sdd-propose

Create a change proposal with intent, scope, and approach. Trigger: When the orchestrator launches you to create or update a proposal for a change.

Quality

55%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/sdd-propose/SKILL.md

Quality

Discovery

25%

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 is too vague and internally-focused to be effective for skill selection. It lacks concrete actions, natural user trigger terms, and relies on system jargon ('orchestrator launches you') rather than describing scenarios a user would naturally express. The core concept of 'change proposal' is somewhat distinctive but insufficiently detailed.

Suggestions

Replace the orchestrator-focused trigger with user-facing scenarios, e.g., 'Use when the user asks to draft an RFC, change proposal, design document, or needs to document the intent and scope of a planned change.'

Add specific concrete actions such as 'Analyzes proposed changes, documents motivation and impact, outlines implementation approach, identifies risks and dependencies, and generates a structured proposal document.'

Include natural trigger terms users would say, such as 'RFC', 'design doc', 'proposal', 'change request', 'implementation plan', or 'technical spec'.

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'intent, scope, and approach' without specifying concrete actions. It doesn't explain what a 'change proposal' entails or what specific operations are performed (e.g., analyzing code diffs, writing documentation, generating templates).	1 / 3
Completeness	It partially answers 'what' (create a change proposal with intent, scope, and approach) and has a trigger clause, but the trigger is system-oriented ('when the orchestrator launches you') rather than describing user-facing scenarios. The 'when' is present but not useful for matching user requests.	2 / 3
Trigger Term Quality	The trigger references 'the orchestrator launches you' which is internal system jargon, not natural user language. Terms like 'change proposal' are somewhat relevant but there are no natural user keywords like 'RFC', 'design doc', 'pull request description', or other variations users might say.	1 / 3
Distinctiveness Conflict Risk	'Change proposal' is somewhat specific as a concept, but without more detail about what kind of changes (code, infrastructure, process) or what format the proposal takes, it could overlap with documentation, planning, or code review skills.	2 / 3
	Total	6 / 12 Passed

Implementation

85%

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 that provides clear, actionable guidance for creating change proposals. The multi-mode branching (engram/openspec/hybrid/none) is thoroughly handled at each step, and the proposal template is concrete and complete. Minor verbosity in repeating mode-conditional logic across steps prevents a perfect conciseness score, but overall the skill is effective and well-organized.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but has some redundancy — the mode-based branching (engram/openspec/hybrid/none) is repeated across multiple steps when it could be consolidated. The proposal template itself is appropriately structured but the surrounding instructions could be tighter.	2 / 3
Actionability	The skill provides a complete, copy-paste-ready proposal.md template with specific markdown structure, concrete examples of each section, and clear directory paths. The return summary format is also fully specified. Each step has concrete actions tied to specific modes.	3 / 3
Workflow Clarity	The 6-step workflow is clearly sequenced with explicit mode-based branching at each step. Step 5 is marked as MANDATORY with persistence validation. The rules section includes update-before-overwrite guidance ('READ it first and UPDATE it'), providing a feedback loop for existing proposals.	3 / 3
Progressive Disclosure	The skill appropriately references shared conventions via one-level-deep links (sdd-phase-common.md Sections A-D, openspec-convention.md) rather than inlining them. The main content stays focused on proposal-specific logic while delegating shared patterns to referenced files.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: Gentleman-Programming/agent-teams-lite
Commit: 6901875

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

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.