This skill should be used when the user says "save plan", "save the plan", "arness code save plan", "structure this plan", "create project from plan", "export plan", "export project plan", "organize this plan", "set up project structure", "turn this into a project", "generate project structure", "finalize the plan", or wants to convert a planning conversation into an actionable phased project structure with implementation and testing plans.
83
79%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/arn-code/skills/arn-code-save-plan/SKILL.mdQuality
Discovery
82%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 excels at providing explicit trigger phrases and clearly stating when the skill should be used, earning strong marks for completeness and trigger term quality. However, it is weaker on specificity—it describes the output at a high level ('actionable phased project structure') without detailing the concrete actions or artifacts produced. The distinctiveness is moderate, as some trigger phrases could overlap with project scaffolding or initialization skills.
Suggestions
Add more specific concrete actions describing what the skill produces, e.g., 'Creates phased markdown plans with task breakdowns, generates directory structures, and outputs implementation checklists.'
Differentiate from project scaffolding/initialization skills by clarifying that this skill specifically transforms conversational planning context into structured plans, not code templates or boilerplate.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions converting a planning conversation into 'an actionable phased project structure with implementation and testing plans,' which names the domain and a general action, but doesn't list multiple specific concrete actions (e.g., what files are created, what format is used, what the output looks like). | 2 / 3 |
Completeness | The description explicitly answers both 'what' (convert a planning conversation into an actionable phased project structure with implementation and testing plans) and 'when' (with a comprehensive list of trigger phrases and a general condition clause). The 'when' is very explicit. | 3 / 3 |
Trigger Term Quality | The description includes an extensive list of natural trigger phrases users would actually say, such as 'save plan', 'create project from plan', 'export plan', 'set up project structure', 'turn this into a project', and 'generate project structure'. These cover many natural variations. | 3 / 3 |
Distinctiveness Conflict Risk | While the trigger phrases are fairly specific to plan-saving/exporting, terms like 'set up project structure' and 'generate project structure' could overlap with scaffolding or project initialization skills. The niche of converting planning conversations is somewhat distinct but not fully delineated from general project creation skills. | 2 / 3 |
Total | 10 / 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 a complex multi-step workflow. Its greatest strength is the clear 6-step sequence with validation checkpoints, error handling, and concrete file/path specifications. The main weakness is its length — some sections are verbose or repeat information that could be consolidated or moved to reference files, particularly the phase identification logic and sketch artifact procedures.
Suggestions
Move the detailed sketch artifact finding procedure (currently inline in Step 3) to a reference file to reduce the main skill's length
Consolidate the phase identification guidance that appears in both Step 3 and Step 4 into a single location, referencing it from the other step
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~200+ lines) with some sections that could be tightened. The detailed tables and conditional logic are necessary for the complex workflow, but there's redundancy in explaining phase identification multiple times (Steps 3 and 4 both explain how to handle plans without explicit phases). Some sections like the sketch artifacts finding procedure are verbose. | 2 / 3 |
Actionability | The skill provides highly concrete, executable guidance: specific bash commands with variable substitution, exact file paths, precise JSON field names and values, clear directory structures, and detailed table mappings from source to output sections. The script invocation and file creation instructions are copy-paste ready. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with explicit validation checkpoints: Step 1 validates paths exist on disk, Step 2 checks script exit codes before proceeding, Step 6 provides a verification checklist. Error recovery is addressed (script failure handling, missing config handling, migration path for legacy configs). The feedback loop for template versioning references an external doc appropriately. | 3 / 3 |
Progressive Disclosure | The skill references external files appropriately (template-versioning.md, templates.md, scripts/save_plan.sh) but the main SKILL.md itself is quite long and monolithic. Some content like the detailed sketch artifact finding procedure or the full PROGRESS_TRACKER.json schema could be moved to reference files. However, without bundle files provided, the referenced paths appear well-structured and one-level deep. | 2 / 3 |
Total | 10 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
1fe948f
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.