CtrlK
BlogDocsLog inGet started
Tessl Logo

sdd-explore

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

57

Quality

66%

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 ./internal/assets/skills/sdd-explore/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-organized, clearly sequenced executor playbook with good progressive disclosure through one-level-deep shared-file references, but it is held back by placeholder-driven/externalized actionable detail and implicit rather than explicit validation checkpoints.

Suggestions

Add an explicit inline validation checkpoint in the step flow (e.g., after Step 3: 'If investigation is insufficient, state what clarification is needed before proceeding') rather than burying it in Rules.

Inline a minimal concrete example of the persisted artifact path and the return envelope so the body is copy-paste ready without chasing the shared Section A/C/D references.

Consolidate the duplicated Section B/C references and overlapping engram/openspec/hybrid/none lists into a single table to remove redundancy.

DimensionReasoningScore

Conciseness

The body is mostly efficient and well-structured, but the repeated cross-references to shared sections (Section A/B/C/D) and overlapping persistence/retrieval lists introduce redundancy that could be tightened, fitting the 'mostly efficient but could be tightened' anchor.

2 / 3

Actionability

It gives a concrete 6-step process with templates and an exact output format, but executable specifics are largely externalized to shared files and the templates are placeholder-driven ({topic}, {list}), so key details are incomplete within the body.

2 / 3

Workflow Clarity

Steps 1-6 are clearly sequenced with a MANDATORY callout, but validation/verification checkpoints are only implicit (error-handling lives in the Rules section rather than inline checkpoints), matching the anchor for a present sequence with missing explicit checkpoints.

2 / 3

Progressive Disclosure

The body is organized into clear sections and defers detailed shared mechanics to one-level-deep, clearly-signaled references (Section A/B/C/D of sdd-phase-common.md, openspec-convention.md) with no nested reference chain, fitting the well-signaled one-level-deep reference anchor.

3 / 3

Total

9

/

12

Passed

Description

75%

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 complete and distinctive, with an explicit trigger clause and a clear SDD-exploration niche, but its trigger terms lean on operational/orchestrator jargon rather than natural user phrasing and its capability list is not comprehensive.

Suggestions

Reframe the trigger in natural user terms (e.g., "Use when the user wants to explore approaches or clarify a requirement before committing to a change") rather than orchestrator-oriented phrasing.

Add a second concrete action or two (e.g., "investigate the codebase, compare approaches, return a structured analysis") to lift specificity from domain-level to a list of concrete actions.

DimensionReasoningScore

Specificity

The description names the domain and a concrete action ("Explore SDD ideas before committing to a change") but does not enumerate multiple specific actions, matching the anchor that names a domain and some actions without being comprehensive.

2 / 3

Completeness

It states what the skill does ("Explore SDD ideas before committing to a change") and provides an explicit trigger clause ("Trigger: orchestrator launches exploration or requirement clarification"), clearly answering both what and when.

3 / 3

Trigger Term Quality

It includes some relevant keywords ("explore", "ideas", "requirement clarification") but the explicit trigger ("orchestrator launches exploration") is operational jargon a user would not naturally say, so common natural-language variations are missing.

2 / 3

Distinctiveness Conflict Risk

It occupies a clear niche (SDD exploration phase) with a distinct trigger tied to the orchestrator flow, making it unlikely to fire for the wrong skill.

3 / 3

Total

10

/

12

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

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository
Gentleman-Programming/gentle-ai
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.