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 Goal Drift Auditor

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

Offline heuristic CALL-E transcript skill that compares the original call goal against the agent's actual turns to measure on-topic ratio, detect off-topic spans, and determine whether the goal was…

MITAuto-check passed

Install Call Goal Drift Auditor

skills CLI
$ npx skills add CALLE-AI/awesome-phone-call-agents --skill call-goal-drift-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-goal-drift-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-goal-drift-auditor .claude/skills/call-goal-drift-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-goal-drift-auditor
GitHub stars
107
Token cost
~1.5k tokens
SKILL.md length
664 words
Files
8 (incl. scripts, references)
Skills in repo
101
Repo updated
First seen
Licence
MIT

At a glance

Offline heuristic CALL-E transcript skill that compares the original call goal against the agent's actual turns to measure on-topic ratio, detect off-topic spans, and determine whether the goal was…

  • SKILL.md covers When To Use, When Not To Use, Workflow and Research Background, plus 1 more section
  • Runs Python scripts from its folder; calls python3

What it does

Call Goal Drift Auditor is an agent skill from CALLE-AI/awesome-phone-call-agents. Offline heuristic CALL-E transcript skill that compares the original call goal against the agent's actual turns to measure on-topic ratio, detect off-topic spans, and determine whether the goal was achieved in the closing — then emits a tighter, bounded goal for the next plancall. It is not a compliance ruling, a semantic understanding system, or authorization to act automatically.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts and reference files (for example `references/example-transcript-drift.json`, `references/example-transcript-on-track.json` and `references/examples.md`).

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-goal-drift-auditor”

Requirements

  • Python 3

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):

    • arxiv.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 Goal Drift Auditor loads about 1.5k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 102 tokens; SKILL.md has 664 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~102
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.4k

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). 664 words, ~1,480 tokens.

Download SKILL.mdSave it as .claude/skills/call-goal-drift-auditor/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
call-goal-drift-auditor
description
Offline heuristic CALL-E transcript skill that compares the original call goal against the agent's actual turns to measure on-topic ratio, detect off-topic spans, and determine whether the goal was achieved in the closing — then emits a tighter, bounded goal for the next plan_call. It is not a compliance ruling, a semantic understanding system, or authorization to act automatically.
license
MIT

call-goal-drift-auditor

An agent told to confirm an appointment that ends up selling whitening packages has drifted. Nobody noticed. Until now.

Every CALL-E call starts with a goal. But calls are dynamic: a curious callee, an ambitious agent script, or a distraction tangent can pull the conversation far from the stated objective. Without post-call auditing, nobody knows the goal was never really achieved — or that three agent turns were spent on topics that were explicitly out of scope.

This skill reads the finished transcript alongside the original goal text, extracts content keywords, measures per-turn on-topic ratio, detects off-topic spans, and reports whether the goal appears achieved in the closing confirmation. It also generates a tighter, bounded goal with explicit scope-limiting instructions for the next call.

When To Use

  • after any CALL-E call where scope discipline matters
  • when a call goal is narrow and violations are measurable (appointment confirmation, payment verification, consent capture)
  • as part of a QA pipeline to detect systematic agent scope creep
  • before replaying a failed or incomplete call with tighter instructions

When Not To Use

  • without a goal file; drift is measured against the goal text and the CLI requires it
  • when the goal is intentionally broad ("assist the caller as needed")
  • as a legal or compliance ruling; it is heuristic and advisory only
  • for non-English transcripts; keyword extraction is English-only

Workflow

Audit a finished call
bash
python3 scripts/goal_drift_auditor.py analyze \
  --transcript path/to/call-result.json \
  --goal-file path/to/goal.txt

Reads the real get_call_run result shape or flat fixture shape. The goal file may be plain text or a JSON object with a goal, task, or objective key. Emits a drift card:

  • goal_keywords[]: content words extracted from the goal (sorted, 4+ char, non-stop-word)
  • agent_turn_count / on_topic_turn_count / on_topic_ratio
  • off_topic_spans[]: each span of ≥ 2 consecutive agent turns without goal keywords, with start_turn_index, length_in_agent_turns, and PII-masked first_off_topic_evidence
  • goal_achieved: true if goal keywords appear with a confirmation phrase in any of the last 4 agent turns
  • verdict: ON_TRACK / MILD_DRIFT / SIGNIFICANT_DRIFT / GOAL_NOT_ACHIEVED, plus unclear paths
  • recommended_action: no_action_required, monitor_and_consider_tighter_goal, or retry_with_tighter_goal with guidance
Craft a tighter, bounded goal
bash
python3 scripts/goal_drift_auditor.py craft \
  --scenario goal-refocus \
  --goal-file path/to/goal.txt

When --goal-file is provided, the original goal is embedded into a structured bounding template that instructs the agent to stay focused, redirect off-topic tangents, and confirm goal achievement explicitly before hanging up.

Show full SKILL.md (303 more words)Show less

Research Background

These references motivate dialogue review; they do not independently validate this skill's keyword/confirmation heuristic or prove that a call goal was met.

ResearchRelevance
Grosz, B.J. & Sidner, C.L. — Attention, Intentions, and the Structure of Discourse (Computational Linguistics, Vol. 12, No. 3, 1986, aclanthology.org/J86-3001)Foundational theory of intentional discourse structure: global discourse purpose vs. local focus; goal drift is when global purpose is displaced by local tangents. Cited 3000+ times
Grice, H.P. — Logic and Conversation (in Studies in the Way of Words, Harvard Univ. Press, 1989)Maxim of Relevance: every conversational contribution should relate to the joint purpose; the theoretical basis for measuring on-topic ratio
Burdisso et al. — Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction (EMNLP 2024, arXiv:2410.18481)Methodology for tracking dialogue trajectory in action-space; off-topic turns are trajectories departing the action-region of the stated goal
Acikgoz et al. — TD-EVAL: Revisiting Task-Oriented Dialogue Evaluation by Combining Turn-Level Precision with Dialogue-Level Comparisons (2025)Background on turn- and dialogue-level evaluation; this skill's keyword heuristic is not an implementation or validation of TD-EVAL
Choubey et al. — Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agents (Salesforce AI Research, ACL 2025, arXiv:2502.17321)Empirical validation that goal adherence is measurable from customer-agent transcripts on ABCD/SynthABCD datasets

This skill computes keyword overlap, on-topic ratio, and span detection using deterministic regex/set logic. It does not use model internals and labels every output analysis_mode: "heuristic".

Differences from sibling skills

  • call-agent-certainty-calibrator compares agent fact accuracy against goal facts; this skill compares agent topic focus against goal keywords.
  • call-script-compliance-auditor checks compliance with a rigid script; this skill works from a natural goal description without requiring a script.
  • call-cross-call-consistency-checker compares two calls horizontally; this skill audits one call vertically (goal vs. reality).
  • call-agent-commitment-tracker detects forward-looking pledges; this skill detects backward-looking topic adherence.

© 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 7 other files (scripts, references) in skills/call-goal-drift-auditor of CALLE-AI/awesome-phone-call-agents.

  • SKILL.md
  • references/example-goal.txt
  • references/example-transcript-drift.json
  • references/example-transcript-on-track.json
  • references/examples.md
  • references/safety.md
  • scripts/goal_drift_auditor.py
  • scripts/test_goal_drift_auditor.py

Open the folder on GitHubat commit 38d4118

Compare with similar skills

Call Goal Drift 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 Goal Drift Auditor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Call Goal Drift Auditor this skillCALLE-AI/awesome-phone-call-agents107—~1.5kAutomated safety check: PassMIT
Goalscodewhale-hq/Codewhale41k—~273Automated safety check: PassMIT
Baoyu Youtube TranscriptJimLiu/baoyu-skills27k1 repos~2.4kAutomated safety check: PassMIT
Youtube Transcriptbrowser-act/skills6.1k—~2.1kAutomated safety check: PassMIT
Youtube Transcriptsickn33/agentic-awesome-skills47k1 repos~1.3kAutomated safety check: PassMIT
Transcription0xsline/OpenChatCut2.2k1 repos~1.1kAutomated safety check: PassAGPL-3.0

Similar skills

  • Goals

    codewhale-hq/Codewhale

    Set, review, and update the user's goals. An agent skill from codewhale-hq/Codewhale.

    41k GitHub stars~273 tokensUpdated today
    Auto-check passed

  • Baoyu Youtube Transcript

    JimLiu/baoyu-skills

    Downloads YouTube video transcripts/subtitles and cover images by URL or video ID.

    27k GitHub starsUsed in 1 repo~2.4k tokens
    Media & CreativeAuto-check passed

  • Youtube Transcript

    browser-act/skills

    YouTube transcript extraction and content reformatting: given a YouTube video URL, opens the video's transcript panel, extracts all timestamped segments, and transforms the raw transcript into…

    6.1k GitHub stars~2.1k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed

  • Youtube Transcript

    sickn33/agentic-awesome-skills

    Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output.

    47k GitHub starsUsed in 1 repo~1.3k tokens
    Knowledge ManagementAuto-check passed

  • Transcription

    0xsline/OpenChatCut

    A skill your agent uses when a video/audio task needs OpenChatCut transcription, captions, subtitles, subtitle styling, transcript search, transcript readiness checks, or enabling captions…

    2.2k GitHub starsUsed in 1 repo~1.1k tokens
    Media & CreativeAuto-check passed

  • Youtube Transcript Skills

    sickn33/agentic-awesome-skills

    Fetch YouTube video transcripts, search videos/channels, browse channels, and extract playlists via the getyoutubetranscript.com API - free tier, no card required.

    47k GitHub starsUsed in 1 repo~1.2k tokens
    Knowledge ManagementAuto-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 Goal Drift Auditor

What does Call Goal Drift Auditor do?

Offline heuristic CALL-E transcript skill that compares the original call goal against the agent's actual turns to measure on-topic ratio, detect off-topic spans, and determine whether the goal was…. Call Goal Drift Auditor is an agent skill from CALLE-AI/awesome-phone-call-agents. Offline heuristic CALL-E transcript skill that compares the original call goal against the agent's actual turns to measure on-topic ratio, detect off-topic spans, and determine whether the goal was achieved in the closing — then emits a tighter, bounded goal for the next plancall.

How do I install Call Goal Drift Auditor in Claude Code?

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

How do I install Call Goal Drift Auditor in Codex?

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

Can I use Call Goal Drift 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-goal-drift-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-goal-drift-auditor, .gemini/skills/call-goal-drift-auditor, .github/skills/call-goal-drift-auditor and .opencode/skills/call-goal-drift-auditor in your project.

What does Call Goal Drift Auditor need to run?

Going by SKILL.md and its folder, Call Goal Drift 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 Goal Drift Auditor access the network?

SKILL.md names 1 domain. As links in the text: arxiv.org. This is read from the text; nothing was executed.

Is Call Goal Drift 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 Goal Drift Auditor use?

Call Goal Drift 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 Goal Drift Auditor use?

About 1.5k tokens (SKILL.md is roughly 5.9k 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 1.9k tokens, read only when the agent opens those files.

What are the alternatives to Call Goal Drift Auditor?

Skills that share tags, products or a category with Call Goal Drift Auditor: Goals (codewhale-hq/Codewhale, 41k stars), Baoyu Youtube Transcript (JimLiu/baoyu-skills, 27k stars), Youtube Transcript (browser-act/skills, 6.1k stars) and Youtube Transcript (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Call Goal Drift 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.