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.

Quality

73%

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 ./.agent/skills/openspec-explore/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.

The content delivers concrete, actionable OpenSpec-aware guidance with a clear sequenced branch and strong section organization. Its chief weakness is conciseness: the large illustrative dialogues and overlapping sections inflate a skill that is conceptually a lightweight stance.

Suggestions

Trim or collapse the four full ASCII worked examples in "Handling Different Entry Points" into a single compact example plus one-line sketches — they demonstrate a stance Claude already knows how to perform.

Merge "What You Might Do" and "Handling Different Entry Points" since both enumerate the same kinds of exploratory moves, to remove overlap.

Move the insight-to-file capture table and artifact path reference into a short "Reference" section near the top so the stance prose stays lean.

Dimension	Reasoning	Score
Conciseness	The body is well-organized but ~290 lines for a skill that declares itself "a stance, not a workflow"; the four large ASCII worked examples and overlapping sections ("What You Might Do" vs "Handling Different Entry Points") are padding that could be trimmed without losing clarity.	3 / 5
Actionability	Provides concrete executable guidance — `openspec list --json`, specific artifact paths, the insight-to-file capture table, and transition commands (`/opsx:new`, `/opsx:ff`) — with only minor gaps in the softer stance directives.	4 / 5
Workflow Clarity	By design non-workflow, but the "When a change exists" branch is a clear 4-step sequence and the capture table acts as a checklist; no destructive or batch operations so the validation cap does not apply.	4 / 5
Progressive Disclosure	No bundle files exist and no external references are used; the body is divided into clearly labeled, `---`-separated sections that are easy to navigate, with only minor organization gaps given the length.	4 / 5
	Total	15 / 20 Passed

Description

78%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 cleanly answers both what and when with a natural trigger phrase and stays in third person, scoring well on completeness and trigger quality. Its main weakness is specificity: the named actions are abstract rather than concrete technical operations.

Dimension	Reasoning	Score
Specificity	Names three actions ("exploring ideas, investigating problems, and clarifying requirements") but they are abstract/generic rather than the crisp technical operations of the anchor-4 example, and the "thinking partner" framing is soft.	3 / 5
Completeness	Explicitly states both what ("a thinking partner for exploring ideas, investigating problems, and clarifying requirements") and when ("Use when the user wants to think through something before or during a change") with a concrete trigger phrase.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ("think through something", "before or during a change", "explore", "investigate", "clarify requirements"), but misses common synonyms like "brainstorm" or "talk through".	4 / 5
Distinctiveness Conflict Risk	"Explore mode" is a distinct niche with a fairly specific trigger, though "exploring ideas / investigating problems" is broad enough to create minor overlap with general analysis skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Draculabo/AntigravityManager
Path: .agent/skills/openspec-explore/SKILL.md
Commit: e29cfdc

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.