CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-ship

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

58

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-ship/SKILL.md
SKILL.md
Quality
Evals
Security

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 skill body is a strong executable workflow: every step has concrete commands, validation checkpoints, and STOP gates, and the error-handling and rollback coverage is exemplary. Its weaknesses are repetition — four separate summary sections restate the same phase list — and complete absence of progressive disclosure, with 470 lines of monolithic content where secondary tables and integration details belong in reference files.

Suggestions

Split secondary material into one-level-deep reference files (e.g., references/error-handling.md, references/integration.md) and keep SKILL.md to the phase workflow with well-signaled links, reducing the main file to roughly 200-250 lines.

Collapse "Red Flags", "Safety Measures", "Quick Reference", and "The Bottom Line" into a single compact checklist — they restate the phase steps nearly verbatim and cost tokens without adding guidance.

Fix the pseudo-executable fragments: wire the ${USER_*} placeholders in the LESSONS.md heredoc to captured variables, note that ${codex_status} must be substituted into the displayed markdown, and replace the sed -i '' portability fallback with a single portable invocation.

DimensionReasoningScore

Conciseness

The body is mostly concrete instruction with no explanations of concepts Claude already knows, but it carries several padded, redundant sections — "Red Flags", "Safety Measures", "Quick Reference", and "The Bottom Line" largely restate the phase steps, and the shouty "MANDATORY COMPLIANCE" block adds emphasis rather than information. This fits anchor 3 (could be tightened) better than anchor 4 given the volume of repetition.

3 / 5

Actionability

Every phase ships concrete, mostly copy-paste-ready bash with real error handling (grep with || echo fallbacks, sed -i variant fallback, find -mmin validation check). Minor gaps keep it at anchor 4 rather than 5: ${codex_status} appears unexpanded inside a markdown block, the ${USER_*} placeholders in the heredoc are never wired to actual variables, and the sed -i '' portability dance is under-explained.

4 / 5

Workflow Clarity

Six explicitly numbered phases with STOP checkpoints, a ready-state gate before any destructive action, audit-completion verification (find for the validation file), and feedback loops on failure ("Resolve issues and run /octo:ship again"), plus an error-handling matrix. This matches anchor 5 (clear sequence, explicit validation, feedback loops) — destructive/batch operations are fully gated with validation.

5 / 5

Progressive Disclosure

The file is well-sectioned with clear headers, but it is a fully monolithic 470-line SKILL.md with no references/, scripts/, or assets/ bundle; everything including the error-handling, safety, and integration tables is inlined. That fits anchor 3 (structure present, content that should be separate is inline) rather than anchor 4, since secondary material clearly belongs in one-level-deep reference files.

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 is concise, uses third-person voice, and clearly pairs a what-clause with a use-when clause — solid fundamentals. It undersells the skill's actual capabilities (Multi-AI audit, lessons capture, archival, rollback checkpoints) and its triggers are limited to a narrow ship/done vocabulary, slightly raising conflict risk with other delivery-oriented skills.

Suggestions

Enumerate the concrete actions the skill performs, e.g., "Package completed work for delivery: run a Multi-AI security audit, capture lessons learned, archive project state, and create a rollback checkpoint. Use when the user says ship, deliver, finalize, we're done, or ready to ship."

Broaden trigger coverage with the natural synonyms users say ("wrap up", "release", "finish the project", "mark as shipped") to reduce missed invocations.

Add a distinguishing qualifier (e.g., "for Claude Octopus projects with an .octo/ directory") to lower conflict risk with generic delivery or deploy skills.

DimensionReasoningScore

Specificity

"Package and finalize completed work for delivery" names the domain and two concrete actions (package, finalize), but omits the skill's other core capabilities (security audit, lessons capture, archive, checkpoint). This matches anchor 3 (1-2 concrete actions, not comprehensive), not anchor 4 which requires several listed actions.

3 / 5

Completeness

Both what ("Package and finalize completed work for delivery") and when ("use when a feature is done and ready to ship") are explicitly stated, meeting anchor 4. The when-clause is a single condition and could be more specific with additional concrete trigger phrases, keeping it below anchor 5.

4 / 5

Trigger Term Quality

Includes natural user phrases like "done", "ready to ship", "ship", and "delivery" that users would genuinely say. A few natural variations are missing (e.g., "wrap up", "release", "finish the project"), so it fits anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

"Finalize completed work" is somewhat generic and could overlap with delivery, deploy, or code-review skills; the "ship" framing adds distinctness but doesn't establish a clearly unique niche. Fits anchor 3 (somewhat specific, overlap risk remains) better than anchor 4.

3 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
nyldn/claude-octopus
Reviewed

Table of Contents

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.