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.

57

Quality

67%

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 ./.agents/skills/deployment-procedures/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The body is a well-structured, principles-oriented guide with a clear validated workflow, but it is over-long for a single file with no reference split-out, repeats checklist content across sections, and stops short of executable commands by design.

Suggestions

Consolidate the overlapping pre-deployment checklist, decision checklist, best practices, and anti-patterns sections, which repeat the same backup/monitor/rollback items, to remove redundancy and tighten token use.

Add a few concrete, copy-paste-ready command snippets for the most common platforms (e.g., 'kubectl rollout undo deployment/<name>', the Vercel/Netlify redeploy-previous-commit command) alongside the principles to raise actionability while preserving the 'think, not scripts' framing.

Split the platform-specific rollback and zero-downtime detail tables into a reference file (e.g., references/PLATFORMS.md) and link to it from the overview, reducing the 234-line monolith and enabling one-level-deep progressive disclosure.

DimensionReasoningScore

Conciseness

Mostly efficient via compact tables and decision trees, but backup/monitor/rollback items recur across the pre-deployment checklist, decision checklist, best practices, and anti-patterns sections, so it could be tightened.

2 / 3

Actionability

Provides concrete specific guidance (platform→method mappings, 'kubectl rollout undo', timed verification windows, 'Performance >50% degraded → rollback') but deliberately stops short of copy-paste executable procedures; the 'teach thinking, not scripts' framing explicitly justifies the flexibility, keeping it above 1 but below 3.

2 / 3

Workflow Clarity

The 5-phase process (PREPARE→BACKUP→DEPLOY→VERIFY→CONFIRM/ROLLBACK) gives a clear sequence with explicit validation (VERIFY phase plus the timed verification window), feedback loops (rollback on issues), and checklists, so the destructive-operation cap at 2 does not apply.

3 / 3

Progressive Disclosure

Well-organized into clear sections, but it is a 234-line single monolithic file with no references or progressive-disclosure mechanism, and content that could be split (platform rollback tables, zero-downtime detail) is inline.

2 / 3

Total

9

/

12

Passed

Description

72%

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 names a clear, distinctive niche with strong natural trigger terms, but it stays abstract ("principles and decision-making") and lacks an inline "Use when…" trigger, leaving the when-guidance only in the separate when_to_use field.

Suggestions

Add an explicit 'Use when…' trigger clause to the description field itself (e.g., 'Use when deploying to production, planning rollbacks, or setting up CI/CD') so completeness is not capped at 2 by relying on the separate when_to_use field.

Reframe 'principles and decision-making' with concrete verb-based actions (e.g., 'Plan, execute, and verify production deployments; design rollback strategies') to lift specificity from abstract noun-phrases to the anchor-3 standard.

DimensionReasoningScore

Specificity

Names the domain and several capability areas ("Safe deployment workflows, rollback strategies, and verification") but frames them as abstract noun-phrases ("principles and decision-making") rather than the concrete verb-based actions of the anchor-3 example.

2 / 3

Completeness

Clearly answers what the skill does, but the when/trigger guidance lives only in the separate when_to_use field rather than the description itself, so per the guideline a missing "Use when…" clause caps this at 2.

2 / 3

Trigger Term Quality

Contains natural terms users actually say — "Production deployment", "rollback strategies", "verification" — giving good coverage that matches the anchor-3 standard.

3 / 3

Distinctiveness Conflict Risk

The production-deployment-plus-rollback niche is clearly distinct with specific triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

10

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

14

/

16

Passed

Repository
vudovn/ag-kit
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.