CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

shipping-and-launch

Prepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.

Quality

86%

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

The canonical home for this skill is shipping-and-launch in addyosmani/agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

73%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 strong, checklist-centric skill body with excellent sequencing, explicit validation gates, and concrete decision thresholds. Its main weaknesses are the inlined generic React/Express error-reporting code and inline checklists that overlap with the external reference files, which cost both conciseness and structural cleanliness.

Suggestions

Replace the full ErrorBoundary and Express error-middleware code blocks with a short snippet or a pointer to the error-reporting pattern, keeping only the project-specific reportError payload fields.

Move the detailed Security, Performance, and Accessibility checklist sections into their already-referenced files (../../references/security-checklist.md, etc.) and keep only a one-line summary per area in SKILL.md to cut duplication and length.

Tighten the Overview to a single sentence of intent; the 'reversible, observable, and incremental' principle is already enforced by the checklists that follow.

DimensionReasoningScore

Conciseness

The checklist-driven body is mostly efficient, but the ~40 lines of standard ErrorBoundary and Express error-middleware code ('class ErrorBoundary extends React.Component', 'app.use((err: Error, req: Request, res: Response, next: NextFunction)') re-explain patterns Claude already knows, and the motivational Overview prose ('Ship with confidence... Every launch should be reversible, observable, and incremental') could be trimmed.

3 / 5

Actionability

Largely concrete: a specific decision-threshold table ('Error rate | Within 10% of baseline | 10-100% above baseline | >2x baseline'), concrete rollout percentages ('5% -> 50% -> 100%'), and a copy-paste rollback command ('git revert <commit> && git push'). Minor gaps: the feature-flag and error-reporting snippets depend on undefined helpers (getFeatureFlags, reportError) and the rollback plan uses template placeholders.

4 / 5

Workflow Clarity

The rollout sequence is explicitly numbered with monitoring checkpoints and hold/advance windows at every stage ('24-48 hour monitoring window', 'Advance only if all thresholds pass'), plus a thresholds table, immediate rollback triggers, and post-launch verification steps — validation feedback loops are everywhere.

5 / 5

Progressive Disclosure

Sections are well-organized with a clearly signaled one-level-deep 'See Also' ('see ../../references/security-checklist.md', 'see ../../references/performance-checklist.md'). No bundle files exist in this directory to verify those paths, and the inline Security/Performance/Accessibility checklists appear to duplicate content in the referenced files, which is a minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

91%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 well-crafted description in third person with explicit what and when clauses, natural trigger synonyms, and a clear production-launch niche. Its only weakness is that the capability statement is a single brief verb phrase with the concrete deliverables implied through the trigger clauses rather than stated directly.

DimensionReasoningScore

Specificity

It lists several concrete items — 'pre-launch checklist', 'setting up monitoring', 'staged rollout', 'rollback strategy' — though these are framed as trigger scenarios rather than parallel capability statements, and the sole explicit action ('Prepares production launches') is brief, so it sits just below the comprehensive level.

4 / 5

Completeness

Explicitly answers both questions: 'Prepares production launches' states the what, and multiple 'Use when...' clauses ('preparing to deploy to production', 'asking what needs to be in place before shipping', 'planning a staged rollout') give concrete trigger phrases.

5 / 5

Trigger Term Quality

Excellent natural-term coverage with synonyms users would actually say: 'deploy to production', 'shipping', 'pre-launch checklist', 'staged rollout', 'rollback strategy' — covering launch/ship/deploy/rollout variants comprehensively.

5 / 5

Distinctiveness Conflict Risk

The production-launch niche ('pre-launch checklist', 'rollback strategy') is distinct, but the deploy/monitoring territory could minorly overlap with a generic deployment or observability skill, so it is mostly rather than fully distinct.

4 / 5

Total

18

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

faisalbasra/match-storyteller

Path

.agents/skills/shipping-and-launch/SKILL.md

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.