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

Exact Ref

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

After a CALL-E call that captured an exact identifier, classify it as spokenonly, conversationalconfirmed, mismatch, or independentlyverified before anything writes it.

MITAuto-check passed

Install Exact Ref

skills CLI
$ npx skills add CALLE-AI/awesome-phone-call-agents --skill exact-ref -a claude-code

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

GitHub CLI
$ gh skill install CALLE-AI/awesome-phone-call-agents exact-ref --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/exact-ref .claude/skills/exact-ref && 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
exact-ref
GitHub stars
107
Token cost
~1.4k tokens
SKILL.md length
598 words
Files
6 (incl. scripts, references)
Skills in repo
101
Repo updated
First seen
Licence
MIT

At a glance

After a CALL-E call that captured an exact identifier, classify it as spokenonly, conversationalconfirmed, mismatch, or independentlyverified before anything writes it.

  • Works in 5 steps: No extracted value → unknown. Do not… → Intended value present and not equal… → secondChannelMatch and extracted equals… → …
  • SKILL.md covers When to use, When not to use, Run it (no install, no… and Classify, plus 4 more sections
  • Runs JavaScript scripts from its folder; calls node and npm

What it does

Exact Ref is an agent skill from CALLE-AI/awesome-phone-call-agents. After a CALL-E call that captured an exact identifier, classify it as spokenonly, conversationalconfirmed, mismatch, or independentlyverified before anything writes it. Never write schema-valid plus readback-yes as a fact.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `references/call-fs01.json`, `references/examples.md` and `references/fixtures.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

  • “/exact-ref”

Requirements

  • Node.js

Workflow steps

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

  1. No extracted value → unknown. Do not invent one.
  2. Intended value present and not equal (ignoring spaces, hyphens, dots, case) → mismatch. Readback-plus-yes does not override. The decision…
  3. secondChannelMatch and extracted equals intended → independently_verified. Only this is writable.
  4. Readback confirmed, no second channel → conversational_confirmed. Not writable.
  5. Otherwise → spoken_only. Not writable.

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 1 file in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node
    • npm

    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):

    • github.com

    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

Exact Ref loads about 1.4k tokens when it runs, and up to ~3k if it reads all its reference files. Until then it costs about 59 tokens; SKILL.md has 598 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3k

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). 598 words, ~1,376 tokens.

Download SKILL.mdSave it as .claude/skills/exact-ref/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
exact-ref
description
After a CALL-E call that captured an exact identifier, classify it as spoken_only, conversational_confirmed, mismatch, or independently_verified before anything writes it. Never write schema-valid plus readback-yes as a fact.

ExactRef

Use this skill when a CALL-E structured result contains an identifier that will be written into a record: confirmation number, ticket, off-hire reference, order id, pickup number.

This skill does not place a call. It compiles a safe outbound task, then gates the returned identifier with a character-level check and a named provenance state. Fixture replay is the default. Live CALL-E create is host-owned and fail-closed.

Hosts: any Agent Skills-compatible environment (Claude Code, Codex, Cursor, OpenClaw, skills.sh installs). Provider: CALL-E Calls API, Python/TypeScript SDK, CLI, or MCP get_call_run output. Side effects: none. The script reads a JSON file and prints a decision.

When to use

  • The next write depends on an exact character string from a phone call
  • CALL-E returned structured_result and someone is about to treat it as true
  • You need a readback protocol in the outbound task without leaking the intended value
  • Top-level status is queued and you must not create a second call

When not to use

  • The value is already on a portal, email, or paper — that is no_call
  • Medical, legal, emergency, or payment-card capture
  • Guessing a phone number, country, language, or run_id
  • Calling track_ui_events or any undocumented MCP tool
  • Treating MCP COMPLETED or Calls task_completed as permission to write

Run it (no install, no credentials)

scripts/exactref.mjs is a single zero-dependency Node 18+ file. Exit 0 only when the decision is writable, 2 when classified but blocked, 1 on bad input.

bash
# The live 2026-09-05 miss: readback said yes, one letter is wrong → mismatch, exit 2
node scripts/exactref.mjs classify --intended 07198FECTIST --extracted 07198SECTIST --readback

# Gate a saved CALL-E call object (REST, SDK, `calle call status --json`, or MCP result{} envelope)
node scripts/exactref.mjs gate --call references/call-fs01.json --field identifier --intended 07198FECTIST

# Human typed the value from a written channel → independently_verified, exit 0
node scripts/exactref.mjs verify --intended 07198FECTIST --extracted 07198SECTIST --typed 07198FECTIST --second-channel

# Compile an outbound task; exit 2 if the intended value leaks into it
node scripts/exactref.mjs compile --field "off-hire reference" --destination "the supplier desk" --intended 07198FECTIST

# Self-check: re-classify every fixture, exit 1 if any disagrees with its expected provenance
node scripts/exactref.mjs fixtures

Fixtures are synthetic (see references/examples.md); the FS-01 identifier pair is the real one, nothing else from the call is included.

Classify

Rules, in order (see references/examples.md, fixtures in references/fixtures.json):

  1. No extracted value → unknown. Do not invent one.
  2. Intended value present and not equal (ignoring spaces, hyphens, dots, case) → mismatch. Readback-plus-yes does not override. The decision names the first differing character (firstMismatch).
  3. secondChannelMatch and extracted equals intended → independently_verified. Only this is writable.
  4. Readback confirmed, no second channel → conversational_confirmed. Not writable.
  5. Otherwise → spoken_only. Not writable.

To mark verified, a human must type the identifier and claim a second channel (email, portal, paper). Typing the extracted wrong value keeps mismatch.

Show full SKILL.md (250 more words)Show less

Gate a CALL-E call

gate reads the call object and refuses before it classifies:

  • Not terminal (queued, in_progress) → unknown, "do not write anything yet". queued plus attempt activity is not idle; do not create again.
  • Terminal without structured_result → unknown. Task completion is not extraction.
  • Terminal with structured_result → classify structured_result[field] against --intended.

It accepts snake_case (REST/Python) and camelCase (TypeScript) field names and unwraps the MCP result{} envelope.

Compile the task

The outbound task must:

  • Ask for the whole identifier, then wait for an end marker
  • Not interrupt during dictation
  • Do one full readback; if refused, ask for the whole string again
  • Ask for a word that starts with an ambiguous letter instead of guessing
  • Leave contradictory times unresolved
  • Never include the intended identifier (the compiler exits 2 if it does)

The compiled resultSchema asks CALL-E for identifier, readback_confirmed, one verbatim identifier_evidence span, and unresolved_time.

Wait honesty

  • Calls waitForResult returns on top-level completed / failed / canceled. It does not wait for structuredResult.
  • queued plus attempt activity is not idle. Do not create again.
  • A local timeout is not hangup or cancel.
  • Goal wait materializes when result or error is non-null.
  • MCP summaries live under result{}. Do not read them at the top level.

Host board (optional)

The ExactRef repository (https://github.com/Arshgill01/ExactRef) ships a local board that shows the character diff and the typed second-channel stamp: npm install && npm test && npm run dev → http://127.0.0.1:3450. Open OH-01, then FS-01. The write stays blocked until a human types 07198FECTIST and claims a second channel.

Safety notes: references/safety.md.

© 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 5 other files (scripts, references) in skills/exact-ref of CALLE-AI/awesome-phone-call-agents.

  • SKILL.md
  • references/call-fs01.json
  • references/examples.md
  • references/fixtures.json
  • references/safety.md
  • scripts/exactref.mjs

Open the folder on GitHubat commit 38d4118

Compare with similar skills

Exact Ref 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.

Exact Ref compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Exact Ref this skillCALLE-AI/awesome-phone-call-agents107—~1.4kAutomated safety check: PassMIT
Capturealirezarezvani/claude-skills28k1 repos~2.8kAutomated safety check: PassMIT
React18 String Refsgithub/awesome-copilot40k1 repos~527Automated safety check: PassMIT
Monitoring Capture ServicePostHog/posthog40k—~5kAutomated safety check: PassCustom licence
Canvas Capture Extensionremotion-dev/remotion63k—~907Automated safety check: PassCustom licence
Performing Network Packet Capture Analysismukul975/Anthropic-Cybersecurity-Skills34k—~2.3kAutomated safety check: PassApache-2.0

Similar skills

  • Capture

    alirezarezvani/claude-skills

    Captures and organizes chaotic brain dumps into a structured, actionable system with zero information loss.

    28k GitHub starsUsed in 1 repo~2.8k tokens
    Agent WorkflowsAuto-check passed

  • React18 String Refs

    github/awesome-copilot

    Official

    Provides exact migration patterns for React string refs (ref="name" + this.refs.name) to React.createRef() in class components.

    40k GitHub starsUsed in 1 repo~527 tokens
    Auto-check passed

  • Monitoring Capture Service

    PostHog/posthog

    Official

    Guide for using the Grafana MCP to monitor and diagnose the capture service (rust/capture) in production.

    40k GitHub stars~5k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

  • Canvas Capture Extension

    remotion-dev/remotion

    Official

    Rebuild, install, and reload the private Remotion Canvas Capture unpacked Chrome extension.

    63k GitHub stars~907 tokensUpdated yesterday
    Media & CreativeAuto-check passed

  • Performing Network Packet Capture Analysis

    mukul975/Anthropic-Cybersecurity-Skills

    Perform forensic analysis of network packet captures (PCAP/PCAPNG) using Wireshark, tshark, and tcpdump to reconstruct network communications, extract transferred files, identify malicious traffic…

    34k GitHub stars~2.3k tokensUpdated 1 mo ago
    SecurityAuto-check passed

  • Import Canvas Capture

    remotion-dev/remotion

    Official

    Import a recorded Remotion Canvas Capture into a project without Studio interactions using the internal experimental-codemod command.

    63k GitHub stars~882 tokensUpdated yesterday
    Media & CreativeAuto-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 Exact Ref

What does Exact Ref do?

After a CALL-E call that captured an exact identifier, classify it as spokenonly, conversationalconfirmed, mismatch, or independentlyverified before anything writes it. Exact Ref is an agent skill from CALLE-AI/awesome-phone-call-agents. After a CALL-E call that captured an exact identifier, classify it as spokenonly, conversationalconfirmed, mismatch, or independentlyverified before anything writes it.

How do I install Exact Ref in Claude Code?

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

How do I install Exact Ref in Codex?

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

Can I use Exact Ref 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 exact-ref -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/exact-ref, .gemini/skills/exact-ref, .github/skills/exact-ref and .opencode/skills/exact-ref in your project.

What does Exact Ref need to run?

Going by SKILL.md and its folder, Exact Ref needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node and npm). Our summary lists: Node.js.

Does Exact Ref access the network?

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

Is Exact Ref 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 Exact Ref use?

Exact Ref 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 Exact Ref use?

About 1.4k tokens (SKILL.md is roughly 5.5k 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 1.7k tokens, read only when the agent opens those files.

What are the alternatives to Exact Ref?

Skills that share tags, products or a category with Exact Ref: Capture (alirezarezvani/claude-skills, 28k stars), React18 String Refs (github/awesome-copilot, 40k stars), Monitoring Capture Service (PostHog/posthog, 40k stars) and Canvas Capture Extension (remotion-dev/remotion, 63k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Exact Ref?

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.