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.

50

Quality

55%

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/AI-Agents-Safe-Coding-Skills-claude/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

60%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 content is a well-structured, principle-oriented deployment guide with a clear phased workflow and explicit verification/rollback feedback loops. Its main weaknesses are redundancy across sections and principle-level rather than fully executable action guidance.

Suggestions

Consolidate the repeated platform tables (deployment method in section 1 and rollback method in section 5) and merge the overlapping pre-deployment and decision checklists to reduce redundancy.

Tighten principle-level steps into more concrete instructions (e.g., specify what 'monitoring open' means and what must pass before CONFIRM vs ROLLBACK) to raise actionability.

Add explicit gating criteria linking the VERIFY phase to the rollback decision table so the workflow is self-contained without cross-section synthesis.

DimensionReasoningScore

Conciseness

The body is mostly compact tables, ASCII diagrams, and checklists that assume Claude's competence, but it carries real redundancy (pre-deployment checklist vs decision checklist, anti-patterns vs best practices, platform tables repeated across sections), matching the anchor for mostly-efficient content that could be tightened.

3 / 5

Actionability

Concrete guidance is present (platform-to-method mappings like 'K8s: kubectl rollout undo', decision tree, rollback thresholds), and code absence is not penalized for this instruction-only skill, but steps remain principle-level with gaps ('Execute with monitoring open' lacks specifics), matching the anchor for some concrete but incomplete guidance.

3 / 5

Workflow Clarity

The 5-phase process (PREPARE, BACKUP, DEPLOY, VERIFY, CONFIRM/ROLLBACK) is clearly sequenced with an explicit VERIFY checkpoint and a feedback loop ('All good? Confirm. Issues? Rollback.'), plus a verification window and checklists, satisfying the destructive-ops validation requirement; it falls just short of 5 because gating criteria are split across sections and require synthesis.

4 / 5

Progressive Disclosure

With no bundle files present, the ~238-line body is organized into ten well-numbered sections with clear headers and minor gaps (repeated platform tables), matching the anchor for good structure with most content appropriately placed.

4 / 5

Total

14

/

20

Passed

Description

50%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 clearly names the deployment domain and its core capabilities but stays at a principles level and omits any explicit 'when to use' trigger guidance, capping most dimensions at the midpoint. Adding a concrete 'Use when...' clause and more natural synonyms would lift specificity, completeness, and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when deploying to production, planning a release, or needing rollback guidance').

Include natural synonyms users say (release, ship, CI/CD, zero-downtime, canary, blue-green) to improve trigger-term coverage and distinctiveness.

Replace abstract framing ('principles and decision-making', 'Teaches thinking, not scripts') with one or two more concrete capability statements to raise specificity.

DimensionReasoningScore

Specificity

Names the deployment domain plus three capability areas ('deployment workflows, rollback strategies, and verification'), but 'principles and decision-making' and 'Teaches thinking, not scripts' are abstract framing rather than concrete actions, matching the anchor that names the domain with limited concrete actions.

3 / 5

Completeness

A clear 'what' is present ('Production deployment principles... rollback strategies, and verification') but there is no 'Use when...' or equivalent explicit trigger guidance, which per the rubric guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

'Production deployment' and 'rollback strategies' are natural user terms, but common synonyms and variations (release, ship, CI/CD, canary, blue-green, zero-downtime) are missing, matching the anchor for some relevant keywords without common variations.

3 / 5

Distinctiveness Conflict Risk

'Production deployment' is a recognizable niche but overlaps with CI/CD, infrastructure, and release-management skills, matching the anchor for somewhat-specific content that could still overlap with similar skills.

3 / 5

Total

12

/

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.

Validation15 / 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
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.