sdd-propose
Create a change proposal with intent, scope, and approach. Trigger: "propose", "propuesta", "proposal", "new change", "nuevo cambio", "sdd new", "sdd propose", "/sdd:new", "sdd:ff", "fast-forward", "fast forward". When triggered by "sdd:ff" or "fast-forward": after creating the proposal, AUTOMATICALLY continue by executing sdd-spec, sdd-design, and sdd-tasks in sequence (do NOT stop after the proposal).
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 excels at trigger term coverage with bilingual support and multiple command variations, and clearly defines when to use the skill. The main weakness is the somewhat vague 'what' - 'change proposal with intent, scope, and approach' could be more concrete about what actions are actually performed beyond creation.
Suggestions
Expand the capability description to include more specific actions (e.g., 'Creates a structured change proposal document defining the problem statement, intended solution, affected components, and implementation approach')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (change proposal) and mentions components (intent, scope, approach), but doesn't elaborate on what these mean or list multiple concrete actions beyond 'create'. | 2 / 3 |
Completeness | Explicitly answers both what ('Create a change proposal with intent, scope, and approach') and when ('Trigger:' followed by comprehensive list). Also includes conditional behavior for fast-forward mode. | 3 / 3 |
Trigger Term Quality | Excellent coverage of trigger terms including natural language ('propose', 'proposal', 'new change'), bilingual support ('propuesta', 'nuevo cambio'), and command variations ('sdd new', '/sdd:new', 'sdd:ff', 'fast-forward'). | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche with distinct 'sdd' prefix triggers and clear domain (change proposals). The combination of 'sdd' commands and proposal-specific terms makes conflicts unlikely. | 3 / 3 |
Total | 11 / 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 skill with excellent actionability and clear workflow sequencing. The main weakness is the large inline template that inflates token count when it could be referenced externally. The error recovery table is a strong addition that handles edge cases explicitly.
Suggestions
Move the full proposal.md template to a separate reference file (e.g., templates/proposal-template.md) and reference it, keeping only a brief example inline
Remove the inline size guideline table - Claude understands T-shirt sizing without the reference chart
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy, such as the inline size guideline table that Claude likely knows, and the full proposal template could be referenced externally rather than inline. | 2 / 3 |
Actionability | Provides fully concrete guidance with exact markdown templates, specific file paths, clear persistence commands (mem_save with topic_key), and explicit output format. Copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | Clear 4-step sequence (Read specs → Write proposal → Persist → Return summary) with explicit mode-based branching. Error recovery table provides validation checkpoints for common failure scenarios. | 3 / 3 |
Progressive Disclosure | References external files appropriately (persistence-contract.md, engram-convention.md, openspec-convention.md), but the large inline proposal template could be split to a separate reference file. The skill is somewhat monolithic. | 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 |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 10 / 11 Passed | |
- Repository
- Yoizen/dev-ai-workflow
- Commit
d9bf9a4
- 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.