CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sy-brainstorm

Analyze options and trade-offs before traceable work is ready, without pretending exploration is a plan. Use when the user wants options, alternatives, decision matrices, or a bounded ideation pass before trace planning.

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 is well-structured with an exemplary validation-first workflow and clean progressive disclosure into a real bundle. Its weak point is actionability: the orchestration mechanics are precise, but the skill never specifies what brainstorm work to perform or the actual commands to run, so Claude must infer the substantive steps.

Suggestions

Define what "the work owned by brainstorm" concretely consists of (e.g., generate N options per dimension, score trade-offs, produce a decision matrix) or point to where that method is defined.

Name the actual validation commands (e.g., the specific plugin validation and SDK proof commands the repository wrapper exposes) instead of referring to them descriptively.

Include a minimal example of a stage-result artifact showing the required fields in use, and remove the duplicated "When to use" section or the stray empty line under the Gotchas header to tighten conciseness.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — no concept explanations, terse lists throughout. It is not a 5 because "When to use" duplicates the frontmatter description verbatim, handoff guidance repeats across Procedure step 5, Validation, and the Handoff section, and the Gotchas section has a stray empty header block.

4 / 5

Actionability

Stage mechanics are concrete — named artifact fields ("schema_version, stage, status, evidence_refs, blocked_by, next_stage"), explicit status values ("pass, fail, blocked, or not_checked"), and routing rules. But key executable details are missing: no actual validation commands ("run plugin validation and SDK proof commands from the repository wrapper" names no commands), no example stage-result artifact, and the core brainstorm work itself ("Perform only the work owned by brainstorm") is never defined, leaving the guidance incomplete.

3 / 5

Workflow Clarity

The five-step procedure is clearly sequenced, and the Validation section adds an explicit fail-fast checkpoint ("stop at the first failed required gate") with a feedback loop ("do not proceed to downstream stages until the failure is resolved or explicitly waived"). The Failure modes section maps each error class to a concrete recovery action ("block and request or create the required artifact through the owning stage"), matching the top anchor's validation steps, feedback loops, and error-recovery coverage.

5 / 5

Progressive Disclosure

The body is a concise overview, and the References section points to four clearly labeled, one-level-deep files (contract, evals, task profile, source context) that all exist in the references/ bundle. Detailed contract material (preconditions, exit criteria, rollback) lives in contract.yaml rather than being inlined, matching the top anchor for well-signaled navigation.

5 / 5

Total

17

/

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 is strong: it pairs a clear, scoped statement of what the skill does with an explicit "Use when" trigger clause containing natural terms. Its main weaknesses are limited action enumeration and missing common synonyms (especially "brainstorm") that would sharpen both trigger matching and distinctiveness.

Suggestions

Add "brainstorm" and related natural synonyms (e.g., "explore approaches", "compare choices") to the "Use when" trigger clause, since users asking for a brainstorm would not say "bounded ideation pass".

Enumerate the concrete outputs of the analysis (e.g., "produce an options list with trade-offs and a recommended decision matrix") to raise specificity beyond the current 1-2 named actions.

Clarify the lifecycle scope in the trigger (e.g., "within SynAIpse trace lifecycle work") to reduce overlap with generic ideation requests.

DimensionReasoningScore

Specificity

"Analyze options and trade-offs" names the domain with one to two concrete actions, but the description does not comprehensively enumerate what the analysis produces (e.g., decision matrices output format, comparison deliverables). It matches the anchor "Names domain and 1-2 concrete actions, but not comprehensive" rather than 4, which requires several listed specific actions.

3 / 5

Completeness

It clearly answers both: the what is "Analyze options and trade-offs before traceable work is ready, without pretending exploration is a plan" and the when is an explicit "Use when the user wants options, alternatives, decision matrices, or a bounded ideation pass before trace planning" with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

"options, alternatives, decision matrices, or a bounded ideation pass" are natural user phrases with good coverage. It falls short of 5 because common synonyms are missing — notably "brainstorm" itself (the skill name), plus "explore approaches" or "compare choices" — while "trace planning" is lifecycle jargon rather than a user-said term.

4 / 5

Distinctiveness Conflict Risk

The pre-trace-planning lifecycle framing carves out a distinct niche with minimal conflict against adjacent stage skills. It stays below 5 because generic "options/alternatives" triggers could pull it in for ordinary comparison or brainstorming requests outside the SynAIpse lifecycle.

4 / 5

Total

16

/

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

jscraik/Agent-Skills

Path

Plugins/synaipse-harness/skills/sy-brainstorm/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.