skill-ship

Package and finalize completed work for delivery — use when a feature is done and ready to ship

Quality

68%

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 ./skills/skill-ship/SKILL.md

Quality

Content

70%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 a well-sequenced, highly actionable shipping workflow with genuine validation checkpoints and error-recovery paths — its strongest asset. It is let down by token-inefficient repetition across summary tables and by a monolithic structure with no progressive disclosure: everything lives inline and the only referenced file is an unresolvable path.

Suggestions

Collapse "Safety Measures", "Red Flags - Never Do", and "The Bottom Line" into the Error Handling table or a single short checklist — they restate the same rules three times.

Move the detailed phase-by-phase bash blocks or the completion/summary templates into a references/ file (e.g. references/ship-process.md), keeping SKILL.md as a lean overview — this also fixes the missing-bundle structure.

Replace the unresolved skills/blocks/codex-host-adapter.md path with an explicit, well-signaled reference or inline the few host-adaptation rules needed, and define the ${USER_*} placeholders so the LESSONS.md append block is directly executable.

Dimension	Reasoning	Score
Conciseness	The body is mostly commands rather than concept explanation, but it carries clear padding: "Safety Measures", "Red Flags - Never Do", "Quick Reference", and "The Bottom Line" repeat the same prohibitions and steps, and the "MANDATORY COMPLIANCE" block is emphatic filler. This matches anchor 3 — mostly efficient but could be tightened — rather than 4 given several redundant sections.	3 / 5
Actionability	Concrete, largely executable bash throughout, e.g. the orchestrate.sh invocation, archive mkdir/cp sequence, and git tag creation, with a portability fallback for sed -i. Minor gaps keep it below anchor 5: unsubstituted placeholders like ${USER_WHAT_WENT_WELL} and {score}, an assumed git repository, and brittle grep patterns such as "^\- \[x\]".	4 / 5
Workflow Clarity	Six phases are clearly sequenced with explicit STOP checkpoints, dedicated validation steps (readiness check, "Verify Audit Completed" via find on the validation file, "Verify Archive" via ls), and feedback loops ("Resolve issues and run /octo:ship again") plus an error-handling table. This matches anchor 5 — explicit validation steps and error-recovery loops.	5 / 5
Progressive Disclosure	The ~450-line body is monolithic with no bundle files at all: no references/, scripts/, or assets/ exist, and the single mentioned file, skills/blocks/codex-host-adapter.md, is buried in a host note and does not resolve. Structure exists (clear section headers), matching anchor 3 rather than 4, since consolidatable tables (Error Handling / Safety Measures / Red Flags) are inlined and the one reference is not clearly signaled.	3 / 5
	Total	15 / 20 Passed

Description

66%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 cleanly pairs a what with an explicit, natural-sounding when clause. Its main weakness is a generic what — packaging/finalizing — that omits the skill's distinctive deliverables (multi-AI audit, lessons capture, archival, rollback checkpoint), which both blunts specificity and raises overlap risk with other delivery-oriented skills.

Suggestions

Enumerate the concrete deliverables in the description, e.g. "Runs a pre-ship security audit, captures lessons, archives project state, and creates a rollback checkpoint."

Add trigger synonyms users actually say, such as "we're done", "finalize this", or "deliver the project", to widen natural invocation coverage.

Sharpen distinctiveness by naming the delivery-validation niche (e.g. mention it is the final ship step after development) so it does not compete with generic build or release packaging skills.

Dimension	Reasoning	Score
Specificity	"Package and finalize completed work for delivery" names the delivery domain and two actions (package, finalize) but mentions none of the concrete deliverables (security audit, lessons capture, archive, checkpoint). It fits anchor 3 — 1-2 concrete actions, not comprehensive — rather than 4, which requires several specific actions.	3 / 5
Completeness	Both a what ("Package and finalize completed work for delivery") and an explicit when ("use when a feature is done and ready to ship") are present. The what is thinner than anchor 5's concrete multi-action description, matching anchor 4: both present, when could be more specific.	4 / 5
Trigger Term Quality	"use when a feature is done and ready to ship" includes natural phrases users would say, but misses common synonyms like "we're done", "deliver", or "finalize". Good coverage with a few natural terms missing matches anchor 4, not 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	"Package and finalize... for delivery" is somewhat specific to shipping but overlaps with generic release, build, and finalize-type skills. Anchor 3 (somewhat specific, overlap risk with similar skills) fits better than 4, since the trigger is not narrowly distinct.	3 / 5
	Total	14 / 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: nyldn/claude-octopus
Path: skills/skill-ship/SKILL.md
Commit: 0093dab

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.