Agent skill

Donation Specification Call

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

Collect only the missing attributes blocking a donation allocation through one previewed, authorised CALL-E phone call, returning schema-validated reported claims without treating the conversation…

MITAuto-check passed

Install Donation Specification Call

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

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

GitHub CLI
$ gh skill install CALLE-AI/awesome-phone-call-agents donation-specification-call --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/donation-specification-call .claude/skills/donation-specification-call && 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
donation-specification-call
GitHub stars
107
Token cost
~2k tokens
SKILL.md length
951 words
Files
7 (incl. scripts, references, assets)
Skills in repo
101
Repo updated
First seen
Licence
MIT

At a glance

Collect only the missing attributes blocking a donation allocation through one previewed, authorised CALL-E phone call, returning schema-validated reported claims without treating the conversation…

  • Works in 11 steps: Find the blocking gaps. Run… → Bind the questions. Every question must… → Verify authorisation. Confirm active… → …
  • SKILL.md covers When To Use, When Not To Use, Required Input and Core Workflow, plus 4 more sections
  • Runs Python scripts from its folder

What it does

Donation Specification Call is an agent skill from CALLE-AI/awesome-phone-call-agents. Collect only the missing attributes blocking a donation allocation through one previewed, authorised CALL-E phone call, returning schema-validated reported claims without treating the conversation as inspection or certification.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts, reference files and assets (for example `assets/example-donation.json`, `assets/example-result.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

  • “/donation-specification-call”

Requirements

  • Python 3

Workflow steps

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

  1. Find the blocking gaps. Run deterministic matching first. Select only unknown hard attributes that prevent a match.
  2. Bind the questions. Every question must map to one known subject_reference and one attribute allowed by that subject's category schema.
  3. Verify authorisation. Confirm active contact consent, recipient-organisation approval, purpose, question-set hash, and expiry.
  4. Reserve idempotency. Derive a stable key from batch_reference + contact_reference + authorisation_version + question_set_hash and persist…
  5. Preview. Show the masked destination, AI disclosure, purpose, exact questions, result schema, likely side effect, and the fact that no…
  6. Require confirmation. Stop unless the operator explicitly approves this exact preview.
  7. Place one call. Send the reviewed task and closed result schema to CALL-E. Store the provider call ID immediately.
  8. Reconcile. Poll or process the webhook for that existing call. A timeout means outcome_unknown; reuse the provider ID or idempotency key…
  9. Validate. Reject unknown subjects, unasked attributes, invalid types or units, impossible quantities, and values without a supporting…
  10. Store claims. Accepted answers become donor_reported or recipient_reported claims. Conflicting claims remain visible; history is never…
  11. Re-run matching. The host application decides whether the newly reported values remove the gap. Human approval still controls allocation…

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/ (Python), which the agent can run.

    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

Donation Specification Call loads about 2k tokens when it runs, and up to ~3.6k if it reads all its reference files. Until then it costs about 64 tokens; SKILL.md has 951 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.6k

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); 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). 951 words, ~1,975 tokens.

Download SKILL.mdSave it as .claude/skills/donation-specification-call/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
donation-specification-call
description
Collect only the missing attributes blocking a donation allocation through one previewed, authorised CALL-E phone call, returning schema-validated reported claims without treating the conversation as inspection or certification.
license
MIT

Donation Specification Call

This is the reusable phone workflow behind The Missing Call, a category-neutral donation matching and fulfilment engine.

Use it when donated goods cannot be matched safely because a required real-world attribute is unknown. Examples include the age range on school supplies, labelled clothing sizes, furniture dimensions, whether goods are packed, available quantities, or whether a required document exists.

The skill asks one authorised contact only the questions currently blocking the match. It returns evidence-linked reported claims for human review. It does not inspect an item, certify its safety, approve an allocation, promise collection, transfer ownership, or prove that a document is genuine.

The governing rule is:

A completed call is not a completed match, and a spoken answer is not an inspection.

When To Use

Use this skill when all of the following are true:

  • a donation offer, recipient request, warehouse record, or transport offer has an unknown hard attribute;
  • that unknown value prevents deterministic compatibility or bundle assembly;
  • the contact has consented to calls for this specific donation-specification purpose;
  • the recipient organisation has authorised the question set;
  • a human operator can preview the exact call before dispatch.

This workflow is category-neutral. It can ask about any attribute defined in the host application's category schema, including quantities, dimensions, sizes, age ranges, packing state, collection windows, accessory presence, or documentary evidence.

When Not To Use

Do not use it when:

  • the phone number is merely present in a CSV, email signature, comment, directory, or public website;
  • the contact or recipient organisation has not authorised the call;
  • the operator has not reviewed the exact questions;
  • the intended result requires physical inspection, legal judgement, safety certification, proof of ownership, medical advice, or regulatory approval;
  • a previous attempt has an unknown outcome and has not been reconciled;
  • the requested action is to book transport, transfer ownership, purchase goods, or promise an allocation;
  • the situation involves an injury, fire, gas leak, electrical danger, or another emergency.

Required Input

The host must provide:

  • batch_reference: opaque donation-offer or request reference;
  • contact_reference: authorised contact identifier;
  • contact_masked: masked display number;
  • contact_role: donor, recipient, warehouse, transport, or coordinator role;
  • organisation_name: organisation represented on the call;
  • authorised_purpose: exactly donation_specification;
  • authorisation_version and expiry;
  • recipient_organisation_authorised: boolean;
  • consent_to_call: boolean;
  • subjects: opaque item or batch references with allowed attributes;
  • questions: only the unresolved hard attributes, including why each answer matters;
  • a closed recipient_result_schema.

Never place personal names, street addresses, pupil details, beneficiary details, or unmasked phone numbers in the task when opaque references are sufficient.

Core Workflow

  1. Find the blocking gaps. Run deterministic matching first. Select only unknown hard attributes that prevent a match.
  2. Bind the questions. Every question must map to one known subject_reference and one attribute allowed by that subject's category schema.
  3. Verify authorisation. Confirm active contact consent, recipient-organisation approval, purpose, question-set hash, and expiry.
  4. Reserve idempotency. Derive a stable key from batch_reference + contact_reference + authorisation_version + question_set_hash and persist call intent before dispatch.
  5. Preview. Show the masked destination, AI disclosure, purpose, exact questions, result schema, likely side effect, and the fact that no call has yet been placed.
  6. Require confirmation. Stop unless the operator explicitly approves this exact preview.
  7. Place one call. Send the reviewed task and closed result schema to CALL-E. Store the provider call ID immediately.
  8. Reconcile. Poll or process the webhook for that existing call. A timeout means outcome_unknown; reuse the provider ID or idempotency key and never redial blindly.
  9. Validate. Reject unknown subjects, unasked attributes, invalid types or units, impossible quantities, and values without a supporting quotation.
  10. Store claims. Accepted answers become donor_reported or recipient_reported claims. Conflicting claims remain visible; history is never overwritten.
  11. Re-run matching. The host application decides whether the newly reported values remove the gap. Human approval still controls allocation and handoff.
text
gap -> authorised questions -> preview -> confirm -> one call -> reconcile
    -> validate evidence -> reported claims -> re-run match -> human decision
Show full SKILL.md (322 more words)Show less

CALL-E Task Contract

Use CALL-E's currently documented create-call fields:

  • task
  • recipients
  • recipient_result_schema
  • metadata
  • idempotency_key

The task must disclose that it is an automated call on behalf of the named organisation and state that the purpose is to complete missing donation information. Ask questions one at a time. Do not improvise unrelated questions. Stop immediately if consent is withdrawn.

The generic result contains:

  • reached_intended_contact: yes | no | unknown
  • contact_role_confirmed: yes | no | unknown
  • consent_continued: yes | no | unknown
  • subject_references: opaque subjects discussed
  • attribute_updates[]: subject, attribute, value, unit, and supporting quote
  • availability_windows[]
  • unanswered_questions[]
  • optional notes

Use assets/example-donation.json for the closed example contract. Run scripts/preview_specification_call.py to inspect the complete no-call plan. Pass --result assets/example-result.json to demonstrate conservative result reconciliation without telephony.

Result Handling

Keep these outcomes distinct:

  • no answer;
  • voicemail;
  • wrong person;
  • refusal;
  • partial answer;
  • complete answer;
  • conflicting answer;
  • provider failure;
  • outcome unknown.

Only apply an attribute when the intended role was reached, consent continued, the subject and attribute were pre-authorised, the value passes the category rule, and a supporting quote exists. Otherwise return an explicit rejection or unresolved field.

Do not convert confidence, tone, or fluency into a higher verification level. A certain-sounding speaker still produces a reported claim.

Safety And Side Effects

Read references/safety.md before any live call.

  • Preview and fixture replay place no calls.
  • Live execution creates at most one billable outbound call for one authorisation.
  • There is no recurring schedule.
  • Cancellation means stopping before operator confirmation; after dispatch, reconcile the existing call rather than creating another.
  • Phone numbers must be masked in logs and summaries.
  • Credentials remain server-side.

Output

Return:

  • whether a call was placed;
  • masked contact and batch reference;
  • call outcome;
  • accepted reported claims with supporting quotes;
  • rejected fields with reasons;
  • conflicts and unanswered questions;
  • verification level for every accepted claim;
  • idempotency key or stored provider reference;
  • the next human-owned action.

Never state that an item is safe, certified, inspected, wiped, licensed, owned, allocated, or scheduled merely because someone said so by phone.

© 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 6 other files (scripts, references, assets) in skills/donation-specification-call of CALLE-AI/awesome-phone-call-agents.

  • SKILL.md
  • assets/example-donation.json
  • assets/example-result.json
  • references/examples.md
  • references/safety.md
  • scripts/preview_specification_call.py
  • tests/test_preview_specification_call.py

Open the folder on GitHubat commit 38d4118

Compare with similar skills

Donation Specification 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.

Donation Specification Call compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Donation Specification Call this skillCALLE-AI/awesome-phone-call-agents107—~2kAutomated safety check: PassMIT
Block Kitopenclaw/openclaw392k—~624Automated safety check: PassMIT
Agent Specificationruvnet/ruflo74k2 repos~1.8kAutomated safety check: PassMIT
Agent Resource Allocatorruvnet/ruflo74k2 repos~4.9kAutomated safety check: PassMIT
Specificity Managementthedaviddias/Front-End-Checklist74k—~477Automated safety check: PassMIT
Render Blockingthedaviddias/Front-End-Checklist74k—~430Automated safety check: PassMIT

Similar skills

  • Block Kit

    openclaw/openclaw

    Use proactively for structured or interactive Slack replies, and when asked to author or validate native Slack Block Kit JSON.

    392k GitHub stars~624 tokensUpdated today
    Auto-check passed
  • Agent skill for specification - invoke with $agent-specification

    74k GitHub starsUsed in 2 repos~1.8k tokens
    Product & Project ManagementAuto-check passed
  • Agent skill for resource-allocator - invoke with $agent-resource-allocator

    74k GitHub starsUsed in 2 repos~4.9k tokens
    Auto-check passed
  • Specificity Management

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing stylesheets, component styles, and responsive behavior related to Keep CSS specificity low and flat.

    74k GitHub stars~477 tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed
  • Render Blocking

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing slow page loads, heavy assets, or rendering delays related to Eliminate render-blocking resources.

    74k GitHub stars~430 tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed
  • Fetchpriority Attribute

    thedaviddias/Front-End-Checklist

    A skill your agent uses when optimising Largest Contentful Paint (LCP), reducing render-blocking resource contention, or fine-tuning resource loading order in the critical rendering path.

    74k GitHub stars~535 tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-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 Donation Specification Call

What does Donation Specification Call do?

Collect only the missing attributes blocking a donation allocation through one previewed, authorised CALL-E phone call, returning schema-validated reported claims without treating the conversation…. Donation Specification Call is an agent skill from CALLE-AI/awesome-phone-call-agents. Collect only the missing attributes blocking a donation allocation through one previewed, authorised CALL-E phone call, returning schema-validated reported claims without treating the conversation as inspection or certification.

How do I install Donation Specification Call in Claude Code?

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

How do I install Donation Specification Call in Codex?

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

Can I use Donation Specification 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 donation-specification-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/donation-specification-call, .gemini/skills/donation-specification-call, .github/skills/donation-specification-call and .opencode/skills/donation-specification-call in your project.

What does Donation Specification Call need to run?

Going by SKILL.md and its folder, Donation Specification Call needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Donation Specification Call 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 Donation Specification 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 Donation Specification Call use?

Donation Specification 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 Donation Specification Call use?

About 2k tokens (SKILL.md is roughly 7.9k 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 1.6k tokens, read only when the agent opens those files.

What are the alternatives to Donation Specification Call?

Skills that share tags, products or a category with Donation Specification Call: Block Kit (openclaw/openclaw, 392k stars), Agent Specification (ruvnet/ruflo, 74k stars), Agent Resource Allocator (ruvnet/ruflo, 74k stars) and Specificity Management (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Donation Specification 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.