CtrlK
BlogDocsLog inGet started
Tessl Logo

ship

Plan launch readiness, staged rollouts, production monitoring, rollback, communications, and post-launch validation. Use when the user asks for `/ship`, pre-launch checklists, release readiness, staged rollout plans, feature flags, deployment monitoring, or rollback planning.

75

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A compact, well-organized instruction-only planning skill that assumes Claude's competence and provides specific enumerated guidance. The main gap is that rollout-stage validation gates are implicit rather than explicitly framed as checkpoints.

Suggestions

Make stage-gate validation explicit in the workflow: between rollout steps, add an explicit 'verify guardrails before expanding' checkpoint rather than leaving it implied by the guardrails step.

Add one or two concrete example guardrail thresholds (e.g. error rate < X%, latency within Yms) so the monitoring/rollback decision is copy-paste actionable rather than template-level.

In the Output Pattern, pair 'Rollout stages and entry/exit criteria' with a short inline example of an entry/exit criterion to ground the template.

DimensionReasoningScore

Conciseness

The body is lean — a one-sentence overview, a tight numbered workflow, short output-pattern bullets, and three example prompts — with no explanation of concepts Claude already knows; every section earns its place.

5 / 5

Actionability

Each workflow step lists concrete sub-items (e.g. rollback: "flag disablement, revert path, data repair, comms, owner escalation"), but as a planning template it stops short of copy-paste-ready specifics like example guardrail thresholds; minor gaps keep it below fully executable.

4 / 5

Workflow Clarity

A clear 7-step sequence with an explicit post-launch feedback loop ("compare live metrics... decide whether to continue, pause, expand, or roll back"), but validation gates between rollout stages are implied via guardrails rather than called out as explicit checkpoints.

4 / 5

Progressive Disclosure

Under 50 lines with no need for external references, organized into clearly labeled sections (Overview, Workflow, Output Pattern, Example Prompts), which meets the simple-skill exception for a top score.

5 / 5

Total

18

/

20

Passed

Description

100%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.

A strong, well-structured description that answers what and when with concrete actions and natural trigger terms in third-person imperative voice. No fluff, over-claims, or verbosity to penalize.

DimensionReasoningScore

Specificity

Names six concrete actions — "launch readiness, staged rollouts, production monitoring, rollback, communications, and post-launch validation" — giving comprehensive coverage rather than a single generic verb.

5 / 5

Completeness

Explicitly states both what ("Plan launch readiness, staged rollouts...") and when ("Use when the user asks for `/ship`...") with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Covers natural phrases users would say — `/ship`, "pre-launch checklists", "release readiness", "staged rollout plans", "feature flags", "deployment monitoring", "rollback planning" — including the slash-command synonym and several common variations.

5 / 5

Distinctiveness Conflict Risk

The `/ship` launch-readiness niche is clearly delineated with distinct triggers, creating minimal overlap risk with other skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
eigent-ai/agent-skills
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.