openspec-onboard

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

Quality

61%

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 ./eval/local/skills/benchmarks/dependency/openspec/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 highly actionable with concrete, cross-platform commands and clear templates, and its phase sequence is well-structured with pause checkpoints. Its weaknesses are verbosity/repetition, a missing verification step in the implementation phase, and a monolithic structure with no progressive disclosure to separate reference files.

Suggestions

Add an explicit verification checkpoint in Phase 9 (e.g. run tests or '/opsx:verify <name>') before archiving, to satisfy the validation requirement for code-modifying operations.

De-duplicate the command-reference table (it appears in Phase 11 and again in Graceful Exit) and tighten the canned display blocks to reduce token load.

Move the command reference and reusable templates into a one-level-deep reference file (e.g. references/commands.md) referenced from the overview, to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and is mostly actionable templates, but it is long (~555 lines) with repetition (the command-reference table appears in Phase 11 and again in Graceful Exit) and large canned display blocks that could be tightened. Above anchor 1 (no concept-padding fluff) but not anchor 3 (lean, every token earns its place).	2 / 3
Actionability	It provides fully executable commands (e.g. 'openspec new change "<name>"', 'openspec instructions proposal --change "<name>" --json', 'openspec archive "<name>"', 'git log --oneline -10') with Unix and Windows PowerShell variants, plus concrete copy-paste templates for proposal/spec/design/tasks. Matches anchor 3 (fully executable, copy-paste ready).	3 / 3
Workflow Clarity	Phases are clearly sequenced (Preflight through Phase 11) with explicit PAUSE checkpoints and an EXPLAIN→DO→SHOW→PAUSE pattern, but Phase 9 (Apply) modifies the real codebase without an explicit verification/test checkpoint before archiving. Per the rubric guideline, missing validation in code-modifying (effectively destructive) operations caps workflow_clarity at 2.	2 / 3
Progressive Disclosure	No bundle files exist and the entire skill lives in one ~555-line SKILL.md; sections are well-organized but the command reference and canned templates are inline rather than split into one-level-deep reference files. Better than anchor 1 (well-structured, not a disorganized wall) but not anchor 3 (no well-signaled external references).	2 / 3
	Total	9 / 12 Passed

Description

57%

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 conveys the skill's purpose and is anchored to a distinct, named-tool niche, but it lacks an explicit 'Use when...' trigger clause and its action list is abstract rather than comprehensive. Adding explicit trigger terms and concrete artifact names would lift the weaker dimensions.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to learn OpenSpec, be onboarded, or try a first workflow cycle.'

Replace abstract phrasing ('walk through a complete workflow cycle') with concrete artifact actions, e.g. '...create a change and generate proposal, specs, design, and tasks, then implement and archive it.'

Include natural trigger variations users would say ('learn OpenSpec', 'OpenSpec tutorial', 'first OpenSpec change') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Guided onboarding for OpenSpec') and a few actions ('walk through a complete workflow cycle', 'narration', 'real codebase work'), but these are abstract rather than a comprehensive list of concrete actions (e.g. proposal, specs, design, tasks, archive). It sits above anchor 1 (vague) but below anchor 3 (multiple specific concrete actions).	2 / 3
Completeness	It clearly states what the skill does ('Guided onboarding... walk through a complete workflow cycle with narration and real codebase work') but provides no 'Use when...' clause or equivalent explicit trigger guidance for when Claude should invoke it. Per the rubric guideline, a missing explicit trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Natural terms like 'onboarding' and 'OpenSpec' are present and would be said by a user, but coverage is thin and lacks common variations or explicit trigger phrasing. Not anchor 1 (no jargon-only terms) but not anchor 3 (good coverage) either.	2 / 3
Distinctiveness Conflict Risk	Tying the skill to a named tool ('OpenSpec') plus a specific purpose ('onboarding') carves a clear niche unlikely to trigger for unrelated skills. It is not anchor 2 ('could still overlap with similar skills') because the onboarding/teaching intent distinguishes it from operational OpenSpec skills.	3 / 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 (555 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: rpamis/comet
Path: eval/local/skills/benchmarks/dependency/openspec/openspec-onboard/SKILL.md
Commit: 2945693

Reviewed: about 9 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.