CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

production-deployment

Plan, execute, and validate production deployments when rollout safety, health checks, observability, rollback, or production-parity verification is required.

Quality

76%

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 ./Skills/agent-ops/production-deployment/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-organized, concise policy-style skill body with clear sectioning, a sequenced workflow, an explicit fail-fast validation loop, and properly signaled one-level-deep references that all resolve except one. Its main weakness is actionability: the guidance names what to confirm and report but provides no concrete commands, rollout patterns, or health-check examples to execute against.

Suggestions

Add 2-3 concrete examples in the Workflow section — e.g., a sample incremental rollout command (canary/blue-green), a health-check invocation, and a rollback trigger criterion — so the guidance is executable rather than purely directional.

Embed validation checkpoints into the workflow steps (e.g., after 'execute rollout', an explicit 'verify health checks pass before declaring success') instead of keeping them only in the separate Validation section.

Fix the dead reference 'Infrastructure/references/deferred-skill-context/agent-ops-production-deployment/' — either point to a path that exists in the bundle or describe how to locate the legacy archive.

DimensionReasoningScore

Conciseness

The body is lean bullet-style with no padding and no explanation of concepts Claude already knows (e.g., 'Redact secrets, tokens, credentials... by default', 'Run the smallest command or test that exercises the changed behavior'). It is 'Efficient; minor instances of over-explanation that could be trimmed' rather than 5, because sections like Philosophy ('Keep the skill focused on the decision and workflow the user actually requested') largely duplicate Constraints/Avoid and earn little per token.

4 / 5

Actionability

Some concrete guidance exists — 'Confirm target environment, change scope, and authorization posture', 'Identify deploy mechanism, health checks, and rollback criteria before execution' — but much stays high-level ('Prefer incremental or reversible rollout patterns', 'Monitor health and logs after deployment') with no example commands, concrete rollout patterns, or health-check specifics. This matches 'Some concrete guidance but incomplete... missing key details' rather than 4's 'concrete code or commands with minor gaps'.

3 / 5

Workflow Clarity

The Workflow section gives a clear sequenced process (confirm scope → identify mechanism/criteria → execute incrementally → monitor → report), and the Validation section adds an explicit fail-fast feedback loop ('stop at first failed gate; do not proceed until it is fixed and rerun'), matching 'Clear sequence with most checkpoints present; minor validation gaps'. It falls short of 5 because checkpoints are described in a separate section rather than embedded per-step, and no concrete gate commands are given.

4 / 5

Progressive Disclosure

Good structure with a dedicated Progressive Disclosure section pointing one level deep to real bundle files — 'Use references/contract.yaml for the machine-readable contract', 'references/evals.yaml', 'references/task-profile.json' (all verified present) — each with a stated purpose. It is a 4 rather than 5 because the referenced path 'Infrastructure/references/deferred-skill-context/agent-ops-production-deployment/' does not exist in the bundle, leaving a dead/unresolvable navigation entry.

4 / 5

Total

15

/

20

Passed

Description

75%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 strong single-sentence description that states concrete actions and an explicit when-clause covering deployment, rollout safety, health checks, observability, and rollback. Trigger keywords are natural and the niche is well-differentiated; the main gaps are a few missing synonyms ('release', 'ship') and a condition-framed rather than user-request-framed when-clause.

DimensionReasoningScore

Specificity

Names the domain ('production deployments') and several concrete actions — 'Plan, execute, and validate' — plus specific concern areas ('rollout safety, health checks, observability, rollback, or production-parity verification'). This matches the anchor 'Lists several specific actions; minor gaps in coverage' rather than 5, since it stops short of comprehensive action coverage (e.g., no explicit rollback-execution or verification-reporting actions), and is clearly above 3's '1-2 concrete actions'.

4 / 5

Completeness

Answers 'what' ('Plan, execute, and validate production deployments') and 'when' explicitly ('when rollout safety, health checks, observability, rollback, or production-parity verification is required'). The when-clause is condition-framed rather than the anchor-5 style of concrete user-trigger phrases ('Use when the user asks to...'), placing it at 'Has both what and when; when could be more explicit or specific' — clearly above 3, where 'when' is only weakly implied.

4 / 5

Trigger Term Quality

Includes natural terms users would say: 'deployments', 'rollout', 'health checks', 'rollback', 'observability', 'production'. A few natural variations are missing ('release', 'ship', 'deploy to prod', 'go-live'), so it fits 'Good keyword coverage; a few natural terms missing' rather than the 5 anchor's comprehensive synonym coverage, and is well above 3's 'missing common variations'.

4 / 5

Distinctiveness Conflict Risk

The niche is distinct — production rollout with safety, rollback, and production-parity verification — so it is unlikely to trigger for unrelated skills, matching 'Mostly distinct; minor overlap risk with closely related skills' (e.g., a generic CI/CD or infrastructure-provisioning skill). It is not a 5 because 'deploy' and 'observability' are broad enough to overlap with adjacent ops skills.

4 / 5

Total

16

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

jscraik/Agent-Skills

Path

Skills/agent-ops/production-deployment/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.