CtrlK
BlogDocsLog inGet started
Tessl Logo

openspec-explore

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

68

1.04x
Quality

53%

Does it follow best practices?

Impact

94%

1.04x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/openspec-explore/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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, self-contained stance document with some genuinely concrete guidance (an openspec command, file paths, a capture table), but it is verbose for a non-procedural skill and keeps illustrative material inline rather than splitting it into one-level-deep references.

Suggestions

Tighten or consolidate the repeated stance statements across "The Stance", "What You Don't Have To Do", and "Guardrails" to reduce redundancy.

Move the four "Handling Different Entry Points" example dialogues into a separate EXAMPLES.md reference and link to it from the body, improving both conciseness and progressive disclosure.

Promote the concrete capture table and `openspec list --json` command higher as the primary actionable reference, since the surrounding behavioral guidance is the least actionable part.

DimensionReasoningScore

Conciseness

The body is well-organized but long (~278 lines) and restates the stance across "The Stance", "What You Don't Have To Do", and "Guardrails", with four verbose example dialogues that could be tightened, matching the anchor for mostly efficient content with some unnecessary explanation.

2 / 3

Actionability

It provides concrete elements (`openspec list --json`, artifact file paths, and an insight-to-artifact capture table), but the bulk of the guidance is behavioral and vague ("Be curious", "Challenge assumptions", "Follow interesting threads"), so it has some concrete guidance but is incomplete as executable instruction.

2 / 3

Workflow Clarity

The "When a change exists" section provides a clear numbered four-step sequence, but the skill is deliberately non-procedural elsewhere and lacks explicit validation/checkpoint steps, matching the anchor for steps listed with implicit or missing checkpoints.

2 / 3

Progressive Disclosure

It is a single monolithic file with no bundle files or external references; internal sections are well-organized, but at ~278 lines (above the 50-line simple-skill threshold) content such as the example dialogues could be split into separate references, matching the anchor for some structure with content that should be separate kept inline.

2 / 3

Total

8

/

12

Passed

Description

57%

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 cleanly answers both what and when with an explicit Use-when trigger, but its opening imperative voice triggers a specificity penalty and its actions lean abstract and somewhat generic, limiting distinctiveness.

Suggestions

Rewrite in third person (e.g., "Explores ideas, investigates problems, and clarifies requirements...") instead of the imperative "Enter explore mode" to avoid the specificity penalty.

Add more natural trigger variations users would actually say (e.g., "brainstorm", "talk through", "think out loud") alongside the product term "explore mode".

Sharpen the actions with more concrete framing to separate this skill from general reasoning/brainstorming skills.

DimensionReasoningScore

Specificity

Lists three actions ("exploring ideas, investigating problems, and clarifying requirements") which alone would rate a 2 for naming a domain plus actions, but the opening "Enter explore mode" is second-person imperative voice, which the rubric penalizes by reducing specificity by 1; the actions are also abstract rather than concrete technical operations.

1 / 3

Completeness

It explicitly states what the skill does ("a thinking partner for exploring ideas, investigating problems, and clarifying requirements") and provides an explicit "Use when the user wants to think through something before or during a change" trigger, clearly answering both what and when.

3 / 3

Trigger Term Quality

It includes natural user phrases ("think through something", "exploring ideas", "investigating problems") but leads with the product-specific jargon "explore mode" and lacks common trigger variations, matching the anchor for some relevant keywords with missing variations.

2 / 3

Distinctiveness Conflict Risk

The "explore mode / thinking partner" framing gives it a recognizable niche, but the underlying actions (exploring, investigating, clarifying requirements) are generic enough to overlap with general reasoning or brainstorming skills.

2 / 3

Total

8

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
arm/mlia
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.