Agent skill · Audited from source
call-list
skill · anthropics/knowledge-work-pluginsApache-2.0 licenceAudited 13 Nov 2026 · source 524d72703284
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 524d72703284 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Builds today's call list. Runs lead-triage to rank the top-5 leads most worth calling, supplies talking points from email history, blocks time on the calendar, and drafts follow-up messages. Trigger on "call list," "who…
Cite
Cite this page
ModelsAtlas. “call-list (anthropics/knowledge-work-plugins)”. Retrieved 13 Nov 2026. https://modelsatlas.com/skills/anthropics/call-list
Trust audit
Audit 0.4.1 · source read 13 Nov 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (0)
No findings at any severity. We re-audit when the source changes.
Audit 0.4.1 · source sha 524d72703284 · 13 Nov 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisheranthropics GitHub organizationOwner of the repository this skill is read from
- Source folderanthropics/knowledge-work-plugins/small-business/skills/call-listThe exact folder we audited
- LicenceApache-2.0As the repository states it
- Commit pinned for this verdict524d72703284A new audit runs when the source changes
- Repository statusNot archivedPushed today
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Builds today's call list. Runs lead-triage to rank the top-5 leads most worth calling, supplies talking points from email history, blocks time on the calendar, and drafts follow-up messages. Trigger on "call list," "who…
---
name: call-list
description: Builds today's call list. Runs lead-triage to rank the top-5 leads most worth calling, supplies talking points from email history, blocks time on the calendar, and drafts follow-up messages. Trigger on "call list," "who am I calling today," "top five to call today," or "block time for calls." An owner who wants leads scored or ranked with no calendar blocks routes to lead-triage directly. Accepts optional count and date arguments.
allowed-tools: Read, WebFetch
---
Run the lead prioritization. Scan the pipeline, rank by urgency and opportunity, pull relevant email context, and get the owner ready to make calls.
Parse arguments:
- `--n` (default: `5`) — number of leads to surface (1–10)
- `--date` (default: today) — date to build the call list for (`YYYY-MM-DD`)
## Step 1 — Pipeline scan (lead-triage)
Run the `lead-triage` skill workflow for the pull and the scoring — it owns the HubSpot field list, the four-dimension model, the note-body urgency fetch, the flat-score guard, and the enrichment leg (with Apollo or Clay connected, company fit for leads that have no company on file — metered, so lead-triage asks once about the credit cost; pass that question through to the owner rather than answering it). Do not rebuild any of that here. Then pull email threads from Mail for each surviving lead (last 3 emails per contact) for the talking points.
## Step 2 — Rank and select top N
Take lead-triage's ranking and select the top `--n` — always exactly `--n` when that many leads exist, regardless of pipeline size. For ties, prefer leads with unanswered inbound signals. If lead-triage reports flat scores, present its CRM-fact ladder order instead and say so.
For each selected lead, produce a call card:
```
{Rank}. {Contact Name} — {Company}
Deal: {currency code} {amount} | Stage: {stage} | Last contact: {X days ago}
Signal: {most recent activity}
TALKING POINTS
• {point from email/deal context}
• {point from email/deal context}
• {open question to ask}
GOAL FOR THIS CALL: {one sentence — advance to next stage / re-engage / close}
```
## Step 3 — Calendar block
For each lead on the list, offer to block 20 minutes on the owner's calendar for the target date.
Show the proposed calendar entries:
```
{time slot} — Call: {Contact Name} ({Company})
```
Wait for owner to confirm which calls to block before creating calendar events.
## Step 4 — Draft follow-ups
For any lead that has an unanswered email older than 3 days, draft a brief follow-up:
```
Subject: Re: {thread subject}
Hi {first name},
{One sentence referencing prior conversation}. {One sentence with a clear next step or question}.
{Sign-off}
```
## Connector failures
If HubSpot is unreachable, stop and tell the owner — lead scoring requires CRM data. If Mail is unreachable, skip the email-context pull in Step 1 and the follow-up drafts in Step 4, and note "Mail not connected — email context and follow-up drafts skipped" in output; calendar blocking in Step 3 still runs. If Google Calendar is unreachable, skip calendar blocking and note it. If the lead-data connector is unreachable or the owner declines the enrichment spend, company fit stays flat for leads with no company on file — say so in the output rather than presenting the order as fit-ranked.
## Approval gates
- **Never send emails automatically.** Present drafts for owner approval only.
- **Never create calendar blocks without owner confirmation** — show the proposed list first.
- **Never update HubSpot deal stages automatically.**
## Output
Present the ranked call list with talk tracks. Then show proposed calendar blocks and ask for confirmation. Then show follow-up drafts and ask which to send.
Alongside the chat summary — never replacing it — render the list as a CALL SHEET artifact using the house style (`../../shared/artifact-style.md`): something the owner prints and works from while dialing. Print-friendly rows, one per lead, each with the call goal and two or three short talking points, plus a blank outcome line to scribble on. This is a work sheet, not a dashboard — no stat tiles, no charts.
## Closing offer
Close with one line on what got built, then the single most relevant next step with its trigger phrase — usually "write this outreach" (`outreach-composer`) for the leads that need email instead of a call. Up to two others: "fill my funnel" (`/grow-pipeline`) or "update the CRM" (`crm-autopilot`). Max three, and skip anything the owner declined earlier this session.
## Using a tool that isn't listed
The connectors named in this skill are the tested paths, not a wall. If the owner wants this flow to use a tool that isn't connected or listed, offer `build-connector` — it checks the connector directory first and connects through Zapier otherwise, never hand-building against a raw API. Once the connection exists, the tool joins this skill like any other optional connector, under the same approval gates.Excerpt, first 4,964 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 524d727
git clone https://github.com/anthropics/knowledge-work-plugins git -C knowledge-work-plugins checkout 524d72703284
The author documents no install command, so this uses the repository directly. Our verdict covers commit 524d72703284 only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
524d72703284
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/anthropics/call-list/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
mattpocock/skills
Implement a piece of work based on a spec or set of tickets.
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
mattpocock/skills
Pursue a long-running goal in a single session by co-ordinating subagents.
Add this badge to your README
[](https://modelsatlas.com/skills/anthropics/call-list/)
<a href="https://modelsatlas.com/skills/anthropics/call-list/"><img src="https://modelsatlas.com/skills/anthropics/call-list/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about call-list
What does the call-list skill do?
Is call-list safe to install?
What can call-list access on my machine?
How current is this page?
Sources
- github.com/anthropics/knowledge-work-plugins/tree/main/small-bus — the audited source at commit 524d72703284 and every finding aboveObserved · 13 Nov 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the call-list skill do?
- Is call-list safe to install?
- What can call-list access on my machine?