CtrlK
BlogDocsLog inGet started
Tessl Logo

consistency-audit

Adversarial consistency audit of a multi-document package across symbol lineage, bidirectional cross-references, brand discipline and naming drift, via scripts/audit_full.sh and the four dimensional audit_*.sh scripts. Use when the user asks to audit a documentation, proposal or discovery package for orphan references, asymmetric links or naming drift before release. [EXPLICIT]

63

Quality

78%

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/claude-native-toolkit/skills/consistency-audit/SKILL.md
SKILL.md
Quality
Evals
Security

Consistency Audit

An adversarial second pair of eyes. Detects the residual 2-25% that the first audit pass missed because the human auditor already trusted what they wrote.

Generic, brand-neutral engineering capability; sourced playbooks in references//knowledge/. [DOC]

TL;DR

Capability: consistency audit [EXPLICIT]

When to use this skill

Use this skill proactively when:

  • A multi-document package (5+ documents, 3+ actors, 20+ roles, 40+ symbols) is reaching "done" status.
  • The user asks for "auditoría", "audit", "consistency check", "polish", "before-final review", "subir a X%", "make it bulletproof".
  • After any major remediation pass that introduced new artifacts (new prototypes, new sections, new events).
  • Before any irreversible distribution moment (steering committee, comité tripartita, board, vendor RFP, client handover).
  • When the user wants to elevate from 90%+ to 100% maturity.

Do NOT use this skill when:

  • The package is a single document <30 pages with no symbol catalogs (overkill).
  • The user is mid-drafting (the skill audits, doesn't draft).
  • The user only wants prose review (use a writing-focused skill instead).

Sub-capabilities (resource map)

Deep, evidence-tagged playbooks — open the one the task needs (ICM Layer 3, on-demand). [INFERENCE]

Reference
references/audit-dimensions.md
references/examples-bupa-discovery.md
references/full-playbook.md
references/output-format.md
references/triggers-and-scope.md

Procedure

  1. Resolve the sub-capability; open the matching references/ playbook. [EXPLICIT]
  2. Apply its decision tables; pick the strategy explicitly. [EXPLICIT]
  3. Validate against the Quality Criteria and tag every claim. [EXPLICIT]

Quality Criteria

  • Sub-capability resolved to one playbook. [INFERENCE]
  • Claims evidence-tagged. [EXPLICIT]

Contract

  • Aceptación: capability resolved to its reference playbook, applied, validated, evidence-tagged. [EXPLICIT]
  • Límites: scoped to this capability; deep procedure in references/. [EXPLICIT]
  • Casos borde: ambiguous/insufficient input → request clarification before proceeding. [EXPLICIT]
  • Supuestos: access to project artifacts (code, docs, configs). [SUPUESTO]
  • Trade-off: depth in references keeps the SKILL.md stage contract lean (ICM). [EXPLICIT]

Packet

Capas del packet, cargables bajo demanda (disciplina ICM: una capa por vez, nunca todas juntas): references/ guías de profundidad (cargar UNA por etapa) · knowledge/ cuerpo de conocimiento · prompts/ prompts listos · examples/ salida de ejemplo · agents/ subagentes del packet · scripts/ automatización local · assets/ recursos estáticos.

Repository
JaviMontano/claude-plugins
Last updated
First committed

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.