CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

60

Quality

75%

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

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 body successfully teaches a non-procedural stance with concrete commands, artifact paths, and a capture mapping, all clearly sectioned. Its main cost is redundancy — the stance principles are repeated across three sections and the illustrative dialogues inflate length without adding operational detail.

Suggestions

Merge 'What You Don't Have To Do' and 'Guardrails' into a single section — they currently repeat the same principles ('don't implement', 'don't rush', 'don't force structure', 'do visualize') already stated in the opening stance paragraph.

Trim or externalize the four full example dialogues (~100 lines) to one or two compact illustrations; the remaining length reduction would materially improve token efficiency, the lowest-scoring dimension.

Specify what to do with the `openspec list --json` output when multiple changes exist (e.g., which artifact to read first), closing the minor actionability gap.

DimensionReasoningScore

Conciseness

The body restates the same core principles in three places — "This is a stance, not a workflow" (line 16), the "What You Don't Have To Do" list (lines 136-143), and the "Guardrails" section (lines 281-290) repeat 'don't implement', 'don't rush', 'don't force structure', and 'do visualize'. There is no conceptual over-explanation, but the ~100 lines of example dialogues plus the redundant sections could be tightened, matching anchor 3 better than the padding level of anchor 2.

3 / 5

Actionability

The body provides concrete, executable anchors: the `openspec list --json` command, exact artifact paths (`openspec/changes/<name>/proposal.md`, `design.md`, `tasks.md`), an insight-type-to-artifact capture table, and transition commands (`/opsx:new`, `/opsx:ff`). Minor gaps remain (e.g., what to do with the `openspec list` output beyond the three bullets), matching anchor 4.

4 / 5

Workflow Clarity

Although deliberately non-procedural, the operating sequence is unambiguous: check context at start, branch on whether a change exists, read artifacts for context, offer to capture (never auto-capture), and the user decides. Entry-point examples and ending guidance cover the paths. No destructive or batch operations exist, so no validation cap applies, but there are no explicit checkpoints of the anchor-5 level either.

4 / 5

Progressive Disclosure

A single well-organized file with clear section headers and no bundle files to navigate. The long example dialogues (lines 149-247) could plausibly live in a reference file, which keeps this at anchor 4 ('minor organization gaps') rather than a fully split structure.

4 / 5

Total

15

/

20

Passed

Description

70%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.

A solid description with an explicit 'Use when...' clause, third-person voice, and natural trigger phrasing. Its main weakness is abstraction — it says what the skill is like (a thinking partner) more than what it concretely does.

DimensionReasoningScore

Specificity

The description names the domain ("a thinking partner") and three actions ("exploring ideas, investigating problems, and clarifying requirements"), but these are abstract gerunds rather than the operationally concrete actions of anchor 4 — there is no specification of what the skill actually produces or operates on.

3 / 5

Completeness

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") are present and explicit. It falls short of anchor 5 because the 'what' is abstract and the 'when' is a single trigger rather than a set of concrete trigger phrases.

4 / 5

Trigger Term Quality

Natural phrases like "think through something", "exploring ideas", "investigating problems", and "before or during a change" would match how users phrase this need, but common synonyms like "brainstorm", "talk through", or "spike" are missing, matching anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

"Explore mode" / "thinking partner" carves a clear niche tied to the OpenSpec change lifecycle, with distinct triggers ("before or during a change"). Minor overlap risk remains with generic planning or discussion skills, matching anchor 4.

4 / 5

Total

15

/

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

dwmkerr/git-workforest

Path

.claude/skills/openspec-explore/SKILL.md

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.