Name: openspec-propose
Rating: 57.599999999999994 (1 reviews)
Author: jabrena

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.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/problem2/scenario3/.agents/skills/openspec-propose/SKILL.md

The canonical home for this skill is openspec-propose in jabrena/plinth

Quality

Content

63%Scale 1-5

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

This is a solid, actionable skill that provides a clear workflow for proposing changes using the openspec CLI. Its main strengths are concrete CLI commands and a well-sequenced multi-step process with dependency tracking. Weaknesses include some redundancy between the steps and the guidelines/guardrails sections, and the lack of example JSON outputs that would help Claude parse CLI responses correctly.

Suggestions

Remove redundant guidance between Steps section and Artifact Creation Guidelines/Guardrails — consolidate 'don't copy context/rules into output' and 're-read dependencies from disk' into a single mention each.

Add a brief example of the expected JSON structure from `openspec status --json` and `openspec instructions --json` so Claude knows exactly which fields to parse.

Dimension	Reasoning	Score
Conciseness	The skill is moderately efficient but includes some unnecessary verbosity. The 'Artifact Creation Guidelines' section repeats points already made in the steps (e.g., re-reading dependencies, not copying context/rules into output). The IMPORTANT callouts are repeated. Some tightening is possible, but it's not egregiously padded.	3 / 5
Actionability	Provides concrete CLI commands (openspec new change, openspec status, openspec instructions) with specific flags and JSON parsing guidance. The workflow is clearly executable. Minor gaps: no example of what the JSON output looks like from status/instructions commands, which would help Claude parse them correctly.	4 / 5
Workflow Clarity	Clear multi-step sequence with a well-defined loop (create artifacts in dependency order), re-check status after each artifact, and a stopping condition (all applyRequires done). Includes verification steps (check artifact exists after writing, re-run status). Minor gap: no explicit error recovery if openspec commands fail or if artifact creation fails validation.	4 / 5
Progressive Disclosure	The content is a single monolithic file with no references to supporting documents. At ~90 lines with multiple sections (steps, guidelines, guardrails), some content like the artifact creation guidelines and guardrails could be separated or the skill could reference external docs for the openspec CLI. However, it's reasonably well-structured with clear headers and sections within the single file.	3 / 5
	Total	14 / 20 Passed

Description

67%Scale 1-5

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 has a solid structure with both 'what' and 'when' clauses clearly present, which is its strongest aspect. However, it suffers from moderate vagueness in what specific actions are performed and what 'artifacts' means concretely, and the trigger terms could be more comprehensive to cover natural user language variations. The skill's niche is not sharply defined, creating potential overlap with related planning or specification skills.

Suggestions

Add more specific concrete actions and artifact types, e.g., 'Generates a design document, technical specification, and implementation task list from a user's feature description'

Include more natural trigger terms and synonyms users might say, such as 'plan a feature', 'RFC', 'project plan', 'spec out', 'scaffold a project', or 'kickoff a new feature'

Clarify what distinguishes this from other planning or spec-writing skills — e.g., emphasize the 'single-step, all-in-one' nature more explicitly or mention the specific output format

Dimension	Reasoning	Score
Specificity	Names the domain (proposing changes/proposals) and mentions a few concrete outputs ('design, specs, and tasks'), but the actions themselves are vague — 'propose a new change' and 'all artifacts generated' lack specificity about what kinds of artifacts, what format, or what concrete steps are performed.	3 / 5
Completeness	Clearly answers both 'what' (propose a new change with design, specs, and tasks in one step) and 'when' ('Use when the user wants to quickly describe what they want to build and get a complete proposal'). The 'Use when' clause is explicit with concrete trigger guidance.	5 / 5
Trigger Term Quality	Includes some relevant terms like 'proposal', 'design', 'specs', 'tasks', and 'build', but misses natural user phrases like 'create a plan', 'project plan', 'feature request', 'RFC', 'spec out', or 'scaffold'. The trigger terms are somewhat generic.	3 / 5
Distinctiveness Conflict Risk	The description could overlap with project planning skills, task management skills, or design document generation skills. Terms like 'design', 'specs', and 'tasks' are broad enough to conflict with more specialized skills in those areas. The 'one step' and 'complete proposal' framing helps somewhat but doesn't fully distinguish it.	3 / 5
	Total	14 / 20 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: jabrena/plinth
Path: benchmarks/problem2/scenario3/.agents/skills/openspec-propose/SKILL.md
Commit: f6dfc6f

Reviewed: about 2 hours 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.