CtrlK
BlogDocsLog inGet started
Tessl Logo

ideation-sandbox

Safely propose architectural features, unknown unknowns, and brainstorm ideas natively in GitHub Discussions. Triggers: Use this skill when the user asks to brainstorm an architecture change, proposes a highly exploratory / undefined technical idea, or as auto-fire trigger for §5.2 Step 2.5 Architectural Step-Back on high-blast-radius proposals before [RESOLVED_TO_AC] / [GRADUATED_TO_TICKET] graduation.

64

Quality

76%

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 ./.agents/skills/ideation-sandbox/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 extremely lean, well-structured progressive-disclosure router that correctly delegates bulk detail to a real reference file. Its weakness is that the body itself carries almost no actionable or workflow content — all substantive guidance and validation checkpoints live in the deferred reference.

Suggestions

Add a brief 2-4 line inline overview summarizing the ideation lifecycle (propose in a Discussion → iterative PR-depth review → graduate) so the body is useful without forcing a file read.

Surface the key validation gate (e.g., the mandatory pre-authoring precedent sweep / Gate 0) directly in the body so the destructive/batch discussion operations have an explicit checkpoint before delegation.

Give at least one concrete executable example in the body (e.g., the `create_discussion` call with the Ideas category) so the body is actionable on its own, not only a redirect.

DimensionReasoningScore

Conciseness

The body is a maximally lean two-sentence router with no padding and no explanation of concepts Claude already knows; every token earns its place, matching the lean/efficient anchor.

5 / 5

Actionability

It gives one concrete executable instruction ("use the `view_file` tool to read" a specific path), but all substantive guidance is deferred to the reference file, leaving the key details of the actual ideation workflow missing from the body.

3 / 5

Workflow Clarity

Only a rough "read the file, then proceed" sequence is present with no validation checkpoints in the body, and the real multi-step workflow (involving discussion create/update operations) is entirely deferred, so it cannot exceed the 3 cap for missing validation in destructive/batch operations.

3 / 5

Progressive Disclosure

SKILL.md acts as a clear router to a single, real, one-level-deep reference (ideation-sandbox-workflow.md, verified present) that is explicitly signaled, but it provides no inline overview/summary of what the reference contains, which keeps it just below the well-signaled-overview 5.

4 / 5

Total

15

/

20

Passed

Description

83%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 strong: it clearly states what the skill does and when to use it, with concrete trigger phrases and a well-scoped niche. Its main weakness is a few user-natural trigger synonyms missing alongside internal jargon, and slight overlap risk from the generic "brainstorm ideas" wording.

Suggestions

Add user-natural trigger synonyms (e.g., "explore an architectural idea", "spike out a design", "think through a risky change") alongside the internal §5.2/high-blast-radius markers.

Tighten the generic "brainstorm ideas" phrasing to tie it explicitly to architectural/exploratory proposals so it is less likely to fire for general brainstorming requests.

Consider trimming the internal graduation markers ([RESOLVED_TO_AC]/[GRADUATED_TO_TICKET]) from the user-facing description or moving them to a separate auto-fire note, since they are jargon a user would not naturally say.

DimensionReasoningScore

Specificity

Names the domain (architectural ideation in GitHub Discussions) and lists several concrete actions — "propose architectural features, unknown unknowns, and brainstorm ideas" — with only minor coverage gaps, fitting the anchor for several specific actions rather than the comprehensive 5.

4 / 5

Completeness

Explicitly answers both "what" (propose features, surface unknown unknowns, brainstorm in GitHub Discussions) and "when" via a "Triggers: Use this skill when..." clause with multiple concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural user phrases such as "brainstorm an architecture change" and "brainstorm ideas", but internal markers like "§5.2 Step 2.5" and "high-blast-radius" are jargon rather than user-natural terms, leaving a few natural synonyms missing.

4 / 5

Distinctiveness Conflict Risk

Carves a distinct niche (GitHub Discussions architectural ideation gated by [RESOLVED_TO_AC]/[GRADUATED_TO_TICKET]), but the broad "brainstorm ideas" phrasing creates minor overlap risk with general ideation skills, so it sits below the minimal-conflict 5.

4 / 5

Total

17

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
neomjs/neo
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.