CtrlK
BlogDocsLog inGet started
Tessl Logo

production-audit

Local-evidence production readiness audit for shipped apps, pre-launch reviews, post-merge checks, and "what breaks in prod?" questions without sending repo data to an external audit service.

79

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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 tight, actionable audit playbook: it sequences the work, supplies real commands and a scoring rubric with validation caps, and models the expected output with a worked example. It avoids concept-explanation padding and stays within a single well-structured file appropriate to its scope.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it gives commands, checklists, and scoring rules without explaining what git, CI, or webhooks are. Every section earns its tokens.

3 / 3

Actionability

Provides copy-paste git commands, a concrete evidence checklist, explicit scoring bands with hard caps, and a full output template with a worked example — all executable guidance rather than abstraction.

3 / 3

Workflow Clarity

A numbered five-step audit sequence is paired with explicit validation checkpoints via the score caps (cap at 69 for missing auth/idempotency/rollback, cap at 84 for non-green CI), giving clear feedback loops for risky releases.

3 / 3

Progressive Disclosure

Single self-contained file with well-organized sections and a See Also pointer to related skills; no bundle files are needed and references are one level deep, which fits a focused single-purpose skill.

3 / 3

Total

12

/

12

Passed

Description

100%

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 concise, concrete, and triggers-rich: it states the capability, the use contexts, and the differentiating constraint in a single sentence without padding. It reads naturally as something a user would say when they need this skill.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and contexts — 'production readiness audit', 'pre-launch reviews', 'post-merge checks', and 'what breaks in prod?' questions — rather than vague language.

3 / 3

Completeness

Explicitly answers both what it does ('Local-evidence production readiness audit') and when to use it ('for shipped apps, pre-launch reviews, post-merge checks, and "what breaks in prod?" questions').

3 / 3

Trigger Term Quality

Includes natural phrases users actually say ('what breaks in prod?', 'ready to ship', 'is this production-ready') alongside technical terms, giving strong coverage.

3 / 3

Distinctiveness Conflict Risk

The local-evidence, no-external-data-sharing framing carves a clear niche distinct from generic code review or security-review skills, making mis-triggering unlikely.

3 / 3

Total

12

/

12

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
affaan-m/ECC
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.