CtrlK
BlogDocsLog inGet started
Tessl Logo

deployment-procedures

Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts.

38

Quality

36%

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 ./plugins/antigravity-bundle-devops-cloud/skills/deployment-procedures/SKILL.md

The canonical home for this skill is deployment-procedures in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

31%Scale 1-5

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

This skill reads as a general deployment knowledge base that restates widely-known DevOps principles Claude already understands. It lacks concrete, executable guidance — no actual commands, config snippets, or platform-specific procedures — while explicitly positioning itself as teaching 'thinking, not scripts.' The content is verbose for the value it adds and would benefit from either being drastically shortened or made significantly more actionable with real examples.

Suggestions

Add concrete, executable examples for at least 2-3 platforms (e.g., actual PM2 restart commands, kubectl rollout undo examples, Vercel CLI commands) to raise actionability.

Cut sections that restate common DevOps knowledge Claude already knows (e.g., what rolling/blue-green/canary deployments are) and focus on project-specific or non-obvious guidance.

Split platform-specific procedures into separate reference files (e.g., VERCEL.md, VPS.md, K8S.md) and keep SKILL.md as a concise overview with clear navigation links.

Add explicit validation commands and feedback loops in the workflow (e.g., 'Run `curl -f https://app/health` — if it fails, execute rollback step') rather than abstract principles like 'Trust but verify'.

DimensionReasoningScore

Conciseness

The skill extensively explains concepts Claude already knows well — deployment basics, what health checks are, why backups matter, what rolling deployments are. The tables and decision trees are mostly common knowledge restated in formatted layouts. Significant padding with motivational quotes and meta-instructions ('Learn to THINK, not memorize scripts').

2 / 5

Actionability

The skill is almost entirely abstract principles and high-level guidance with no executable code, specific commands, or concrete examples. Tables list platform names and one-line descriptions but never show actual commands (e.g., no actual PM2 commands, no kubectl examples, no CI/CD config snippets). The skill explicitly disclaims providing actionable scripts.

2 / 5

Workflow Clarity

The 5-phase deployment process provides a clear sequence, and rollback triggers are defined. However, validation steps are implicit rather than explicit — there are no concrete verification commands, no feedback loops with specific retry conditions, and the verification window is just time-based guidance without actionable checkpoints.

3 / 5

Progressive Disclosure

All content is inlined in a single monolithic file with 10 major sections and no references to supporting files. The platform-specific details, emergency procedures, and anti-patterns could easily be split into separate reference files. No bundle files exist to support progressive disclosure.

2 / 5

Total

9

/

20

Passed

Description

41%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 identifies a clear domain (production deployment) and touches on key subtopics like rollback and verification, but remains at a high level without specifying concrete actions Claude would perform. The absence of a 'Use when...' clause is a significant gap for skill selection, and the phrase 'Teaches thinking, not scripts' is meta-commentary that doesn't help Claude decide when to invoke this skill.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases like 'deploying to production', 'rollback plan', 'release strategy', 'go live', or 'production incident'.

Replace 'Teaches thinking, not scripts' with concrete capabilities, e.g., 'Guides decisions on blue-green vs canary deployments, defines rollback criteria, and creates pre/post-deployment verification checklists'.

Include common synonyms and related terms users might say: 'release', 'ship to prod', 'revert', 'CI/CD pipeline', 'hotfix deployment'.

DimensionReasoningScore

Specificity

Names the domain (production deployment) and lists a few concrete areas (deployment workflows, rollback strategies, verification), but these are still somewhat high-level categories rather than specific actions. 'Teaches thinking, not scripts' is meta-commentary rather than a concrete capability.

3 / 5

Completeness

Has a reasonable 'what' (production deployment principles, rollback strategies, verification) but completely lacks a 'when' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when...' caps completeness at 3, and the 'what' is also somewhat vague, placing this at 2.

2 / 5

Trigger Term Quality

Includes relevant terms like 'deployment', 'rollback', and 'production' that users might naturally say, but misses common variations and synonyms such as 'release', 'deploy to prod', 'ship', 'CI/CD', 'hotfix', 'revert', or 'go live'.

3 / 5

Distinctiveness Conflict Risk

The focus on 'production deployment' and 'rollback strategies' provides some specificity, but terms like 'safe deployment workflows' and 'verification' are broad enough to overlap with CI/CD skills, DevOps skills, or general infrastructure skills. The 'principles and decision-making' framing adds ambiguity about whether this is a conceptual guide or an operational tool.

3 / 5

Total

11

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.