skill-ship

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

Quality

72%

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 ./.claude/skills/skill-ship/SKILL.md

Quality

Content

77%

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

The content is highly actionable with a clear, well-validated multi-phase workflow, but it is monolithic and padded with redundant summary tables that hurt token efficiency and progressive disclosure.

Suggestions

Consolidate or remove redundant summary sections (Quick Reference, The Bottom Line, Red Flags, Safety Measures) that restate the same phase sequence to improve conciseness.

Split large inline templates (lessons capture, delivery summary, audit process) into reference files under references/ and link to them from the body to raise progressive_disclosure.

Move the verbose markdown output templates into a single referenceable block rather than repeating placeholder-heavy templates inline across phases.

Dimension	Reasoning	Score
Conciseness	The body provides real executable bash without explaining known concepts, but is padded with redundant summary sections (Quick Reference, The Bottom Line, Red Flags, Safety Measures, Integration) that restate the same process, matching the 'mostly efficient but could be tightened' anchor. It is not level 3 because of clear redundancy, and not level 1 because it avoids known-concept padding and contains substantial real content.	2 / 3
Actionability	It supplies concrete, copy-paste-ready commands throughout (grep on STATE.md, orchestrate.sh invocation, mkdir/cp archive, git tag, sed with macOS fallback), matching the 'fully executable, specific examples' anchor; it is not level 2 because guidance is complete rather than pseudocode or partial.	3 / 3
Workflow Clarity	The six phases are clearly sequenced with explicit validation checkpoints ('STOP', audit verification, verify archive) and feedback loops (audit failed -> resolve -> rerun), matching the top anchor; validation is present for the destructive/batch steps, so it is not capped at 2.	3 / 3
Progressive Disclosure	No bundle files exist and the ~450-line skill is monolithic in a single file with sections that could be split, matching the 'some structure but content that should be separate is inline' anchor; it is not level 3 because it is not under 50 lines and lacks well-signaled one-level-deep references, and not level 1 because sections are well organized with no nested references.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 states both capability and an explicit trigger in third person, but its action list and trigger variations are narrow, limiting specificity and distinctiveness.

Suggestions

Add concrete sub-actions to the description (e.g., 'run a multi-AI security audit, capture lessons, archive state, and tag a checkpoint') to lift specificity from 2 to 3.

Broaden trigger terms with common variations users would say, such as 'finalize,' 'release,' 'mark as done,' or 'we're done.'

Sharpen the niche phrasing to reduce overlap with generic deliver/release skills, e.g., 'Finalize a completed Claude Octopus project for shipment' rather than 'completed work.'

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Package and finalize completed work for delivery') but 'completed work' is generic and the action list is not comprehensive, matching the anchor for naming a domain and some actions.	2 / 3
Completeness	It explicitly answers both what ('Package and finalize completed work for delivery') and when ('use when a feature is done and ready to ship') with an explicit 'Use when' clause, matching the top anchor; it is not level 2 because the when is explicit rather than implied.	3 / 3
Trigger Term Quality	'use when a feature is done and ready to ship' includes natural phrases users would say, but coverage of common variations is limited, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The delivery/finalization niche is identifiable, but 'completed work for delivery' is moderately generic and could overlap with release or deliver skills, matching the 'somewhat specific but could still overlap' anchor.	2 / 3
	Total	9 / 12 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: .claude/skills/skill-ship/SKILL.md
Commit: 9f39f0c

Reviewed: 2 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.