arn-planning
This skill should be used when the user says "planning", "arness planning", "plan a feature", "start planning", "I want to build", "new feature", "plan something", "what should I build", "pick an issue", "plan a bug fix", "I have an idea", "spec and plan", "plan from scratch", "plan this", "feature planning", "bug planning", "plan this issue", "arn-planning", or wants to go from an idea, issue, or bug report through to a complete implementation plan ready for execution. Handles severity-aware scope routing across three ceremony tiers (swift, standard, thorough), routing between feature specs, bug specs, and quick implementations, and produces a reviewed plan ready for execution. Chains to arn-implementing at completion.
71
64%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/arn-code/skills/arn-planning/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 extensive trigger terms and clearly answering both what and when, making it strong on completeness and trigger term quality. However, the actual capabilities are described in somewhat jargon-heavy terms ('severity-aware scope routing', 'ceremony tiers') rather than plain concrete actions, and some trigger terms are broad enough to potentially conflict with other skills. The description is also front-loaded with a very long list of trigger phrases which, while thorough, makes it harder to quickly parse the actual capabilities.
Suggestions
Replace jargon like 'severity-aware scope routing across three ceremony tiers (swift, standard, thorough)' with plainer descriptions of what the skill concretely produces, e.g., 'Creates feature specifications, bug fix plans, or quick implementation outlines based on task complexity'.
Consider narrowing overly broad trigger terms like 'I want to build' and 'new feature' to reduce conflict risk with implementation-focused skills, or add clarifying context about when this skill should be chosen over an implementation skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions some concrete actions like 'severity-aware scope routing', 'routing between feature specs, bug specs, and quick implementations', and 'produces a reviewed plan ready for execution', but these are somewhat jargon-heavy and not fully concrete in terms of what the skill actually does step-by-step. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (handles severity-aware scope routing, routes between feature/bug specs, produces reviewed implementation plans) and 'when' (extensive list of trigger phrases plus the general condition 'wants to go from an idea, issue, or bug report through to a complete implementation plan'). | 3 / 3 |
Trigger Term Quality | The description includes an extensive list of natural trigger phrases users would say, such as 'plan a feature', 'I want to build', 'new feature', 'I have an idea', 'plan a bug fix', 'pick an issue', etc. These cover a wide range of natural user language variations. | 3 / 3 |
Distinctiveness Conflict Risk | While the planning focus is clear, some trigger terms like 'I want to build', 'new feature', and 'I have an idea' are quite broad and could overlap with implementation or brainstorming skills. The mention of 'arn-planning' and specific ceremony tiers helps somewhat, but the generic planning terms create moderate conflict risk. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive orchestration skill with excellent workflow clarity and state management, but it suffers significantly from verbosity. The repeated preference lookup/save pattern appears three times with near-identical text, and the progress bar is shown ten times. The skill would benefit greatly from extracting the preference handling pattern into a shared reference and condensing the gate presentations, which would likely cut the content by 40% without losing any actionable information.
Suggestions
Extract the repeated preference check/save pattern (two-tier lookup, write-back, 'remember this?' follow-up) into a shared reference file like `references/preference-gate-pattern.md` and reference it from each gate instead of duplicating ~30 lines each time.
Add a concrete YAML example showing what `~/.arness/workflow-preferences.yaml` looks like after preferences are saved, so the write-back logic is unambiguous.
Consolidate the progress bar displays — define the format once at the top and just reference the current stage marker at each step, rather than repeating the full ASCII art.
Add a brief inline summary of the scope router criteria (the 6 criteria and their weights) rather than relying entirely on the external reference, so the scoring logic in Step 3C is self-contained enough to execute.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~400+ lines. While it's a complex orchestration skill, there is massive repetition — the preference check pattern (two-tier lookup, write-back logic, 'remember this?' follow-up) is duplicated nearly identically across G2, G3, and G4. This could be factored into a shared reference. The progress bar ASCII art is repeated 10 times. Many gate presentations include exhaustive option listings that could be condensed. | 1 / 3 |
Actionability | The skill provides very specific routing logic, decision tables, and clear skill invocations (e.g., 'Skill: arn-code:arn-code-pick-issue'). However, there is no executable code — no YAML examples for preference files, no concrete file path examples, no sample AskUserQuestion invocations. The scope router scoring is described but the actual criteria are in an external reference without any inline summary. | 2 / 3 |
Workflow Clarity | The workflow is exceptionally well-sequenced with numbered steps, clear gates (G1-G5), explicit decision tables for routing, state detection with artifact-based resume points, and progress indicators at each stage. Error handling is comprehensive with specific recovery paths. Validation checkpoints exist at each gate. | 3 / 3 |
Progressive Disclosure | The skill references external files appropriately (scope-router-criteria.md, ensure-config.md, preferences-schema.md) and delegates to sub-skills. However, the massive amount of inline content — particularly the repeated preference check/save patterns and the detailed gate presentations — should be factored into references. The skill states it 'MUST NOT duplicate sub-skill logic' but then includes extensive inline detail about how each gate works. No bundle files were provided to verify reference accuracy. | 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- AppsVortex/arness
- Commit
1fe948f
- 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.