reference-pack

Reference skill demonstrating the 10/10 skillpack contract. Adds a "what does this skillpack do" answer to the user's agent.

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./examples/skillpack-reference/skills/reference-pack/SKILL.md

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 an efficient, actionable reference: concrete gbrain commands, the ten doctor dimensions, and a publish checklist with a fix loop. It is well-structured with only minor conciseness and validation-gate gaps.

Suggestions

Add an explicit validation gate to the publish workflow (e.g., 'Only run gbrain skillpack pack once doctor --json reports zero core failures').

Trim the parenthetical rationale like '(codex T1 supply-chain hardening)' or move it to a footnote to tighten token efficiency.

Since no bundle files ship with this skill, either add the referenced eval/test files to references/ or clarify in-line that these paths describe a target pack's structure rather than bundled assets.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly on-point, organized into earned sections (artifacts, doctor dimensions, tiers, usage, tests) and assuming competence; only minor spots (e.g. the parenthetical 'codex T1 supply-chain hardening') could be trimmed, fitting 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	Concrete executable commands and specific paths are provided (gbrain skillpack doctor <pack-dir>, --fix --yes, gbrain skillpack info/search, the publish checklist) plus exact dimension names and tier thresholds, with only minor gaps versus fully copy-paste-ready coverage.	4 / 5
Workflow Clarity	The Author's checklist gives a clear doctor-then-pack sequence and the doctor step doubles as a fix-emitting checkpoint, but there is no explicit 'only proceed when doctor passes' gate before pack, leaving a minor validation gap consistent with score 4.	4 / 5
Progressive Disclosure	No bundle files exist and referenced paths describe a pack's expected structure rather than in-skill navigation, but the body is well-organized into clear single-level sections with no nested reference chains, giving good structure with minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

41%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 clear niche but is light on concrete actions and omits an explicit 'Use when' trigger clause, leaning on the separate triggers list for the when. It is distinct but underspecified for self-contained routing.

Suggestions

Add an explicit 'Use when ...' clause to the description naming natural user phrasings (e.g., 'Use when the user asks what a gbrain skillpack is or how third-party packs work').

Replace generic verbs ('demonstrating', 'Adds a ... answer') with concrete actions (e.g., 'Explains the skillpack contract, lists the four required artifacts, and maps the doctor's ten scoring dimensions').

Surface at least one or two natural keywords (skillpack, third-party pack, doctor) directly in the description rather than only in the triggers list.

Dimension	Reasoning	Score
Specificity	The description names the domain ("skillpack contract") but its only actions are generic verbs ("demonstrating", "Adds a ... answer") with no concrete capabilities enumerated, fitting the 'names the domain but actions are minimal' anchor rather than the 1-2 concrete action anchor.	2 / 5
Completeness	It gives a clear 'what' (demonstrates the contract, adds a what-does-it-do answer) but the 'when' is only weakly implied via the separate triggers field and never appears as an explicit 'Use when...' clause, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Natural trigger phrases live only in the frontmatter triggers list, not in the description; the description uses jargon like "10/10 skillpack contract" with one or two generic keywords and is missing the natural phrasings a user would say.	2 / 5
Distinctiveness Conflict Risk	"10/10 skillpack contract" / "reference skillpack" carves a clear niche with distinct triggers and only minor overlap risk with closely related skillpack tooling skills.	4 / 5
	Total	11 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: garrytan/gbrain
Path: examples/skillpack-reference/skills/reference-pack/SKILL.md
Commit: e78f1c3

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.