common-agent-guardrail…
Define deterministic guardrails for agent tool calls — protected paths, test-file locks during bug fixes, post-edit formatters, production approval gates,…
Adjudicates authorized exercise outcomes against independently held ground truth, redacted evidence, and explicit status boundaries. Use when comparing observations, resolving discrepancies, or preparing evidence-led security-review handoffs.
$ npx -y skills add hoangnguyen0403/agent-skills-standard --skill cyber-exercise-adjudication --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/cyber-exercise-adjudicationContext preview
The summary Claude sees to decide when to auto-load this skill.
Adjudicates authorized exercise outcomes against independently held ground truth, redacted evidence, and explicit status boundaries. Use when comparing observations, resolving discrepancies, or preparing evidence-led security-review handoffs.
name: cyber-exercise-adjudication
guardrail: true
description: Adjudicates authorized exercise outcomes against independently held ground truth, redacted evidence, and explicit status boundaries. Use when comparing observations, resolving discrepancies, or preparing evidence-led security-review handoffs.
metadata:
labels: [cybersecurity, adjudication, white-team]
triggers:
keywords: [exercise adjudication, independent ground truth, outcome adjudication, evidence discrepancy, exercise finding status]Compare evidence to pre-held expectations without self-approved promotion or compliance claims.
cyber-exercise-adjudication/ ├── SKILL.md ├── references/adjudication-record.md └── evals/evals.json
1. Confirm adjudicator independence from operator and evidence collector. 2. Load approved objective, scope, expected observation, and ground-truth version. 3. Compare redacted evidence by time, source, and limitation; record discrepancies. 4. Assign `confirmed`, `suspected`, `blocked`, `not-tested`, or `false-positive` only with rationale. 5. Preserve unresolved conflicts and route them to an accountable owner. 6. Emit sanitized findings to `artifacts/security-review.md` when that artifact is in scope.
Adjudication records carry `engagement_scope_ref`, `skill_version`, `source`, `observed_at`, `finding_status`, `evidence_refs`, `limitations`, and `accountable_owner`.
The portable SDLC standards layer for AI coding agents. Sync once, then work in your own runtime.
Repo: hoangnguyen0403/agent-skills-standard
Define deterministic guardrails for agent tool calls — protected paths, test-file locks during bug fixes, post-edit formatters, production approval gates,…
Draws architecture diagrams as editable draw.io files with a fixed house style, C4 levels, evidence-tagged shapes, and optional multi-view identity checks. Use…
Enforce SOLID principles, guard-clause style, function size limits, and intention-revealing naming across all languages. Use when refactoring for readability,…
Standardize BRD and BRD-lite discovery for business goals, stakeholder impact, current-to-future state, and measurable value outcomes. Use when creating BRD,…
Conduct high-quality, persona-driven code reviews. Use when reviewing PRs, critiquing code quality, or analyzing changes for team feedback.
Maximize context window efficiency, reduce latency, and prevent lost-in-middle issues through strategic masking and compaction. Use when token budgets are…