packet-factory

Creates, reviews, and dispatches atomic work packets. Every task with a side effect requires an APPROVED packet before execution. Scope is immutable after approval — expansion requires a new packet.

Quality

66%

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/jason-my-claw-is-the-law-deebee-4567b4/skills/packet-factory/SKILL.md

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise, actionable, and well-structured for a simple skill, with concrete executable commands. The main gap is the lack of an explicit validation/feedback checkpoint in the dispatch workflow, which caps workflow clarity.

Suggestions

Add an explicit validation step before dispatch (e.g., confirm the packet is APPROVED and verify scope is locked) and a feedback loop for what to do if dispatch fails.

Document the criteria the review step uses to choose APPROVED vs REJECTED so the workflow has a clear decision checkpoint.

Specify how dispatch output is verified/logged after execution to close the feedback loop on this side-effecting operation.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized into tight operational sections with concrete commands, assuming Claude's competence; the single motivational line still earns its place, matching the score-3 anchor.	3 / 3
Actionability	The Commands section provides fully executable shell commands with real flags and concrete example arguments (intent, source, destination, id), matching the score-3 copy-paste-ready anchor.	3 / 3
Workflow Clarity	The create→review→dispatch sequence is present, but dispatch is a side-effecting operation with no explicit validation checkpoint or error-recovery feedback loop, so workflow clarity is capped at 2 per the destructive-operations guideline.	2 / 3
Progressive Disclosure	At under 50 lines with no need for external references, the skill qualifies for the simple-skill exception and is organized into clear sections (Commands, Packet Queue, Scope Lock Rule), matching the score-3 anchor.	3 / 3
	Total	11 / 12 Passed

Description

45%

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 concrete about actions but relies on internal jargon with no natural trigger terms or "Use when…" guidance, capping both completeness and distinctiveness. Adding an explicit trigger clause using user-facing language would raise the weaker dimensions.

Suggestions

Add an explicit "Use when…" clause stating when Claude should invoke this skill (e.g., before performing any task with side effects).

Replace internal jargon ("atomic work packets", "scope is immutable") with natural user-facing language so the description triggers on phrases users actually say.

Clarify the trigger conditions in plain terms to reduce overlap with other operational/gating skills.

Dimension	Reasoning	Score
Specificity	"Creates, reviews, and dispatches atomic work packets" lists multiple concrete actions, matching the score-3 anchor listing several specific actions.	3 / 3
Completeness	It clearly states what the skill does but lacks any explicit "Use when…" clause or trigger guidance, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Terms like "atomic work packets", "side effect", and "scope is immutable" are internal operational jargon rather than language a user would naturally say; no "Use when…" trigger phrases are present, matching the score-1 jargon anchor.	1 / 3
Distinctiveness Conflict Risk	The packet-gating niche is somewhat specific, but the broad "task with a side effect" framing and absence of distinct natural triggers means it could still overlap with other operational skills, matching the score-2 anchor.	2 / 3
	Total	8 / 12 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: open-gitagent/opengap
Path: examples/jason-my-claw-is-the-law-deebee-4567b4/skills/packet-factory/SKILL.md
Commit: d7a8e2e

Reviewed: 4 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.