common-agent-guardrail…
Define deterministic guardrails for agent tool calls — protected paths, test-file locks during bug fixes, post-edit formatters, production approval gates,…
Maintains sparse, reviewable cybersecurity framework edges with versioned IDs, relation, rationale, source, and review status. Use when mapping exercise observations or procedures to NIST, ATT&CK, or another named framework.
$ npx -y skills add hoangnguyen0403/agent-skills-standard --skill cyber-framework-mapping --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/cyber-framework-mappingContext preview
The summary Claude sees to decide when to auto-load this skill.
Maintains sparse, reviewable cybersecurity framework edges with versioned IDs, relation, rationale, source, and review status. Use when mapping exercise observations or procedures to NIST, ATT&CK, or another named framework.
name: cyber-framework-mapping
guardrail: true
description: Maintains sparse, reviewable cybersecurity framework edges with versioned IDs, relation, rationale, source, and review status. Use when mapping exercise observations or procedures to NIST, ATT&CK, or another named framework.
metadata:
labels: [cybersecurity, framework-mapping, provenance]
triggers:
keywords: [framework mapping, control mapping, ATT&CK mapping, NIST mapping, framework edge, mapping review]Map only evidenced relationships; catalog context is not proof of efficacy, compliance, or coverage.
cyber-framework-mapping/ ├── SKILL.md ├── references/edge-record.md └── evals/evals.json
1. Name framework, version, stable ID, and exact source URL or document section. 2. Choose relation (`supports`, `describes`, `observed-as`, `partial`, `unknown`, or `conflicts`). 3. Write a bounded rationale tied to an evidence record, not a generic similarity. 4. Set review status: `reviewed`, `needs-review`, or `unreviewed`; include reviewer and date when reviewed. 5. Preserve empty or unknown mappings explicitly; do not infer a complete catalog. 6. On a version/source change, preserve the prior versioned edge and its evidence unchanged. Create a separately versioned candidate linked to the prior record, mark it `needs-review`, and re-review; never overwrite historical mappings.
For mapped observations, 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…