CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gooo-review-service-grants

Review service-grant narrowing proposals with Gooo for one required request or an ordered list, and select eligible candidates by a supplied preference. Use for supported service-pattern reviews through the native Go command or connected MCP tools.

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 highly actionable with copy-paste commands, exact schemas, and worked JSON examples, and its workflow includes explicit error/validation checkpoints for per-proposal batch assessment. Its weakest point is conciseness: repeated negative guidance and inline time-sensitive version chatter (Go 1.27.3, preview.13/16) inflate the token cost without adding proportional clarity.

Suggestions

Consolidate the scattered 'do not invent / preserve explicitly requested' prohibitions into one short 'Guardrails' list instead of repeating them in each section.

Move the version-sensitive material (Go 1.27.3 pin, preview.13 vs preview.16 MCP behavior, pinned commit hashes) into a clearly labeled 'Version notes' or 'Old patterns' section so the main workflow stays durable and lean.

Add a short numbered step sequence at the top (choose path → discover tool → assess per proposal → report result) so the workflow order is explicit rather than implied by section headings.

DimensionReasoningScore

Conciseness

The body avoids known-concept filler and is information-dense, but repeats prohibitions across sections ('do not invent', 'preserve an explicitly requested') and carries time-sensitive version details ('Go 1.27.3', 'preview.13', 'preview.16', pinned commit hashes) inline rather than in a deprecated/old-patterns section. Mostly efficient but could be tightened, matching anchor 3.

3 / 5

Actionability

Fully executable guidance: a pinned copy-paste 'go run ...@v0.0.0-20261022032513-52fb59a8ca9a' command, exact JSON payloads for both tools with expected decisions ('ELIGIBLE', 'REFUSED with REQUIRED_REQUEST_REMOVED'), and exact input schemas ('exactly four strings: before, after, required_type, and required_name'). Specific examples cover the common single-request and ordered-list cases — anchor 5.

5 / 5

Workflow Clarity

A clear sectioned sequence (choose execution path, discover the tool, assess each proposal, preserve and report the result) with explicit validation checkpoints for batch assessment — 'A nonzero exit supplies no policy result on stdout', 'report its first diagnostic, without a partial proof or a guessed decision', plus a recovery guide link. Not anchor 5 because the sequence is implicit in section order rather than explicit steps with feedback loops.

4 / 5

Progressive Disclosure

No bundle files exist, and the body is well organized with detail deferred to one-level-deep linked guides (native recovery guide, connection/setup guides, host application example). Minor gaps: version-specific MCP details (preview.13/preview.16 behavior) are inlined rather than split into a separate reference, so anchor 4 rather than 5.

4 / 5

Total

16

/

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 specific and distinctive with an explicit 'Use for...' clause covering both what the skill does and when to use it. Its main weakness is a somewhat circular 'when' clause and missing natural trigger variations, which keeps completeness and trigger quality at 4 rather than 5.

DimensionReasoningScore

Specificity

Names several concrete actions — 'Review service-grant narrowing proposals', 'select eligible candidates by a supplied preference' — plus the transports ('native Go command or connected MCP tools'). Fits anchor 4 rather than 3 because it goes beyond 1-2 generic actions, but not 5 since coverage of what the review produces is incomplete.

4 / 5

Completeness

Answers 'what' clearly (review proposals, select candidates) and includes an explicit 'Use for...' trigger clause ('Use for supported service-pattern reviews through the native Go command or connected MCP tools'). The 'when' is present but slightly circular ('supported service-pattern reviews' mirrors the skill's own activity), so it does not reach anchor 5's concrete trigger phrases.

4 / 5

Trigger Term Quality

Contains natural niche terms users would say — 'service-grant', 'narrowing proposals', 'eligible candidates', 'preference', 'MCP tools', 'native Go command'. Good keyword coverage, though common variations like 'assess' or 'permission review' are missing, so not anchor 5.

4 / 5

Distinctiveness Conflict Risk

A highly specific niche — Gooo service-grant narrowing with named tools and selection semantics — with distinct triggers and virtually no overlap risk with other skills. Clear match to anchor 5.

5 / 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

kimjooyoon/gooo-go-ports

Path

.agents/skills/gooo-review-service-grants/SKILL.md

Revision

69c7ea0

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill