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. Use when auditing production readiness before launch, after a merge, or when asked what breaks in prod.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

75%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, mostly lean audit skill with concrete git commands, a clear ordered workflow, decision-gate scoring caps, and a worked output example. The main gaps are question-based rather than executable risk-lens checks and the absence of explicit validate-then-retry feedback loops.

Suggestions

Convert at least some Risk Lens questions into executable checks (e.g. 'grep -r \"auth\" middleware/' or a command to confirm webhook idempotency) to lift actionability toward fully executable guidance.

Add an explicit feedback loop in the workflow (e.g. 'if a blocker is found, stop and report blockers before computing a final score') to add a validation checkpoint to the audit sequence.

Trim the intro meta-commentary about being a 'maintainer-safe rewrite' since it does not help Claude run the audit and competes for context.

Dimension	Reasoning	Score
Conciseness	The body is largely lean with bullet lists and no over-explanation of familiar concepts, but the intro meta-commentary ('maintainer-safe rewrite of the stale community production-audit idea...') and a few framing sentences could be trimmed, matching the efficient-with-minor-over-explanation anchor.	4 / 5
Actionability	Provides concrete executable git commands, a specific file-surface checklist, and a copy-paste output template with a worked example, but the Risk Lenses are framed as questions to ask rather than executable checks, leaving minor gaps.	4 / 5
Workflow Clarity	A clear five-step sequence with explicit scoring caps acting as decision gates; this is a read-only audit so the destructive/batch validation cap does not apply, but it lacks explicit validate-then-branch feedback loops that would push it to the top anchor.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with all content appropriately inline for an audit checklist and one-level-deep See Also links; there is no separate reference file to split into, so it sits just below the clear-overview-with-external-references top anchor.	4 / 5
	Total	16 / 20 Passed

Description

86%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, well-structured description that clearly states the skill's purpose and explicit usage triggers with natural phrasing. The only gap is that specificity rests on a single audit verb rather than a list of distinct concrete actions, and there is minor overlap with related review skills.

Suggestions

List 2-3 concrete distinct actions the audit performs (e.g. 'inspects release surface, scores ship/block risk, names evidence checked') to lift specificity from a single generic verb to multiple concrete operations.

Add one distinguishing phrase differentiating this from security-review beyond 'local-evidence' (e.g. 'triages launch risk across auth, data, payments, and ops') to reduce overlap with sibling review skills.

Dimension	Reasoning	Score
Specificity	Names the production-audit domain plus several concrete review contexts (pre-launch, post-merge, 'what breaks in prod'), but the core action is a single generic verb ('audit') rather than multiple distinct concrete operations, fitting the domain-plus-actions anchor better than the comprehensive-coverage anchor.	3 / 5
Completeness	Explicitly answers both what ('Local-evidence production readiness audit...') and when ('Use when auditing production readiness before launch, after a merge, or when asked what breaks in prod') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would actually say ('is this production-ready', 'ready to ship', 'what breaks in prod', 'audit this repo') with synonyms and an explicit 'Use when' clause, matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	The 'local-evidence' and 'without sending repo data to an external audit service' framing carves a clear niche, but there is minor overlap risk with sibling skills like security-review and deployment-patterns (acknowledged in See Also).	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/production-audit/SKILL.md
Commit: d8409a4

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.