CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

close-automation

Automate Close CRM tasks via Rube MCP (Composio): create leads, manage calls/SMS, handle tasks, and track notes. Always search tools first for current schemas.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/close-automation/SKILL.md

The canonical home for this skill is close-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

50%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body covers the six core Close workflows with concrete tool names and useful API-specific pitfalls, but it is held back by a missing lead-search tool for ID resolution, no validation checkpoints around the destructive delete workflow, filler and redundant sections, and a fully monolithic structure with no progressive disclosure to reference files. All four dimensions land at the midpoint.

Suggestions

Name the actual tool(s) for lead search and duplicate checking in the ID Resolution pattern and add them to the Quick Reference table, since every activity workflow depends on obtaining lead_id.

Add explicit validation before the destructive CLOSE_DELETE_CALL workflow (e.g., verify the call_id belongs to the intended lead and confirm with the user before deleting) and a backoff-and-retry loop for 429 rate-limit responses during bulk operations.

Move the per-tool parameter reference and Known Pitfalls into a references file (eliminating the duplication between per-workflow 'Pitfalls' and 'Known Pitfalls'), and delete the filler 'When to Use' section or replace it with genuine trigger guidance.

DimensionReasoningScore

Conciseness

The body is mostly factual Close-specific detail (params, ID formats, pitfalls), but it is padded: the 'When to Use' section is pure filler ('This skill is applicable to execute the workflow or actions described in the overview'), per-workflow pitfalls are repeated in 'Known Pitfalls' (custom-field ID references and ID formats each appear twice), and non-code prose sits in fenced code blocks. Not a 2 because the core content is accurate API knowledge rather than generic concept explanation; not a 4 because the filler section, redundancy, and fenced prose are more than minor trimmings.

3 / 5

Actionability

Tool names, key parameters, ID formats, and a quick-reference table are concrete, but key details are missing for the core loop: ID resolution says 'Search for leads using the Close search API' without naming a tool (and no search tool appears in the Quick Reference), and 'Duplicate lead detection is not automatic; check before creating' gives no method. Not a 4 because the missing lead-search step blocks every activity workflow that requires lead_id.

3 / 5

Workflow Clarity

Sequences are present and the setup section has verification checkpoints (confirm RUBE_SEARCH_TOOLS responds, confirm connection is ACTIVE before workflows), but the destructive operation (CLOSE_DELETE_CALL, 'Deletion is permanent and cannot be undone') has no validation or confirmation checkpoint, and bulk operations ('Implement delays between bulk operations') have no verify-then-retry loop. Per the judging guidelines, missing validation in destructive/batch workflows caps workflow clarity at 3.

3 / 5

Progressive Disclosure

Section structure is good (per-workflow headers, quick-reference table), but the ~215-line body is a single monolithic file with zero bundle files or external references, inlining per-tool parameter reference material and a duplicated pitfalls section that would fit better in a reference file. Not a 4 because the entire API reference is inline with no navigation to layered detail.

3 / 5

Total

12

/

20

Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A solid, concise description with concrete capability statements and strong distinctiveness, weakened by the absence of an explicit 'Use when...' trigger clause and somewhat sparse natural-synonym coverage. Adding trigger guidance would lift it into the top tier.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user wants to work with Close CRM — creating or updating leads, logging calls, sending SMS, or managing follow-up tasks and notes.'

Broaden natural trigger terms to include synonyms users actually say: 'log a call', 'send a text message', 'contacts', 'deals/opportunities', 'follow-ups'.

Clarify scope by naming what is out of scope (e.g., email and deal management) if those are intentionally unsupported, so users route to the right skill.

DimensionReasoningScore

Specificity

The description lists several concrete actions — 'create leads, manage calls/SMS, handle tasks, and track notes' — grounded in a named mechanism ('via Rube MCP (Composio)'). It falls short of the 5 anchor because coverage has gaps: no mention of contacts, deals/opportunities, email, or lead search/update, so it is not comprehensive.

4 / 5

Completeness

The 'what' is clear ('Automate Close CRM tasks via Rube MCP (Composio): create leads, manage calls/SMS, handle tasks, and track notes') but there is no 'Use when...' clause or equivalent explicit trigger guidance; 'Always search tools first for current schemas' is an operating instruction, not a trigger. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Natural user-facing terms like 'Close CRM', 'create leads', 'calls/SMS', 'tasks', and 'notes' are present and would be said by a user needing this skill. Not a 5 because common variations are missing (e.g., 'log a call', 'send a text', 'contacts', 'deals', 'follow-up').

4 / 5

Distinctiveness Conflict Risk

'Close CRM' combined with 'Rube MCP (Composio)' carves out a clear niche with distinct, product-specific triggers and minimal overlap risk with other CRM or messaging skills.

5 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/close-automation/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.