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

82%

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

Quality

Content

77%Weight 40%Scale 1-5

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

A highly actionable, well-sequenced workflow with strong validation checkpoints, but it is verbose and bundles a large task-formatting specification inline that would benefit from being split into a referenced file.

Suggestions

Move the detailed worktrail task-formatting rules (lines ~77–134: files: declarations, requirement coverage, [e2e]/[cleanup] tags, task sizing, review: skip) into a references/ file and link to it, keeping SKILL.md as an overview.

Dedupe the 'do NOT run /opsx:apply' / worktrail-orchestrator-replaces-apply guidance, which currently appears in the preamble, step 4, and the Output section.

Tighten the collision-serialization and per-phase hot-file prose, which re-explains compile-step behavior Claude could instead be pointed to once in a reference.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands and field names, but the ~60-line worktrail task-formatting rules and repeated 'do NOT run /opsx:apply' warnings add padding that could be tightened or offloaded.	3 / 5
Actionability	Fully executable: specific bash commands, JSON field names (applyRequires, resolvedOutputPath), and concrete copy-paste-ready examples of files: declarations and [e2e]/[cleanup] tags cover the common cases.	5 / 5
Workflow Clarity	Clear numbered Steps 1–5 with explicit checkpoints (re-run openspec status after each artifact, check applyRequires done), user-input feedback loops, and a final verification checklist re-checking tasks.md against the formatting rules.	5 / 5
Progressive Disclosure	Has clear section headers (Steps, Output, Guidelines, Guardrails) but no bundle files exist and the dense worktrail task-format spec (~60 lines of inline rules) clearly belongs in a separate reference file rather than the SKILL.md overview.	3 / 5
	Total	16 / 20 Passed

Description

87%Weight 40%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.

A strong description that clearly states both capability and trigger conditions in third-person voice with concrete artifacts named. Minor specificity gains are possible by enumerating the individual artifact actions more fully.

Dimension	Reasoning	Score
Specificity	Names the domain (proposing a change) and several concrete actions — 'design, specs, and tasks' artifacts generated in one step — but the individual actions are lightly sketched rather than comprehensively enumerated, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' (propose a change with design/specs/tasks artifacts in one step) and 'when' via a concrete 'Use when the user wants to quickly describe what they want to build' trigger clause.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('describe what they want to build', 'proposal', 'design, specs, and tasks') with good keyword coverage, though a few common synonyms (e.g. 'spec change', 'feature request') are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (one-step OpenSpec change proposal with design/specs/tasks artifacts) with distinct triggers that are unlikely to fire for unrelated skills.	5 / 5
	Total	18 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: behindthedash/worktrail
Path: skills/openspec-propose/SKILL.md
Commit: ca98247

Reviewed: ~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.