managing-deployment-rollbacks

Deploy use when you need to work with deployment and CI/CD. This skill provides deployment automation and orchestration with comprehensive guidance and automation. Trigger with phrases like "deploy application", "create pipeline", or "automate deployment".

Quality

45%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/devops/deployment-rollback-manager/skills/managing-deployment-rollbacks/SKILL.md

Quality

Discovery

40%

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 padded with vague buzzwords ('comprehensive guidance and automation', 'orchestration') without specifying concrete capabilities. While it includes some trigger phrases and a 'use when' clause, the lack of specific actions and the generic framing make it difficult to distinguish from other DevOps-related skills.

Suggestions

Replace vague language like 'comprehensive guidance and automation' with specific concrete actions such as 'configure CI/CD pipelines, manage rolling deployments, set up staging environments, handle rollbacks'.

Expand trigger terms to include common variations like 'continuous integration', 'continuous delivery', 'release pipeline', 'rollback', 'staging', 'production', and specific tool names if applicable.

Sharpen the 'Use when' clause to clearly delineate this skill's scope from adjacent skills (e.g., infrastructure provisioning, container orchestration) by specifying exact scenarios.

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'deployment automation and orchestration with comprehensive guidance and automation.' It does not list any concrete actions—no specific tasks like 'configure CI/CD pipelines,' 'manage rollbacks,' or 'set up staging environments' are mentioned.	1 / 3
Completeness	It has a weak 'what' (vague 'deployment automation and orchestration') and does include a 'when' clause ('Use when you need to work with deployment and CI/CD' plus trigger phrases), but the 'what' is so vague that the overall completeness is undermined. The 'when' exists but is generic.	2 / 3
Trigger Term Quality	It includes some relevant trigger phrases like 'deploy application', 'create pipeline', and 'automate deployment', which are natural terms users might say. However, it misses common variations like 'CI/CD', 'continuous integration', 'release', 'rollback', 'staging', 'production deploy', or specific tools.	2 / 3
Distinctiveness Conflict Risk	The mention of 'deployment' and 'CI/CD' provides some domain specificity, but the description is broad enough that it could overlap with infrastructure-as-code skills, DevOps skills, or cloud provisioning skills. It lacks clear niche boundaries.	2 / 3
	Total	7 / 12 Passed

Implementation

50%

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

This skill provides a solid conceptual framework for deployment rollbacks across multiple platforms with good error handling coverage and clear sequencing. However, it falls short on actionability—lacking executable code blocks, actual script templates, or concrete configuration examples that Claude could directly use. The multi-platform scope makes it broad but shallow, and the absence of feedback loops in the workflow and bundle files for detailed platform-specific guidance limits its effectiveness.

Suggestions

Add executable code blocks for each platform: a complete kubectl rollback script, an ECS CLI update-service command, and a Lambda alias update command with actual flags and parameters.

Replace the natural-language 'Examples' section with concrete input/output pairs showing actual commands run and expected outputs (e.g., kubectl output after successful rollback).

Add explicit feedback loops: 'If step 7 verification fails, check error table below, apply fix, and re-run verification before proceeding.'

Split platform-specific procedures into separate referenced files (e.g., KUBERNETES_ROLLBACK.md, ECS_ROLLBACK.md) to improve progressive disclosure and reduce the monolithic feel.

Dimension	Reasoning	Score
Conciseness	The content is reasonably structured but includes some unnecessary verbosity. The 'Examples' section provides vague natural-language prompts rather than executable examples, and the 'Output' section describes deliverables abstractly. Some sections like Prerequisites explain things Claude would already know (e.g., what Prometheus and Datadog are).	2 / 3
Actionability	The instructions provide specific commands like `kubectl rollout undo deployment/<name>` but most steps remain at the description level without executable code blocks, scripts, or copy-paste ready configurations. The 'Output' section lists deliverables but doesn't provide actual templates or scripts. The 'Examples' section contains natural language prompts rather than concrete input/output pairs.	2 / 3
Workflow Clarity	Steps are clearly sequenced (detect → assess → rollback → verify → report → automate) and step 7 serves as a validation checkpoint. However, there's no explicit feedback loop for what to do if the rollback verification in step 7 fails, and the workflow covers multiple platforms (K8s, ECS, Lambda) in a single linear sequence which could be confusing. Missing explicit 'if validation fails, do X' loops caps this at 2.	2 / 3
Progressive Disclosure	The content is well-sectioned with clear headers (Overview, Prerequisites, Instructions, Output, Error Handling, Examples, Resources). However, with no bundle files, all content is inline in a single file. The Resources section provides external links which is good, but the skill would benefit from splitting platform-specific rollback procedures into separate referenced files rather than mixing K8s, ECS, and Lambda in one document.	2 / 3
	Total	8 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3a2d27d

Reviewed: 1 day 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.