CtrlK
BlogDocsLog inGet started
Tessl Logo

openspec-onboard

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

62

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/openspec-onboard/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

The skill is highly actionable with a clear, well-sequenced workflow and explicit validation/pause checkpoints, but it is a monolithic single file with no progressive disclosure into referenced bundle files.

Suggestions

Extract the repeated artifact templates (proposal, spec WHEN/THEN, design, tasks) into a referenced file (e.g. references/artifact-templates.md) and link to it from each phase.

Move the command reference table to a separate references/commands.md and summarize inline, reducing the main body length.

Trim the framing prose that restates what each artifact 'is' (Claude can infer from the template) to tighten conciseness.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete commands and templates, but the explanatory prose framing artifact purposes ('The proposal captures why...') mildly over-explains concepts Claude already knows.

4 / 5

Actionability

Provides copy-paste ready bash commands (openspec status/init/new/archive), exact artifact file paths, and complete WHEN/THEN spec and proposal templates covering the common cases.

5 / 5

Workflow Clarity

Clear 11-phase sequence with explicit PAUSE checkpoints, a preflight validation gate, graceful exit handling, and a recap; feedback and recovery loops are explicit.

5 / 5

Progressive Disclosure

Single monolithic file with all artifact templates and the command reference inlined; no bundle references exist, and content that could be split (artifact templates, command reference) remains inline.

3 / 5

Total

17

/

20

Passed

Description

62%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.

The description conveys a clear niche and concrete actions but omits any explicit 'when to use' trigger guidance, which caps completeness. Adding a 'Use when...' clause with natural trigger phrases would lift the two weakest dimensions.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when a user is new to OpenSpec or asks to learn the OpenSpec workflow.'

Include natural trigger phrases users would actually say (e.g. 'onboard', 'tutorial', 'walk me through', 'learn OpenSpec') rather than only domain terms.

Mention the command trigger (e.g. '/opsx:onboard') so users invoking it verbally map to the skill.

DimensionReasoningScore

Specificity

Names the domain ('OpenSpec' onboarding) and several concrete actions ('walk through a complete workflow cycle', 'narration', 'real codebase work'), with only minor abstraction gaps versus the comprehensive anchor.

4 / 5

Completeness

Has a clear 'what' but lacks any explicit 'Use when...' trigger clause, so per the rubric completeness caps at 3.

3 / 5

Trigger Term Quality

Includes relevant terms ('onboarding', 'OpenSpec', 'workflow cycle') but omits natural user phrasings and synonyms a user would actually say; no file extensions or common variations.

3 / 5

Distinctiveness Conflict Risk

Clearly niched to OpenSpec onboarding with a distinct, narrow trigger and minimal overlap risk with other skills.

5 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (550 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
PBH-BTN/PeerBanHelper
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.