Generate structured planning docs for web projects with context-safe phases, verification criteria, and exit conditions. Creates IMPLEMENTATION_PHASES.md plus conditional docs. Use when: starting new projects, adding major features, or breaking large work into manageable phases.
Install with Tessl CLI
npx tessl i github:jezweb/claude-skills --skill project-planning66
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
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description has good structure with an explicit 'Use when' clause and mentions specific outputs, earning strong completeness marks. However, it uses somewhat technical jargon ('context-safe phases', 'exit conditions') that may not match natural user language, and the trigger scenarios are broad enough to potentially conflict with other project-related skills.
Suggestions
Add more natural trigger terms users would say, such as 'plan', 'roadmap', 'break down tasks', 'project phases', or 'implementation plan'
Replace technical terms like 'context-safe phases' and 'exit conditions' with user-friendly language describing the concrete benefits or outputs
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (web project planning) and some actions (generate planning docs, creates IMPLEMENTATION_PHASES.md), but 'context-safe phases', 'verification criteria', and 'exit conditions' are somewhat technical/abstract rather than concrete user-facing actions. | 2 / 3 |
Completeness | Clearly answers both what (generate structured planning docs with phases, verification criteria, exit conditions, creates specific files) and when (explicit 'Use when:' clause with three trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes some natural terms like 'new projects', 'major features', 'phases', but misses common variations users might say like 'plan', 'roadmap', 'breakdown', 'task list', 'milestones', or 'project structure'. | 2 / 3 |
Distinctiveness Conflict Risk | Specific to web project planning docs and mentions unique outputs (IMPLEMENTATION_PHASES.md), but 'starting new projects' and 'adding major features' could overlap with general project scaffolding or code generation skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive, actionable guidance for project planning with excellent workflow clarity and concrete templates. However, it severely violates token efficiency by embedding ~600+ lines of template boilerplate that should be in separate referenced files. The content is well-structured but the monolithic approach makes it impractical for context window management.
Suggestions
Extract all template structures (DATABASE_SCHEMA.md, API_ENDPOINTS.md, ARCHITECTURE.md, UI_COMPONENTS.md, CRITICAL_WORKFLOWS.md, INSTALLATION_COMMANDS.md, ENV_VARIABLES.md, SESSION.md templates) into separate referenced files like `templates/DATABASE_SCHEMA_TEMPLATE.md`
Reduce the main SKILL.md to ~150-200 lines covering: workflow overview, phase types summary, validation rules, and links to template files
Move the 'Default Stack Knowledge' section to a separate STACK_DEFAULTS.md file that can be referenced when needed
Consolidate the 'Phase Type' definitions into a compact table rather than verbose subsections with repeated structure
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~800+ lines with extensive template boilerplate that Claude doesn't need spelled out. Explains obvious concepts (what a PDF is equivalent: what phases are, what verification means) and includes full template structures that could be referenced externally. | 1 / 3 |
Actionability | Highly actionable with concrete templates, specific file structures, executable bash commands, and copy-paste ready examples. The phase templates, mermaid diagrams, and installation commands are all directly usable. | 3 / 3 |
Workflow Clarity | Excellent workflow structure with clear 6-step recommended workflow, explicit validation rules (≤8 files, ≤4 hours), verification requirements per phase type, and auto-split logic for oversized phases. Includes quality checklist and common mistakes section. | 3 / 3 |
Progressive Disclosure | Monolithic wall of text with all templates inline rather than referenced. The 8+ full template structures (DATABASE_SCHEMA.md, API_ENDPOINTS.md, ARCHITECTURE.md, UI_COMPONENTS.md, etc.) should be in separate referenced files, not embedded in the main skill. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1123 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 12 / 16 Passed | |
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.