Lead a team — run standups, coordinate tasks, and communicate.
50
38%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/persona-team-lead/SKILL.mdQuality
Discovery
25%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 is too vague and generic to effectively differentiate this skill from others. It lists broad management activities without concrete specifics about what Claude actually does, and completely lacks a 'Use when...' clause to guide skill selection. The trigger terms are partially relevant but miss many natural user phrasings.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about running standups, tracking team progress, assigning tasks, or managing sprint ceremonies.'
Replace vague terms like 'communicate' with specific actions such as 'draft standup agendas, summarize blockers, generate status reports, assign action items'.
Add distinctive keywords that narrow the niche, such as 'agile', 'sprint', 'daily standup', 'team coordination', 'project tracking' to reduce conflict with generic task or communication skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names some actions ('run standups, coordinate tasks, and communicate') but these are fairly generic management activities without concrete specifics about what the skill actually does (e.g., generate standup agendas, assign tasks, draft status updates). | 2 / 3 |
Completeness | Describes a vague 'what' (lead a team with standups, tasks, communication) but completely lacks a 'when' clause or explicit trigger guidance. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'standups', 'coordinate tasks', and 'team', but misses common variations users might say such as 'project management', 'sprint', 'daily meeting', 'task assignment', 'team lead', or 'status update'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Coordinate tasks' and 'communicate' are extremely generic phrases that could overlap with project management, communication, task tracking, or many other skills. 'Lead a team' is broad and not a clear niche. | 1 / 3 |
Total | 6 / 12 Passed |
Implementation
52%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is admirably concise and avoids unnecessary verbosity, but it reads more like a cheat sheet of commands than an actionable guide for leading a team. It lacks workflow sequencing (e.g., a typical day/week flow), concrete examples of inputs and outputs, and any validation or error-handling guidance. The referenced workflows do the heavy lifting, but without examples or sequencing, Claude would struggle to orchestrate them effectively.
Suggestions
Add a 'Typical Day/Week' workflow section that sequences the commands (e.g., morning: run standup → post to Chat → check calendar; weekly: run digest → review OKRs), with explicit checkpoints.
Include at least one concrete example showing a sample standup report output and how it gets posted to Chat, so Claude knows what to expect and can verify correctness.
Add brief error handling guidance — e.g., what to do if a workflow command fails or returns empty results, especially for standup-report and email-to-task.
Improve progressive disclosure by adding brief one-line descriptions next to each workflow reference explaining what it does and linking to its documentation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. No unnecessary explanations of what standups or OKRs are. Every line provides a concrete command or actionable tip. No padding or concept explanations. | 3 / 3 |
Actionability | The skill references specific workflow commands and flags, which is good, but all guidance is at the invocation level — there are no concrete examples of inputs/outputs, no sample standup report format, and no illustration of what these workflows actually produce or how to customize them. | 2 / 3 |
Workflow Clarity | There is no sequencing of steps, no validation checkpoints, and no feedback loops. The instructions are a flat list of independent actions with no guidance on order, frequency beyond 'daily'/'weekly', or what to do if a workflow fails. For a team lead persona coordinating multiple workflows, this lacks the multi-step process clarity needed. | 1 / 3 |
Progressive Disclosure | The skill references external workflows and utility skills, providing some structure. However, the references are not clearly signaled with links or descriptions of what each workflow contains, and there's no quick-start section or navigation guidance to help discover the right workflow for a given situation. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 10 / 11 Passed | |
a3768d0
Table of Contents
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.