CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gsd-explore

Socratic ideation and idea routing — think through ideas before committing to plans

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./pi/package-skills/gsd-explore/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 an efficient, well-structured Pi-dispatch wrapper that adds only environment-specific knowledge Claude would lack, with concrete dispatch mechanics and explicit fail-closed error handling. Its main gaps are the absence of a worked gsd_dispatch call example and a single external reference expressed as a non-resolvable template placeholder.

DimensionReasoningScore

Conciseness

The body is lean and every sentence carries Pi-specific facts Claude would not know (no subagent API, gsd_dispatch semantics, @path non-expansion, fail-closed behavior). There is no padding or explanation of concepts Claude already knows, matching 'Lean and efficient; assumes Claude's competence; every token earns its place.'

5 / 5

Actionability

Concrete, executable guidance is present: call gsd_dispatch with role and task, translate Agent(...) steps to role/prompt, STOP on unresolved roles or child failure, and read execution_context files first with explicit optional/required failure branches. It falls short of 5 because there is no worked example of an actual gsd_dispatch call, and the real workflow lives behind a placeholder path.

4 / 5

Workflow Clarity

The sequence is clear (read execution_context files 'before doing anything else', then execute the workflow, dispatching roles via gsd_dispatch) with explicit fail-closed checkpoints and decision branches for optional vs. required steps. Not 5 because there is slight ordering tension between the opening 'Invoke this Pi skill' line and the 'Before doing anything else' read-first instruction, and the actual step sequence is delegated entirely to the external workflow file.

4 / 5

Progressive Disclosure

For a short skill with no bundle files present, the body is well organized with bold section markers and XML tags, and the single reference is clearly signaled one level deep under <execution_context>. Not 5 because that reference is an unresolved placeholder path (@__GSD_PI_ENGINE_ROOT__/gsd-core/workflows/explore.md) that cannot be verified as a real file in the bundle.

4 / 5

Total

17

/

20

Passed

Description

50%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 identifies a distinctive concept (Socratic ideation and idea routing) but stays at the level of abstract labels. It lacks an explicit 'Use when' trigger clause and natural trigger phrases, and never enumerates the concrete actions the skill actually performs, leaving both completeness and specificity at the midpoint.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to brainstorm, explore, or think through an idea before committing to a plan.'

Enumerate concrete actions instead of abstract labels, e.g. 'guides the developer through probing questions, optionally spawns research, and routes outputs to notes, todos, seeds, requirements, or new phases.'

Include natural synonyms users would say (brainstorm, explore an idea, refine an idea) to improve trigger term coverage and distinctiveness from generic planning skills.

DimensionReasoningScore

Specificity

The description names the domain plus two activities ("Socratic ideation and idea routing") but these are abstract labels rather than concrete actions like asking probing questions, spawning research, or routing outputs to notes/todos/requirements. It matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' rather than 2 (a domain is named with specific activities) or 4 (several specific actions are not listed).

3 / 5

Completeness

The 'what' is stated (Socratic ideation and idea routing) but the 'when' is only weakly implied by the tagline 'think through ideas before committing to plans'; there is no explicit 'Use when...' clause, which per the judging guidelines caps completeness at 3. Not 4 because the trigger condition is never made explicit.

3 / 5

Trigger Term Quality

Phrases like "think through ideas" and "before committing to plans" are natural, but coverage is thin — no synonyms like brainstorm, explore, or refine, no 'Use when' phrasing, and 'Socratic ideation'/'idea routing' lean technical. This fits 'Some relevant keywords but missing common variations or synonyms' rather than 4's 'Good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

'Socratic ideation' carves out a niche, but without explicit trigger phrases the description could overlap with generic brainstorming, planning, or explore-style skills. Fits 'Somewhat specific but could still overlap with similar skills' rather than 4, which requires mostly distinct triggers.

3 / 5

Total

12

/

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

open-gsd/gsd-core

Path

pi/package-skills/gsd-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.