacks, care check-ins - and every one of them assumes the agent coached the patient rather than lectured them. Nothing in the sibling skills codes WHETHER the agent actually practiced Motivational Interviewing: did it reflect, ask open questions, gate advice behind permission - or did it slip into "you should" and "if you keep skipping" confrontation? This skill is a heuristic lexical coder inspired by the MITI 4.2.1 instrument: it classifies every agent sentence, counts the behaviors, derives the classic ratios, and grades a coarse verdict - abstaining honestly with NOT_MI_CALL when the callee never voiced any change talk. The counts and ratios are the product; the verdict is a coarse summary, not a clinical judgment.

When To Use

  • after any behavior-change call - refill reminder, medication adherence, care check-in - before trusting that the agent coached rather than lectured
  • when iterating on goal templates to improve agent style: run the audit, read the weakest counters, adjust the template, re-run
  • as a gate between get_call_run and any automation that acts on how the call went

When Not To Use

  • as a clinical instrument or therapist QA; this is heuristic lexical coding of a phone agent, never a basis for evaluating human clinicians
  • on calls with no change talk: NOT_MI_CALL is the honest abstention, not an error - grading agent style on a call that was never an MI conversation would be noise
  • on non-English transcripts; all lexicons are English-only stems
  • as a lie detector or intent test; it counts sentence shapes, it does not read minds

Verdicts

VerdictMeaningSuggested routing
MI_ADHERENTzero non-adherent behaviors, at least one reflection, open questions >= closed questionsproceed, keep the card as evidence
PARTIALLY_ADHERENTcatch-all: zero reflections, closed-heavy questioning, or scattered unpermitted advice below the thresholdreview the weakest counters before trusting the style
NON_ADHERENTany confrontation or warning, OR >= 3 pieces of advice without permissiona human reviews the call; template rework before more calls
NOT_MI_CALLno callee change talk detectedabstain; do not grade style on a non-MI call

How It Works

Four deterministic stages, offline, no LLM:

  1. Mask first. Any 7+-digit run (separators included) is masked in every turn before any coding, keeping the last two characters. Phone digits never classify and never leak into the card.
  2. Classify each agent sentence. First match wins, in precedence order: reflection > affirmation > confront > warn (conditional "if you don't/keep..." or "without...you'll" shape plus a loss word in the same sentence) > advice (permission must start at or before the advice sentence within the same turn) > question (open by wh-initial or "tell me about"/"walk me through", closed by auxiliary-initial or declarative "?") > information statement.
  3. Change-talk gate. Callee turns are scanned for DARN-flavored lexical anchors ("I want to quit", "part of me", "I'd like to", ...). No change talk anywhere means the call is not an MI conversation and the verdict is NOT_MI_CALL regardless of agent style.
  4. Verdict + ratios. Priority NOT_MI_CALL > NON_ADHERENT > MI_ADHERENT > PARTIALLY_ADHERENT. The card also reports reflections_per_question, open_question_share, and a low_sample advisory when fewer than 6 agent turns were coded.

Craft: the MI goal template

bash
python3 scripts/motivational_interviewing_fidelity_auditor.py craft

Emits a refill-reminder goal that operationalizes OARS - open with an open question, reflect ("It sounds like..."), ask permission before any suggestion, roll with resistance, let the patient choose the next step - so the calls this skill later audits start adherent.

Show full SKILL.md (443 more words)Show less

Foundation

FunctionCitation
Method anchor (the coding instrument: behavior counts + global ratings)Moyers, T. B., Manuel, J. K., & Ernst, D. Motivational Interviewing Treatment Integrity Coding Manual (MITI 4.2.1). https://motivationalinterviewing.org/sites/default/files/miti4_2.pdf
Instrument validation evidenceMoyers, T. B., Rowell, L. N., Manuel, J. K., Ernst, D., & Houck, J. M. (2016). "The Motivational Interviewing Treatment Integrity Code (MITI 4): Rationale, Preliminary Reliability and Validity." Journal of Substance Abuse Treatment 65:36-42. DOI 10.1016/j.jsat.2016.01.001, PMID 26874558. CORRECTION vs common miscite: 5 authors, not 3
Foundational framework (4th ed)Miller, W. R., & Rollnick, S. (2023). Motivational Interviewing: Helping People Change and Grow (4th ed.). Guilford Press, 338 pp. ISBN 9781462552795 (hardcover) / 9781462552801 (e-book). CORRECTION: 4th-ed subtitle is "...Change and Grow" (3rd ed was "Helping People Change")
Efficacy + digital-delivery evidence (why fidelity is worth auditing at all; MI works incl. digital applications)Bahri, A. A. (2025). "Motivational Interviewing to Promote Healthy Lifestyle Behaviors: Evidence, Implementation, and Digital Applications." Journal of Multidisciplinary Healthcare 18:6629-6642. DOI 10.2147/JMDH.S557957. Honest label: narrative review (summarizes RCTs/meta-analyses), NOT itself a meta-analysis
Recency (MI dialogue systems with LLMs)Xie, Z., Majumder, B. P., Zhao, M., Maeda, Y., Yamada, K., Wakaki, H., & McAuley, J. (2024). "Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoning." Findings of ACL 2024. arXiv:2403.15737, https://aclanthology.org/2024.findings-acl.782. Author-list CORRECTIONS pinned from the anthology page: Mengjie Zhao (not Mengxue), Yoshinori Maeda, Keiichi Yamada, Hiromi Wakaki - search snippets had all four wrong

Boundaries

  • call-negotiation-coach owns pre-call strategy coaching for negotiations; this skill audits MI fidelity after behavior-change calls.
  • call-apology-effectiveness-auditor owns post-grievance repair quality; this skill owns behavior-change coaching style.
  • call-leading-question-guard owns coercive question form; this skill counts the broader MI behavior profile of which questions are one part.
  • bridgecalle-active-listener is the vertical senior check-in application; this skill is the horizontal fidelity auditor any health-call app can gate on.

Limitations

  • English lexicons only; no multilingual coverage
  • heuristic lexical coding inspired by MITI 4.2.1 - stems, not deep reflection coding: "It sounded like..." variants are covered, but paraphrase reflections without lexical stems are undercounted
  • permission is same-turn only: an earlier turn's permission does not carry into a later turn's advice
  • wh-initial questions grade open, including "How about...?" (really a closed offer); auxiliary-initial questions grade closed, including "Could you tell me about...?" (really an open invitation) - deterministic rules, documented, not special-cased
  • a string-form transcript becomes a single agent turn: callee change talk is never present and the verdict is NOT_MI_CALL - supply real turn lists
  • masked digits never classify; they are unreadable by design
  • low_sample advisory fires under 6 agent turns; counts over so few sentences are fragile evidence

Testing

bash
python3 scripts/test_motivational_interviewing_fidelity_auditor.py

Runs offline with plain python3 and pytest, both from the skill root; see references/examples.md for real CLI output on the bundled fixtures.

© CALLE-AI, 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 9 other files (scripts, references) in skills/call-motivational-interviewing-fidelity-auditor of CALLE-AI/awesome-phone-call-agents.

  • SKILL.md
  • references/example-call-result-nonadherent.json
  • references/example-call-result-not-mi.json
  • references/example-call-result-partial.json
  • references/example-call-result.json
  • references/example-goal.txt
  • references/examples.md
  • references/safety.md
  • scripts/motivational_interviewing_fidelity_auditor.py
  • scripts/test_motivational_interviewing_fidelity_auditor.py

Open the folder on GitHubat commit 38d4118

Compare with similar skills

Call Motivational Interviewing Fidelity Auditor 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.

Call Motivational Interviewing Fidelity Auditor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Call Motivational Interviewing Fidelity Auditor this skillCALLE-AI/awesome-phone-call-agents107—~2.1kAutomated safety check: PassMIT
Code Reviewflutter/flutter180k—~1.4kAutomated safety check: PassBSD-3-Clause
Interview Meaddyosmani/agent-skills105k6 repos~3.8kAutomated safety check: PassMIT
Simplify CodeNousResearch/hermes-agent252k—~3.7kAutomated safety check: PassMIT
Architectural Code ReviewDonchitos/Claude-Code-Game-Studios26k—~3.5kAutomated safety check: PassMIT
Coding Agentopenclaw/openclaw392k1 repos~2.7kAutomated safety check: PassMIT

Similar skills

  • Code Review

    flutter/flutter

    Performs a comprehensive, multi-step code review of pull requests or local code changes, using iterative refinement (generation, critique, synthesis) to ensure high-quality, actionable feedback.

    180k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed

  • Interview Me

    addyosmani/agent-skills

    Asks one question at a time, each with a best guess attached, until the agent is about 95 percent sure what you really want, before any plan, spec or code.

    105k GitHub starsUsed in 6 repos~3.8k tokens
    Agent WorkflowsAuto-check passed

  • Simplify Code

    NousResearch/hermes-agent

    Parallel 4-agent cleanup of recent code changes. An agent skill from NousResearch/hermes-agent.

    252k GitHub stars~3.7k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Architectural Code Review

    Donchitos/Claude-Code-Game-Studios

    Performs an architectural review of code against coding standards, SOLID, testability and performance, and reports no verdict when the inputs are missing.

    26k GitHub stars~3.5k tokensUpdated 3 days ago
    DevelopmentAuto-check passed

  • Coding Agent

    openclaw/openclaw

    Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.

    392k GitHub starsUsed in 1 repo~2.7k tokens
    DevelopmentAuto-check passed

  • Review Code

    penpot/penpot

    Code review flow — review a diff, PR, or code change, delegating the review to a subagent that follows the code-review-criteria skill.

    61k GitHub stars~1k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from CALLE-AI/awesome-phone-call-agents

All 101 skills in this repo

  • Accessible Outing Verifier

    CALLE-AI/awesome-phone-call-agents

    Demonstrates advisory accessibility-planning checks with offline fixtures and a proposed bounded CALL-E workflow; use for exploring unknown or qualified venue claims without making calls.

    107 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

  • Ground Truth Gate

    CALLE-AI/awesome-phone-call-agents

    A skill your agent uses when an agent holds some evidence for a physical-world claim but the evidence is broader, narrower, or older than the exact question asked, and it must first decide whether a…

    107 GitHub stars~3.3k tokensUpdated yesterday
    Auto-check passed

  • Is It Accessible

    CALLE-AI/awesome-phone-call-agents

    Call a venue and ask the accessibility questions that matter to one specific person — step-free entry, hearing loop, guide dogs, quiet hours, changing places — then return a per-need verdict backed…

    107 GitHub stars~4.3k tokensUpdated yesterday
    Auto-check passed

  • Landmark Navigation Assist

    CALLE-AI/awesome-phone-call-agents

    Turns a pre-written, building-level location config into a CALL-E outbound phone-call task that guides a delivery driver through the last few hundred metres to a specific building using landmarks…

    107 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed

  • Research Gap Call Verifier

    CALLE-AI/awesome-phone-call-agents

    Turn cited business research into a bounded, approval-gated phone-call plan that asks only unresolved factual questions, then reconcile CALL-E-compatible results without treating voicemail, refusal…

    107 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

  • Structured Outcome Followup Call

    CALLE-AI/awesome-phone-call-agents

    Place a goal-driven CALL-E call that collects specific structured answers, score those answers against a deterministic rubric you supply, and conditionally trigger a follow-up action — all runnable…

    107 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

Questions about Call Motivational Interviewing Fidelity Auditor

What does Call Motivational Interviewing Fidelity Auditor do?

Offline experimental CALL-E helper that codes agent turns in health-behavior calls against MITI-4.2.1-inspired lexical categories (reflections, open questions, permission-gated advice…. Call Motivational Interviewing Fidelity Auditor is an agent skill from CALLE-AI/awesome-phone-call-agents.1-inspired lexical categories (reflections, open questions, permission-gated advice, confrontation) and grades MI adherence, abstaining honestly when no change talk is present; not certified MI coding, a clinical judgment, or authorization to act.

How do I install Call Motivational Interviewing Fidelity Auditor in Claude Code?

Run `npx skills add CALLE-AI/awesome-phone-call-agents --skill call-motivational-interviewing-fidelity-auditor -a claude-code`. Or copy the skill folder (skills/call-motivational-interviewing-fidelity-auditor in CALLE-AI/awesome-phone-call-agents) into .claude/skills/call-motivational-interviewing-fidelity-auditor in your project. Claude Code loads it when a task matches its description.

How do I install Call Motivational Interviewing Fidelity Auditor in Codex?

Run `npx skills add CALLE-AI/awesome-phone-call-agents --skill call-motivational-interviewing-fidelity-auditor -a codex`. Or copy the skill folder (skills/call-motivational-interviewing-fidelity-auditor in CALLE-AI/awesome-phone-call-agents) into .agents/skills/call-motivational-interviewing-fidelity-auditor in your project. Codex loads it when a task matches its description.

Can I use Call Motivational Interviewing Fidelity Auditor 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 CALLE-AI/awesome-phone-call-agents --skill call-motivational-interviewing-fidelity-auditor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/call-motivational-interviewing-fidelity-auditor, .gemini/skills/call-motivational-interviewing-fidelity-auditor, .github/skills/call-motivational-interviewing-fidelity-auditor and .opencode/skills/call-motivational-interviewing-fidelity-auditor in your project.

What does Call Motivational Interviewing Fidelity Auditor need to run?

Going by SKILL.md and its folder, Call Motivational Interviewing Fidelity Auditor needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Call Motivational Interviewing Fidelity Auditor access the network?

SKILL.md names 2 domains. As links in the text: motivationalinterviewing.org and aclanthology.org. This is read from the text; nothing was executed.

Is Call Motivational Interviewing Fidelity Auditor 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Call Motivational Interviewing Fidelity Auditor use?

Call Motivational Interviewing Fidelity Auditor is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Call Motivational Interviewing Fidelity Auditor use?

About 2.1k tokens (SKILL.md is roughly 8.3k 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 3.4k tokens, read only when the agent opens those files.

What are the alternatives to Call Motivational Interviewing Fidelity Auditor?

Skills that share tags, products or a category with Call Motivational Interviewing Fidelity Auditor: Code Review (flutter/flutter, 180k stars), Interview Me (addyosmani/agent-skills, 105k stars), Simplify Code (NousResearch/hermes-agent, 252k stars) and Architectural Code Review (Donchitos/Claude-Code-Game-Studios, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Call Motivational Interviewing Fidelity Auditor?

CALLE-AI (a GitHub organization) maintains it in CALLE-AI/awesome-phone-call-agents, which has 107 GitHub stars. The repository holds 101 skills in this directory. The repository was last updated on October 10, 2026.

Source: CALLE-AI/awesome-phone-call-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.