CtrlK
BlogDocsLog inGet started
Tessl Logo

openspec-propose

Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.

84

1.04x
Quality

85%

Does it follow best practices?

Impact

69%

1.04x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-sequenced, actionable workflow with strong validation checkpoints and executable commands. Its main weakness is mild redundancy between the step instructions and the Artifact Creation Guidelines section.

Suggestions

Consolidate the repeated 'context and rules are constraints, not file content' guidance into one location to remove duplication between step 4 and the Guidelines section.

Trim the Artifact Creation Guidelines to only points not already implied by the openspec instructions JSON fields described in step 4.

DimensionReasoningScore

Conciseness

Mostly efficient with direct bash commands and no over-explanation of concepts, but the 'Artifact Creation Guidelines' section reiterates rules already covered in step 4 (notably the context/rules constraint), which could be tightened.

2 / 3

Actionability

Provides fully executable commands ('openspec new change', 'openspec status --json', 'openspec instructions') plus concrete tool usage (TodoWrite, AskUserQuestion) and documents the expected JSON fields, making it copy-paste ready.

3 / 3

Workflow Clarity

Five clearly sequenced steps with explicit validation checkpoints (re-run 'openspec status' after each artifact, verify file existence, confirm applyRequires done) and a feedback loop for unclear context.

3 / 3

Progressive Disclosure

A single self-contained file with well-organized Input/Steps/Output/Guidelines/Guardrails sections and no nested external references, appropriate for this workflow skill with no bundle files present.

3 / 3

Total

11

/

12

Passed

Description

85%

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 is well-structured with an explicit 'Use when' trigger and concrete artifact list, clearly occupying a distinct niche. Trigger term coverage is the weakest point, relying on domain-specific language rather than diverse natural phrasings.

Suggestions

Broaden trigger terms with natural user phrasings (e.g., 'plan a feature', 'draft a spec', 'start a new change') to improve recall.

Consider naming the openspec tool explicitly in the description so users referencing it by name trigger the skill.

DimensionReasoningScore

Specificity

Lists multiple concrete artifacts ('design, specs, and tasks') and the action of generating them 'in one step', matching the anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly states both what ('Propose a new change with all artifacts generated in one step') and when via a clear 'Use when the user wants to...' clause.

3 / 3

Trigger Term Quality

Includes natural phrases like 'describe what they want to build' and 'proposal', but coverage of variations a user might say is limited and leans on the openspec domain rather than broad natural terms.

2 / 3

Distinctiveness Conflict Risk

Targets a distinct openspec change-proposal niche with specific triggers ('design, specs, and tasks ready for implementation'), making overlap with unrelated skills unlikely.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
arm/mlia
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.