Phone
BlockRunAI/ClawRouter
Verify phone numbers (carrier + SIM-swap fraud signals) and place AI-powered outbound voice calls via BlockRun's gateway (Twilio + Bland.ai).
HITL outbound collections phone call from overdue JSON (E.164, integer minor units, region); CALL-E create plus poll; structured promise out; dry-run default; never posts to unsupported regions…
MITAuto-check passed
Install Ledger Collections Call
$ npx skills add CALLE-AI/awesome-phone-call-agents --skill ledger-collections-call -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install CALLE-AI/awesome-phone-call-agents ledger-collections-call --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/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ledger-collections-call .claude/skills/ledger-collections-call && 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 "ledger-collections-call" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/ledger-collections-call into .claude/skills/ledger-collections-call/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ledger-collections-call", 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/CALLE-AI/awesome-phone-call-agents/tree/main/skills/ledger-collections-callType 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 CALLE-AI/awesome-phone-call-agents --skill ledger-collections-call -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install CALLE-AI/awesome-phone-call-agents ledger-collections-call --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ledger-collections-call .agents/skills/ledger-collections-call && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ledger-collections-call" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/ledger-collections-call into .agents/skills/ledger-collections-call/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ledger-collections-call", 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 CALLE-AI/awesome-phone-call-agents --skill ledger-collections-call -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install CALLE-AI/awesome-phone-call-agents ledger-collections-call --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ledger-collections-call .cursor/skills/ledger-collections-call && 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 "ledger-collections-call" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/ledger-collections-call into .cursor/skills/ledger-collections-call/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ledger-collections-call", 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/CALLE-AI/awesome-phone-call-agents.git --path skills/ledger-collections-call--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 CALLE-AI/awesome-phone-call-agents --skill ledger-collections-call -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install CALLE-AI/awesome-phone-call-agents ledger-collections-call --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ledger-collections-call .gemini/skills/ledger-collections-call && 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 "ledger-collections-call" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/ledger-collections-call into .gemini/skills/ledger-collections-call/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ledger-collections-call", 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 CALLE-AI/awesome-phone-call-agents ledger-collections-callInstalls 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 CALLE-AI/awesome-phone-call-agents --skill ledger-collections-call -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ledger-collections-call .github/skills/ledger-collections-call && 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 "ledger-collections-call" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/ledger-collections-call into .github/skills/ledger-collections-call/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ledger-collections-call", 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 CALLE-AI/awesome-phone-call-agents --skill ledger-collections-call -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install CALLE-AI/awesome-phone-call-agents ledger-collections-call --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ledger-collections-call .opencode/skills/ledger-collections-call && 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 "ledger-collections-call" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/ledger-collections-call into .opencode/skills/ledger-collections-call/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ledger-collections-call", 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
ledger-collections-call- GitHub stars
- 107
- Token cost
- ~1.5k tokens
- SKILL.md length
- 657 words
- Files
- 9 (incl. scripts, references, assets)
- Skills in repo
- 101
- Repo updated
- First seen
- Licence
- MIT
At a glance
HITL outbound collections phone call from overdue JSON (E.164, integer minor units, region); CALL-E create plus poll; structured promise out; dry-run default; never posts to unsupported regions…
- Works in 5 steps: Confirm the user authorized this one… → Confirm E.164 and that doNotCall is false. → Confirm amountMinor is a JSON integer… → …
- SKILL.md covers When To Use, When Not To Use, Required Inputs and Preflight, plus 6 more sections
- Runs Python scripts from its folder; calls python3
What it does
Ledger Collections Call is an agent skill from CALLE-AI/awesome-phone-call-agents. HITL outbound collections phone call from overdue JSON (E.164, integer minor units, region); CALL-E create plus poll; structured promise out; dry-run default; never posts to unsupported regions including YE.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts, reference files and assets (for example `assets/sample-overdue.json`, `references/examples.md` and `references/overlap.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
- “/ledger-collections-call”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Confirm the user authorized this one collections call.
- Confirm E.164 and that doNotCall is false.
- Confirm amountMinor is a JSON integer (no remainder).
- Confirm region is supported and is not YE. See references/regions.md.
- Run scripts/preview.py before any CALL-E plan.
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
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
Ledger Collections Call loads about 1.5k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 58 tokens; SKILL.md has 657 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); 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). 657 words, ~1,534 tokens.
Download SKILL.mdSave it as
.claude/skills/ledger-collections-call/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.- name
- ledger-collections-call
- description
- HITL outbound collections phone call from overdue JSON (E.164, integer minor units, region); CALL-E create plus poll; structured promise out; dry-run default; never posts to unsupported regions including YE.
- license
- MIT
Ledger Collections Call
Use this skill when a merchant (or an agent acting for one) has explicit authority to place one disclosed phone call about an overdue balance, and needs a structured promise back.
The directory name does not mean a money write. A CALL-E promised result is display-only. Payment stays a later human confirm (or another tool). Read references/overlap.md before treating this as a collections product: it is not kept.
This skill does not book a payment, post a ledger row, or run a campaign. A human reviews the result before any cash movement.
When To Use
- One overdue contact the operator already authorized, with E.164, integer
amountMinor, currency, locale, and region in JSON - Preview the CALL-E task and recipient result schema without credentials
- Refuse Yemen and other unsupported regions before
POST /v1/calls - Hand a structured promise to a human, a display-only card, or
keptcapture — not to a cashier
When Not To Use
- Consumer FDCPA / statutory debt-collection engines
- Collecting cards, CVV, bank passwords, or OTPs (PCI)
- Automatic retry when the outcome is
unknown, timeout, voicemail, orno_answer - Writing a ledger, invoice, or
keptfinancial record from the structured result - CSV campaigns, call budgets, bank-feed reconcile (that is
kept) - First-contact sales, scraped lists, or numbers the user did not authorize
- Hidden schedulers, webhooks, or
create_and_waiton the HTTP request - Inferring region from a leading
+1
Required Inputs
JSON object:
| Field | Type | Notes |
|---|---|---|
contactId | UUID string | Stable local id; used in the idempotency material |
displayName | string | Spoken name |
phoneE164 | string | E.164, authorized |
amountMinor | integer | Outstanding balance, smallest currency unit. No floats |
currency | string | ISO code, e.g. USD |
locale | en or ar | Task language. Documented in English; do not embed other scripts in this folder |
region | ISO 3166-1 alpha-2 | Stated by the operator. Not inferred from the number |
doNotCall | boolean | If true, refuse |
Optional: storeName (default Store), promisedDate (YYYY-MM-DD or empty; authorization material only).
Preflight
- Confirm the user authorized this one collections call.
- Confirm E.164 and that
doNotCallis false. - Confirm
amountMinoris a JSON integer (no remainder). - Confirm
regionis supported and is not YE. Seereferences/regions.md. - Run
scripts/preview.pybefore any CALL-E plan.
Dry-Run Preview
No CALL-E credentials. No network. scripts/preview.py never POSTs.
If the skill lives under docs/skills/ (originating product repo):
python3 docs/skills/ledger-collections-call/scripts/preview.py \
--request docs/skills/ledger-collections-call/assets/sample-overdue.jsonIf the skill lives under skills/ (this awesome-list layout):
python3 skills/ledger-collections-call/scripts/preview.py \
--request skills/ledger-collections-call/assets/sample-overdue.jsonPreview prints a masked phone, the CALL-E task, the result schema, and an idempotency key. It exits 0 with status: not_called. --live is rejected: live execute is not implemented in this skill.
Show full SKILL.md (239 more words)Show less
CALL-E Goal Template
Device-owned English (locale en). Shame language and fake legal threats are forbidden. Disclose that the caller is the store's assistant. Ask for a promise date and amount. Do not collect card numbers.
Call {displayName} on behalf of {storeName}. Identify yourself as the store's assistant, not a government collector. Their outstanding balance is {amountLine}. Ask whether they can promise a payment date and amount. Be brief, polite, and stop if they refuse. Return structured fields only: promised / refused / voicemail / no_answer / wrong_number / callback_requested, integer minor-unit amount if they state one, ISO date if they state one.amountLine is formatted from integer amountMinor plus currency (for example USD 15.00 for 1500 USD). Do not re-convert through floating point.
For locale ar, use the same constraints in Arabic at execute time. This folder stays English-only.
Structured Result
See references/result-schema.md. Required outcome enum: promised, refused, voicemail, no_answer, wrong_number, callback_requested. Optional integer promised_amount_minor, promised_currency, promised_date (YYYY-MM-DD).
A promised result is not a payment. voicemail, no_answer, and unknown all need a human. Do not redial unknown.
Live Planning
preview.py does not dial. Live requires a host that already has CALL-E authentication, a human confirm, and a second explicit gate (for example --live plus --confirm PLACE-REAL-CALLS on that host). This skill documents the gates; it does not implement POST /v1/calls.
If you use the CALL-E CLI after review:
calle call plan --to-phone <E164_PHONE> --goal "<reviewed goal text>" --timezone America/New_York --language English --region USDo not run calle call start unless the user separately confirms. Do not post unsupported regions including YE.
Cancellation And Idempotency
Idempotency key (hex SHA-256), not uuid4:
sha256("{contactId}|{amountMinor}|{currency}|{promisedDate}|{utcDate}")utcDate is YYYY-MM-DD in UTC for the authorization day. promisedDate may be empty.
If the user cancels before dial, do not execute. If a result is ambiguous, route to a human rather than calling again with a new key.
Safety Notes
Read references/safety.md, references/examples.md, references/regions.md, references/result-schema.md, and references/overlap.md before live planning.
© 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 8 other files (scripts, references, assets) in skills/ledger-collections-call of CALLE-AI/awesome-phone-call-agents.
- SKILL.md
- assets/sample-overdue.json
- references/examples.md
- references/overlap.md
- references/regions.md
- references/result-schema.md
- references/safety.md
- scripts/preview.py
- scripts/test_preview.py
Open the folder on GitHubat commit 38d4118
Compare with similar skills
Ledger Collections Call 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 |
|---|---|---|---|---|---|---|
| Ledger Collections Call this skillCALLE-AI/awesome-phone-call-agents | 107 | — | ~1.5k | Automated safety check: Pass | MIT | |
| PhoneBlockRunAI/ClawRouter | 6.6k | — | ~2.4k | Automated safety check: Pass | MIT | |
| Recursive Decision Ledgeraffaan-m/ECC | 277k | 1 repos | ~701 | Automated safety check: Pass | MIT | |
| Agent Collective Intelligence Coordinatorruvnet/ruflo | 74k | 2 repos | ~1k | Automated safety check: Pass | MIT | |
| Collection Digestoutline/outline | 41k | — | ~498 | Automated safety check: Pass | Custom licence | |
| Party Ledger Reconciliationsickn33/agentic-awesome-skills | 47k | 1 repos | ~5.2k | Automated safety check: Pass | MIT |
Similar skills
Recursive Decision Ledger
affaan-m/ECC
Run repeated rollouts ("Prime Gauss" style recursive prompting) while keeping an append-only decision ledger of trials, marks, coherence checks, and promotion gates, so recursive confidence never…
Agent Collective Intelligence Coordinator
ruvnet/ruflo
Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator
Collection Digest
outline/outline
Summarize what changed in an Outline collection since a date; use when the user asks what is new, what was updated, or wants a digest of recent documents.
Party Ledger Reconciliation
sickn33/agentic-awesome-skills
Party ledger reconciliation: party type, name and PAN/VAT, ledger against statement balance, difference and reason, duplicates, confirmation status and adjustment.
Ledger
alsk1992/CloddsBot
Trade decision audit trail and statistics. An agent skill from alsk1992/CloddsBot.
More from CALLE-AI/awesome-phone-call-agents
All 101 skills in this repoAccessible 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.
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…
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…
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…
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…
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…
Questions about Ledger Collections Call
What does Ledger Collections Call do?
HITL outbound collections phone call from overdue JSON (E.164, integer minor units, region); CALL-E create plus poll; structured promise out; dry-run default; never posts to unsupported regions…. Ledger Collections Call is an agent skill from CALLE-AI/awesome-phone-call-agents.164, integer minor units, region); CALL-E create plus poll; structured promise out; dry-run default; never posts to unsupported regions including YE.
How do I install Ledger Collections Call in Claude Code?
Run `npx skills add CALLE-AI/awesome-phone-call-agents --skill ledger-collections-call -a claude-code`. Or copy the skill folder (skills/ledger-collections-call in CALLE-AI/awesome-phone-call-agents) into .claude/skills/ledger-collections-call in your project. Claude Code loads it when a task matches its description.
How do I install Ledger Collections Call in Codex?
Run `npx skills add CALLE-AI/awesome-phone-call-agents --skill ledger-collections-call -a codex`. Or copy the skill folder (skills/ledger-collections-call in CALLE-AI/awesome-phone-call-agents) into .agents/skills/ledger-collections-call in your project. Codex loads it when a task matches its description.
Can I use Ledger Collections Call 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 ledger-collections-call -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ledger-collections-call, .gemini/skills/ledger-collections-call, .github/skills/ledger-collections-call and .opencode/skills/ledger-collections-call in your project.
What does Ledger Collections Call need to run?
Going by SKILL.md and its folder, Ledger Collections Call needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Ledger Collections Call 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 Ledger Collections Call 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 Ledger Collections Call use?
Ledger Collections Call 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 Ledger Collections Call use?
About 1.5k tokens (SKILL.md is roughly 6.1k 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 2.4k tokens, read only when the agent opens those files.
What are the alternatives to Ledger Collections Call?
Skills that share tags, products or a category with Ledger Collections Call: Phone (BlockRunAI/ClawRouter, 6.6k stars), Recursive Decision Ledger (affaan-m/ECC, 277k stars), Agent Collective Intelligence Coordinator (ruvnet/ruflo, 74k stars) and Collection Digest (outline/outline, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ledger Collections Call?
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.