call-log-composition
Use this skill when working with call log composition, formatting call details, handling AI notes, transcripts, and understanding the call log flow in App Connect.
67
52%
Does it follow best practices?
Impact
92%
1.87xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent-skills/call-log-composition/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a specific domain (call logs in App Connect) but fails to articulate concrete actions the skill performs, relying on vague verbs like 'working with', 'handling', and 'understanding'. The 'Use when' clause is present but largely restates the domain rather than providing distinct trigger scenarios. It also uses second-person voice ('Use this skill') rather than third-person declarative statements.
Suggestions
Replace vague verbs with specific concrete actions, e.g., 'Formats call log entries with duration, caller ID, and timestamps; parses AI-generated notes and transcripts; structures call detail records for App Connect.'
Strengthen the 'Use when' clause with distinct trigger scenarios, e.g., 'Use when the user asks to create, format, or review call logs, parse call transcripts, or integrate call records into App Connect.'
Add natural keyword variations users might say, such as 'call history', 'call records', 'call summary', 'phone log', or 'call details'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'working with call log composition' and 'handling AI notes' without listing concrete actions. There are no specific verbs describing what the skill actually does (e.g., 'formats call duration fields', 'parses transcript JSON'). | 1 / 3 |
Completeness | It has a 'Use when...' clause which addresses the 'when', but the 'what' is weak and vague—it doesn't clearly describe what concrete actions the skill performs. The 'when' clause essentially restates the domain rather than providing distinct trigger scenarios. | 2 / 3 |
Trigger Term Quality | Includes some relevant domain keywords like 'call log', 'transcripts', 'AI notes', and 'App Connect' that users might mention. However, it lacks common variations and more specific terms users would naturally say (e.g., 'call history', 'call records', 'call summary'). | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'App Connect' and 'call log' provides some domain specificity, but terms like 'formatting', 'handling', and 'understanding the flow' are generic enough to overlap with other documentation or data-handling skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides strong actionable guidance with concrete, executable code examples covering the full call log lifecycle. Its main weaknesses are verbosity in the output format section (showing all three formats in full) and the lack of error handling/validation checkpoints in the workflow. The content would benefit from better progressive disclosure by splitting detailed format examples and connector implementation into separate reference files.
Suggestions
Condense the Output Formats section by showing one format in full and briefly noting the key differences for the other two, or move the full examples to a separate FORMATS.md reference file.
Add error handling guidance and validation checkpoints to the Call Log Flow section—e.g., what to do if composeCallLog returns unexpected output or if the CRM API call fails.
Split the connector implementation and log parsing sections into a separate reference file (e.g., CONNECTOR_GUIDE.md) to improve progressive disclosure and reduce the main skill's length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with concrete code examples, but includes some redundancy—showing all three output formats in full when one example plus a brief note about differences would suffice. The output format examples are quite verbose and could be condensed. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples throughout: composeCallLog usage, upsert functions, connector implementation, parsing existing logs, and user settings checks. All examples include realistic parameters and return values. | 3 / 3 |
Workflow Clarity | The 'Call Log Flow' section provides a clear 5-step sequence, but it lacks validation checkpoints or error handling guidance. For a multi-step process involving external API calls and data transformation, there are no feedback loops for failure cases (e.g., what if the CRM API call fails, or if log composition produces invalid output). | 2 / 3 |
Progressive Disclosure | The content is reasonably well-structured with clear section headers, but it's a monolithic document with no references to external files. The full output format examples and connector implementation details could be split into separate reference files, especially given the document's length. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ringcentral/rc-unified-crm-extension
- Commit
f59d4a2
- 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.