packmind-onboard
Complete automated onboarding: analyzes codebase, creates package, and generates standards & commands via CLI. Automatic package creation when none exist, user selection when packages are available.
61
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
17%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 explains the skill's functionality at a high level but fails to provide explicit trigger guidance for when Claude should select it. The language is technical and internal-facing rather than matching natural user requests. The lack of a 'Use when...' clause and absence of user-friendly trigger terms significantly limits its effectiveness for skill selection.
Suggestions
Add an explicit 'Use when...' clause with natural trigger terms like 'set up project', 'initialize codebase', 'get started with new repo', or 'configure development environment'
Replace jargon like 'CLI' and 'package creation' with user-facing language describing the outcomes (e.g., 'creates configuration files', 'sets up coding standards')
Clarify what 'standards & commands' means concretely - e.g., 'generates linting rules, git hooks, and common development scripts'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names domain (onboarding) and lists some actions (analyzes codebase, creates package, generates standards & commands), but the actions are somewhat abstract - 'standards & commands' lacks concrete detail about what these actually are. | 2 / 3 |
Completeness | Describes what it does but completely lacks a 'Use when...' clause or any explicit trigger guidance. The description only explains functionality without telling Claude when to select this skill. | 1 / 3 |
Trigger Term Quality | Uses technical jargon like 'CLI', 'package creation', and 'onboarding' that users are unlikely to naturally say. Missing common user phrases like 'set up project', 'get started', 'initialize', or 'new project setup'. | 1 / 3 |
Distinctiveness Conflict Risk | 'Onboarding' and 'codebase analysis' could overlap with other code analysis or project setup skills. The mention of 'package' and 'standards' provides some specificity but the scope remains somewhat ambiguous. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill for complex automated onboarding. Its strengths are clear workflow sequencing with validation checkpoints, concrete CLI commands, and comprehensive error handling. The main weakness is length—some content (JSON schemas, edge cases) could be extracted to reference files to improve token efficiency.
Suggestions
Extract JSON schemas for Standards and Commands to a reference file (e.g., references/cli-schemas.md) and link to it, reducing main skill length
Consolidate Steps 9, 9.1, and 9.2 which have overlapping content and confusing numbering (9.1/9.2 appear after Step 10)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundancy (Step 9 and 9.1/9.2 overlap, JSON schemas repeated in detail). Some sections could be tightened, though most content is necessary for the complex workflow. | 2 / 3 |
Actionability | Provides fully executable bash commands, complete JSON schemas for CLI input, exact print statements, and specific file paths. Every step has concrete, copy-paste ready instructions. | 3 / 3 |
Workflow Clarity | Excellent multi-step sequencing with explicit validation checkpoints (user confirmation before creation, progress tracking, error handling). Clear feedback loops for partial failures and graceful degradation paths. | 3 / 3 |
Progressive Disclosure | References external files appropriately (references/*.md for analysis details), but the main skill file is quite long (~400 lines). The JSON schemas and some edge cases could potentially be moved to reference files. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (628 lines); consider splitting into references/ and linking | Warning |
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
Total | 13 / 16 Passed | |
- 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.