sdd-init

Trigger: sdd init, iniciar sdd, openspec init. Initialize SDD context, testing capabilities, registry, and persistence.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./internal/assets/skills/sdd-init/SKILL.md

Quality

Content

78%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.md body is a compact, well-structured instruction contract that delegates detail to a verified reference file and provides concrete paths, keys, and a decision table. It is slightly shy of fully lean and lacks explicit failure-recovery feedback loops, capping workflow_clarity and conciseness at 4.

Dimension	Reasoning	Score
Conciseness	The body is a lean set of directive sections with no concept padding Claude already knows; a few sentences (e.g., the Language Domain Contract) could be tightened further, keeping it just below fully lean.	4 / 5
Actionability	Concrete file paths, config keys (capture_prompt: false, sdd/{project}/testing-capabilities), and a decision table give mostly executable guidance, with minor gaps where exact commands defer to the reference file.	4 / 5
Workflow Clarity	A clear seven-step sequence pairs with a decision-gates table and an explicit gate to ask before overwriting openspec/, but recovery/feedback loops on failure are only lightly addressed, so it stops short of explicit validation checkpoints.	4 / 5
Progressive Disclosure	The body is a well-organized overview and pushes detection checklists, config skeletons, and output templates into a real, one-level-deep references/init-details.md, with clearly signaled links and no nested reference chains.	5 / 5
	Total	17 / 20 Passed

Description

66%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 front-loads concrete trigger phrases and lists specific initialization actions, but it omits an explicit 'Use when' guidance clause, which the rubric caps at completeness 3. Trigger quality and distinctiveness are strong thanks to the command-style keywords.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when initializing or bootstrapping SDD in a project') to lift completeness above 3.

Concretize the abstract nouns 'context' and 'persistence' (e.g., 'detect stack and testing capabilities, write registry and config artifacts') to push specificity to 5.

Include a few more natural trigger synonyms or file markers (e.g., 'sdd setup', 'bootstrap SDD') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several specific concrete actions — 'Initialize SDD context, testing capabilities, registry, and persistence' — though 'context' and 'persistence' are somewhat abstract, leaving minor coverage gaps rather than full comprehensiveness.	4 / 5
Completeness	It clearly states what the skill does but lacks an explicit 'Use when...' clause; the 'when' is only weakly implied by the trigger prefix, which caps completeness per the rubric guideline.	3 / 5
Trigger Term Quality	Explicit trigger phrases 'sdd init, iniciar sdd, openspec init' include a non-English synonym users would naturally type, giving good keyword coverage with only a few natural variants missing.	4 / 5
Distinctiveness Conflict Risk	The distinct command-named triggers ('sdd init', 'openspec init') carve a clear niche with minimal overlap risk against other skills, though the SDD domain could touch related dev-tooling skills.	4 / 5
	Total	15 / 20 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
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: Gentleman-Programming/gentle-ai
Path: internal/assets/skills/sdd-init/SKILL.md
Commit: a245f26

Reviewed: 1 day 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.