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.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

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 content is highly actionable with concrete commands, explicit JSON contract details, and a well-sequenced workflow with validation checkpoints. The main weakness is conciseness, where a few dense explanatory passages could be trimmed.

Suggestions

Tighten the long guideline bullets about the transitive required-set closure and skip handling into a compact checklist; the rationale can be inferred from the commands.

Consider moving the verbose 'Artifact Creation Guidelines' and 'Guardrails' into a short bulleted checklist to reduce wall-of-text density.

DimensionReasoningScore

Conciseness

The body avoids basic-concept padding and uses executable commands, but several dense guideline passages (e.g. the transitive-required-set closure explanation) could be tightened, placing it at mostly-efficient rather than maximally lean.

2 / 3

Actionability

Provides fully executable bash commands (openspec new change, status --json, instructions) with specific JSON fields to parse and concrete output paths, making the guidance copy-paste ready.

3 / 3

Workflow Clarity

Sequences a multi-step process (steps 1-5) with dependency-ordered artifact creation, explicit checkpoints (re-run status after each artifact, verify file exists before proceeding), and clear stop conditions for skipped/blocked artifacts.

3 / 3

Progressive Disclosure

Organized as a single well-structured SKILL.md with clearly labeled sections and no nested or multi-level external references; no bundle files exist, so the content is appropriately self-contained.

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 clearly conveys the skill's purpose and when to use it, with concrete artifact types and an explicit trigger clause. Trigger-term variation is the weakest area, keeping it just short of maximal coverage.

Suggestions

Broaden trigger terms with natural variations users might say, e.g. "scaffold a spec", "write up a change proposal", or "draft design and tasks", to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Propose a new change with all artifacts generated in one step" and "a complete proposal with design, specs, and tasks" — rather than vague language.

3 / 3

Completeness

Explicitly answers both what (generate proposal/design/specs/tasks in one step) and when ("Use when the user wants to quickly describe what they want to build"), matching the anchor with an explicit Use-when clause.

3 / 3

Trigger Term Quality

Includes natural phrases users would say ("describe what they want to build", "propose a change") but offers limited synonym variation and no short-form trigger variants, so coverage is partial.

2 / 3

Distinctiveness Conflict Risk

The artifact-generation niche with concrete triggers (proposal, design, specs, tasks) is distinct and unlikely to fire for unrelated skills.

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
Fission-AI/OpenSpec
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.