openspec-onboard

Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.

Quality

62%

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 ./.agent/skills/openspec-onboard/SKILL.md

Quality

Content

65%

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 thorough, action-oriented onboarding walkthrough with real CLI commands and clear sequencing, but it is a long monolithic file and skips an explicit verification step during implementation. Splitting heavy template blocks into references and adding a verify checkpoint would strengthen the weaker dimensions.

Suggestions

Insert an explicit 'openspec verify' step in Phase 9 (Apply) before archive, rather than only listing it in the command reference table.

Move the large verbatim display templates (welcome, task suggestions, recap) into a references file and reference them by path to reduce inline token load.

Tighten the Phase 11 recap and repeated full-screen blocks to trim verbosity while keeping the cycle clear.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and actionable, but the large verbatim display templates (welcome, task suggestions, recap) and the recap phase add padding that could be tightened.	2 / 3
Actionability	Provides fully executable commands ('openspec new change', 'openspec archive', 'openspec instructions proposal --change ... --json'), concrete file paths, and copy-paste-ready templates.	3 / 3
Workflow Clarity	Eleven well-sequenced phases with PAUSE checkpoints and preflight validation, but the implementation phase modifies real code without an explicit verify/validate step in the cycle, which the rubric caps at 2 for destructive/batch work.	2 / 3
Progressive Disclosure	No bundle files exist and the ~540-line SKILL.md is monolithic; sectioning is clean but content that could be split out (full templates, command reference) is inline with no one-level-deep references.	2 / 3
	Total	9 / 12 Passed

Description

60%

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 concretely states what the skill does in third person, but lacks an explicit 'when to use' trigger clause and leans on domain-specific phrasing rather than natural user terms. Adding a 'Use when...' clause with common phrasings would lift the weaker dimensions.

Suggestions

Append a 'Use when...' clause naming natural user triggers, e.g. 'Use when onboarding to OpenSpec, learning the workflow, or running a first change cycle.'

Add common user phrasings such as 'get started', 'learn', or 'tutorial' alongside 'onboarding' to improve trigger term coverage.

Include a brief disambiguator (e.g. 'first-time walkthrough, not day-to-day changes') to sharpen distinctiveness against other OpenSpec skills.

Dimension	Reasoning	Score
Specificity	Names concrete actions — 'walk through a complete workflow cycle', 'narration', 'real codebase work' — matching the anchor that lists multiple specific concrete actions.	3 / 3
Completeness	Clearly states what the skill does but omits any 'Use when...' trigger guidance; per the rubric a missing explicit when-clause caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant keywords ('onboarding', 'OpenSpec', 'workflow cycle') but misses common natural variations a user would say ('learn', 'get started', 'tutorial', 'how do I use'), and 'workflow cycle' leans on internal jargon.	2 / 3
Distinctiveness Conflict Risk	The onboarding niche is fairly distinct, but the absence of explicit when-triggers limits disambiguation from adjacent OpenSpec tutorial-style skills, so it could still overlap.	2 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (550 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: Draculabo/AntigravityManager
Path: .agent/skills/openspec-onboard/SKILL.md
Commit: de8d68d

Reviewed: about 11 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.