Tessl • The management layer for AI agent skills

The body is an exemplary executable release runbook: concrete commands throughout, rigorous validation gates for the two irreversible operations, and clear sequencing. The only weak spot is progressive disclosure — it is a long monolithic file that could split reference material into bundle files.

Dimension	Reasoning	Score
Conciseness	The ~166-line body is dense with executable commands and assumes Claude's competence (no explanations of crates, semver, or git), but a few asides and the dual jj/git repetition leave minor instances that could be trimmed, fitting the 4 anchor better than 5.	4 / 5
Actionability	Every step ships copy-paste-ready shell commands (e.g., `cargo publish --dry-run`, `gh pr checks <pr> --watch --interval 30`, `gh release create v<new> ...`) with jj/git variants covering the common cases.	5 / 5
Workflow Clarity	A clear 9-step sequence with explicit, named validation gates (merge gate, publish gate, dry-run pre-flight) and error-recovery feedback loops ("If any check fails: stop, report the failing check, and do not merge"), satisfying the 5 anchor and the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and no nested references, but it is a single long file with no bundle files; content like the provider-seams table and pitfalls could be externalized, so it does not reach the 5 anchor's clear one-level-deep reference structure.	4 / 5
	Total	18 / 20 Passed

Description

70%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, third-person, and occupies a clearly distinct niche, but it lacks an explicit "Use when..." trigger clause, which caps its completeness. Adding a brief trigger sentence would lift completeness toward 5.

Suggestions

Append a "Use when..." clause naming the natural trigger phrases (e.g., "Use when the user asks to cut a release, bump the crate version, or publish to crates.io").

Mention "version bump" / "bump the crate version" as a trigger synonym to broaden trigger-term coverage toward 5.

Optionally name the forge-tagging step so the action list more comprehensively reflects the full release scope.

Dimension	Reasoning	Score
Specificity	"Cut a release of a Rust crate and publish to crates.io, with externally-gated merge and publish steps" names several concrete actions (cut release, publish to crates.io, gated merge, gated publish); falls short of 5 because it omits sub-actions like version bumping and forge tagging.	4 / 5
Completeness	The "what" is clear but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3; the "when" is only weakly implied by the domain.	3 / 5
Trigger Term Quality	Natural terms users would say are present ("release", "Rust crate", "crates.io", "publish"); missing common variations like "bump version" or "version bump", so it sits at 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	"Release of a Rust crate and publish to crates.io" is a clear, narrow niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: imbue-ai/offload
Path: .agents/skills/release-to-crates/SKILL.md
Revision: 6998230

Reviewed: 1 month ago

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.

release-to-crates

Table of Contents

Is this your skill?