sdd-init

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

Quality

81%

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

Quality

Content

72%

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 well-structured, actionable instruction skill with concrete file targets and a clean reference split. Its main weaknesses are a redundant orchestrator/executor gate explanation and mostly implicit validation checkpoints in the execution workflow.

Suggestions

Collapse the ORCHESTRATOR GATE blockquote and the Executor Override section into a single concise directive to remove the duplicated delegation guidance and tighten conciseness.

Add an explicit validation checkpoint in the Execution Steps, e.g. after persistence initialization, verify the written artifacts exist and match the resolved mode before returning the envelope, to lift workflow clarity.

Tighten the Language Domain Contract to a one-line rule with the override condition, since the current three-sentence form repeats the same neutral-register guidance.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and stays lean, but the "ORCHESTRATOR GATE" blockquote and the "Executor Override" section restate the same delegation point, matching the level-2 anchor of mostly efficient with some tightening possible; it is not level 3 because of that redundancy, and not level 1 because there is no concept padding.	2 / 3
Actionability	Concrete file paths and config keys (".atl/skill-registry.md", "sdd/{project}/testing-capabilities", "openspec/config.yaml testing:") plus an exact Output Contract field list provide specific, executable guidance matching the level-3 anchor; as an instruction-only skill the absence of code is not penalized because the guidance is actionable.	3 / 3
Workflow Clarity	Numbered Execution Steps 1–7 and the Decision Gates table give a clear sequence with branching, matching the level-2 anchor of steps listed but checkpoints implicit; it is not level 3 because explicit validation/feedback-loop checkpoints are thin (only "ask before updating" if openspec exists), and not level 1 because the sequence is unambiguous.	2 / 3
Progressive Disclosure	The body is a clear overview pointing to a one-level-deep, described reference ("[references/init-details.md] — detection checklist, Engram payloads, config skeleton, and output templates", verified to exist), matching the level-3 anchor; detail is appropriately split out rather than inlined.	3 / 3
	Total	10 / 12 Passed

Description

90%

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 pairs an explicit trigger clause with a concise list of initialization actions, giving it strong trigger coverage and clear distinctiveness. Its only weakness is mild abstraction in some named actions ("context", "capabilities") rather than fully concrete operations.

Dimension	Reasoning	Score
Specificity	Quotes "Initialize SDD context, testing capabilities, registry, and persistence" name the SDD domain and several actions, matching the level-2 anchor; not level 3 because terms like "context" and "capabilities" are somewhat abstract rather than concrete operations.	2 / 3
Completeness	The explicit "Trigger:" clause answers when and "Initialize SDD context, testing capabilities, registry, and persistence" answers what, matching the level-3 anchor that requires both; the presence of an explicit trigger clause means it is not capped at level 2.	3 / 3
Trigger Term Quality	Quotes "Trigger: sdd init, iniciar sdd, openspec init" give good coverage of natural command-style terms a user would actually type (including a Spanish variant), matching the level-3 anchor; it is not level 2 because common variations are well represented rather than partially missing.	3 / 3
Distinctiveness Conflict Risk	The SDD-specific command triggers ("sdd init", "iniciar sdd", "openspec init") occupy a clear niche unlikely to fire for unrelated skills, matching the level-3 anchor; it is not level 2 because the triggers are distinct rather than merely domain-tagged.	3 / 3
	Total	11 / 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
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: e01b114

Reviewed: about 14 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.