sdd-init

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

Quality

70%

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

67%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.

A well-structured, actionable init skill with a clear sequenced workflow and good progressive disclosure. Its main weakness is redundancy: the strict_tdd fallback rules are duplicated between the Decision Gates and Execution Steps.

Suggestions

De-duplicate the strict_tdd fallback logic: state the rule once (in Decision Gates) and have Execution Step 4 reference it rather than restating it verbatim.

Tighten the Language Domain Contract to a single concise rule plus the override exception instead of three overlapping paragraphs.

Add an explicit post-write verification checkpoint in the Execution Steps (e.g., confirm artifacts were written and the registry is non-empty before returning the envelope).

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, but the strict_tdd fallback logic is repeated near-verbatim in both the Decision Gates table and Execution Step 4, and the Language Domain Contract is slightly over-explained.	3 / 5
Actionability	Instruction-only but concrete: specific files to inspect (package.json, go.mod, pyproject.toml, Cargo.toml), explicit paths (.atl/skill-registry.md, openspec/config.yaml), config keys (capture_prompt, strict_tdd), and an input-to-action decision table.	4 / 5
Workflow Clarity	A clear 8-step sequence with explicit decision gates and fail-closed logic plus a pre-write guard ("ask before updating openspec/"), but there is no post-write verification step.	4 / 5
Progressive Disclosure	A clear overview points one level deep to a real, well-signaled references/init-details.md (and shared convention files), though some dense decision logic is inlined in the overview rather than delegated to the reference.	4 / 5
	Total	15 / 20 Passed

Description

73%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.

A solid, concrete description with explicit trigger guidance and a distinct niche. Its main weakness is the single-verb capability statement, which lists targets but not multiple distinct actions.

Suggestions

Replace the single "Initialize" verb with multiple distinct actions (e.g., "Detects the stack and test runners, builds the skill registry, and persists SDD context") to raise specificity.

Add a situational "Use when..." clause (e.g., "Use when the user asks to set up or initialize SDD in a project") alongside the trigger list to make the when more explicit.

Include a few more natural trigger synonyms or phrasings users might say (e.g., "setup sdd", "sdd bootstrap") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	"Initialize SDD context, testing capabilities, registry, and persistence" names the domain and several concrete init targets, but uses a single verb ("Initialize") repeated over nouns rather than multiple distinct actions as in the 4-anchor (extract/fill/convert).	3 / 5
Completeness	It answers both what ("Initialize SDD context, testing capabilities, registry, and persistence") and when (explicit "Trigger: ..." guidance with concrete phrases), but the when is a command-style trigger list rather than a situational "Use when..." clause.	4 / 5
Trigger Term Quality	"Trigger: sdd init, iniciar sdd, openspec init" provides good keyword coverage including a Spanish synonym ("iniciar sdd"), though a few natural variations are missing.	4 / 5
Distinctiveness Conflict Risk	"sdd init" / "openspec init" carve a clear SDD-initialization niche with distinct command triggers and minimal conflict risk with other skills.	5 / 5
	Total	16 / 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: 71cf25f

Reviewed: 4 days 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.