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.

55

Quality

61%

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 ./skills/openspec-explore/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 body is a well-organized, appropriately behavioral instruction skill with genuinely concrete CLI commands and a clear numbered workflow for the change-context path, though it is longer than it needs to be due to extensive scripted dialogue examples and could split illustrative examples into a reference file.

Suggestions

Trim the four scripted example dialogues to one or two representative ones, or move them to a references/examples.md file and keep a one-line pointer in SKILL.md.

Cut or compress the 'What You Don't Have To Do' section, since it restates the stance already covered by 'This is a stance, not a workflow' and the Guardrails section.

Consider adding a brief validation cue for artifact creation (e.g., running 'openspec validate') before capturing insights into specs or designs.

DimensionReasoningScore

Conciseness

The body is mostly efficient stance guidance, but roughly 100 lines of scripted example dialogues with large ASCII art plus a 'What You Don't Have To Do' section that restates the stance could be tightened, matching 'mostly efficient but includes some unnecessary explanation or could be tightened'.

3 / 5

Actionability

Concrete, executable commands are provided ('openspec list --json', 'openspec status --change "<name>" --json', 'openspec store list --json') with specific JSON fields to consume (changeRoot, artifactPaths, actionContext) and a table mapping insight types to capture locations; minor gaps remain in that the bulk of the guidance is behavioral rather than operational.

4 / 5

Workflow Clarity

The 'when a change exists' path is a clear numbered 4-step sequence ending with an explicit user-decision checkpoint, and the entry check (openspec list --json) is specified; the skill is non-destructive so no validation cap applies, but the deliberately unsequenced stance sections keep it below the top anchor.

4 / 5

Progressive Disclosure

The body is a single 275-line file with clear section headers but no bundle files at all; the four example dialogues are content that could live in a reference file, and at over 50 lines the simple-skill exception does not apply, matching 'some structure but could be better organized'.

3 / 5

Total

14

/

20

Passed

Description

58%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 well-formed with an explicit 'Use when' trigger clause and a clear purpose statement, but its capability list is abstract and it lacks both natural-skill synonyms and any mention of its OpenSpec-specific context, limiting trigger precision and distinctiveness.

Suggestions

Add one or two concrete capability phrases that ground the abstract stance (e.g., 'surfaces risks and tradeoffs, maps existing architecture, sketches ASCII diagrams to clarify thinking').

Broaden trigger terms with common user phrasings such as 'brainstorm', 'talk through an idea', 'compare approaches', or 'explore the problem space'.

Mention the OpenSpec context (e.g., 'within an OpenSpec project') so the description is distinguishable from generic planning or brainstorming skills.

DimensionReasoningScore

Specificity

The description names the domain ('thinking partner for exploring ideas, investigating problems, and clarifying requirements') with three stated actions, but the actions are abstract soft-skill verbs rather than concrete capabilities, matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor.

3 / 5

Completeness

Both 'what' (a thinking partner for exploring/investigating/clarifying) and 'when' ('Use when the user wants to think through something before or during a change') are explicitly present. It falls below the top anchor because the 'what' is somewhat abstract and the 'when' could enumerate more concrete trigger situations.

4 / 5

Trigger Term Quality

'think through something', 'exploring ideas', and 'investigating problems' are natural user phrases, but common variations users would say (brainstorm, talk through, compare options, discuss an approach) are missing, matching the 'some relevant keywords but missing common variations or synonyms' anchor.

3 / 5

Distinctiveness Conflict Risk

'Exploring ideas, investigating problems, and clarifying requirements' is fairly broad and would overlap with generic planning, brainstorming, or discussion skills; the OpenSpec-specific niche that defines this skill is never mentioned in the description.

3 / 5

Total

13

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
behindthedash/worktrail
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.