skill-ship

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

Quality

70%

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

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 highly actionable with a well-validated, clearly sequenced workflow, but it is verbose and monolithic. Removing redundant restatements and splitting long reference material into bundle files would improve both conciseness and progressive disclosure.

Suggestions

Collapse the repeated workflow summaries (Quick Reference, The Bottom Line, Core principle) into a single canonical sequence to cut ~100+ lines of redundancy.

Merge the Safety Measures and Red Flags tables, which cover the same prohibitions from two angles.

Move the full audit/lessons templates or the per-phase bash scripts into references/ files and link to them, so SKILL.md stays an overview and progressive disclosure can score higher.

Dimension	Reasoning	Score
Conciseness	The ~471-line body restates the same six-step workflow at least four times (Core principle, The Process, Quick Reference table, The Bottom Line) and the Safety Measures and Red Flags tables overlap heavily, so while content is mostly useful it could be tightened considerably.	3 / 5
Actionability	It supplies concrete, executable bash (grep, sed, git tag, mkdir, cp) with real paths, but the lessons heredoc interpolates undefined variables like ${USER_WHAT_WENT_WELL} that would expand to empty, leaving a minor execution gap.	4 / 5
Workflow Clarity	Six phases are explicitly sequenced with validation checkpoints (STOP on not-ready, verify audit file exists, ls the archive), feedback loops (audit failed → fix → re-run), and an error-handling table, matching the anchor for clear sequence with explicit validation and recovery.	5 / 5
Progressive Disclosure	No bundle files exist and the entire skill is one ~471-line SKILL.md with good section headers but no file splitting or one-level-deep references, fitting the anchor for some structure with content that should be separate kept inline.	3 / 5
	Total	15 / 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 cleanly pairs a what with an explicit when and uses natural trigger language, but its capability statement is somewhat generic. Tightening "completed work" into concrete deliverables would lift specificity and completeness.

Suggestions

Replace the generic "completed work" with concrete deliverables (e.g., "archive STATE.md/PROJECT.md, run Multi-AI audit, tag a git checkpoint") to raise specificity.

Add the missing natural synonyms ("deliver", "finalize", "complete the project") to the description's trigger phrasing so the frontmatter alone covers common user phrasings.

Dimension	Reasoning	Score
Specificity	"Package and finalize completed work for delivery" names the domain and two concrete actions (package, finalize), but "completed work" stays generic and offers no concrete artifacts, matching the anchor that names 1-2 actions without comprehensive coverage.	3 / 5
Completeness	It 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, but the "what" is less concrete than the anchor-5 example, so it sits at 4 rather than 5.	4 / 5
Trigger Term Quality	The phrase "use when a feature is done and ready to ship" surfaces natural terms ("done", "ready to ship", "ship") users would say, but omits common synonyms like "deliver", "finalize", or "complete the project" that the body's own trigger section lists.	4 / 5
Distinctiveness Conflict Risk	The shipping/finalization niche is mostly distinct with a clear "ready to ship" trigger, but it carries minor overlap risk with closely related deliver/complete skills referenced in the body, keeping it just below the minimal-conflict anchor 5.	4 / 5
	Total	15 / 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: nyldn/claude-octopus
Path: .claude/skills/skill-ship/SKILL.md
Commit: f9b8c92

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.