sdd-explore

Explore SDD ideas before committing to a change. Trigger: orchestrator launches exploration or requirement clarification.

Quality

59%

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 ./internal/assets/skills/sdd-explore/SKILL.md

Quality

Content

65%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 body is well-structured, concise, and actionable with concrete artifact paths and an exact return template. Its main weakness is workflow_clarity: the exploration workflow lacks explicit validation checkpoints or feedback loops despite touching broad codebase reads and a mandatory persistence step.

Suggestions

Add an explicit validation checkpoint after Step 3 (e.g., 'Verify you have read real code for each affected area before analyzing options') and a feedback loop if investigation is incomplete before persisting.

Fill the Approaches table with a worked mini-example or one concrete row so the analysis step is copy-paste ready rather than a placeholder.

Either bundle or inline the essentials from skills/_shared/sdd-phase-common.md Sections A-D so the navigation is self-contained and the references resolve within the skill bundle.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's competence (role gating, terse step lists, a compact INVESTIGATE tree and return template), with only minor explanatory phrasing that could be trimmed; it avoids explaining basic concepts.	4 / 5
Actionability	Mostly concrete and executable — explicit artifact paths, topic_key values, persistence modes, and an exact return-format template — with minor gaps such as the Approaches table being a placeholder rather than worked example.	4 / 5
Workflow Clarity	A clear six-step sequence exists, but the investigate/analyze steps lack explicit validation checkpoints and the cap applies: exploration involves potentially broad/batch reads with no verify-relevance or feedback loop before persisting the artifact.	3 / 5
Progressive Disclosure	Structure is well organized into clearly signaled sections and it delegates detail to one-level-deep shared references (skills/_shared/sdd-phase-common.md Sections A-D), though those references are external to this bundle and not navigable from the file itself.	4 / 5
	Total	15 / 20 Passed

Description

53%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 is specific and clear about what the skill does and gives an explicit trigger, but the trigger is framed for an orchestrator rather than as natural user language, which weakens trigger-term quality. Overall a solid, well-scoped description with room to add user-facing trigger phrases.

Suggestions

Add natural user-facing trigger phrases (e.g., 'Use when the user wants to explore an idea, weigh approaches, or understand impact before committing to a change') so the skill surfaces in real conversations.

Third-person voice is correct; keep it and avoid first/second person in any future edits.

Consider listing 1-2 more concrete output actions (e.g., 'compares approaches, identifies affected files') to lift specificity toward a 5.

Dimension	Reasoning	Score
Specificity	Names a concrete domain (SDD exploration) and specific actions — 'investigate the codebase, think through problems, compare approaches, and return a structured analysis' — but is not a multi-action list of concrete operations like the score-5 anchor.	4 / 5
Completeness	Clearly states what the skill does (explore/investigate and return analysis) and gives a 'when' trigger ('Trigger: orchestrator launches exploration or requirement clarification'), though the trigger is system-oriented rather than user-facing.	4 / 5
Trigger Term Quality	Triggers are internal/operational ('orchestrator launches exploration or requirement clarification') rather than natural phrases a user would actually say; it is effectively only one or two generic terms.	2 / 5
Distinctiveness Conflict Risk	The SDD exploration niche is fairly distinct from sibling skills, with minor overlap risk against adjacent SDD-phase skills; the explicit sub-agent role framing narrows the conflict surface.	4 / 5
	Total	14 / 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-explore/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.