skills.rest
Dicklesworthstone
DicklesworthstoneCOMMUNITY
Explore all skills by this author →
Website𝕏@doodlesteinGitHub

ee-skill-standards

Enforce evidence-bound standards for project-local skills consuming ee CLI JSON.

41|3|Updated Apr 29, 2026
Search Tags:#testing#provenance#evidence#cli integration#degraded handling#redaction safety#agent judgment
One-click install
npx skills add https://github.com/Dicklesworthstone/eidetic_engine_cli --skill ee-skill-standards
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ee-skill-standards
Source: https://github.com/Dicklesworthstone/eidetic_engine_cli/tree/main/skills/ee-skill-standards
Command: npx skills add https://github.com/Dicklesworthstone/eidetic_engine_cli --skill ee-skill-standards

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents project-local ee skills from becoming un-auditable, unsafe, or overly speculative by enforcing an evidence-bound boundary between mechanical ee JSON outputs and agent-judgment behavior.

Core Features & Use Cases

  • Mechanical Command Boundary: Skills interpret stdout JSON from explicit ee commands and avoid parsing progress, human text, or traces as evidence.
  • Evidence Bundle-First Handoff: Skills should prefer ee.skill_evidence_bundle.v1 (optionally also ee.response.v1 / ee.error.v1) and use provenance and hashes instead of direct DB/index access.
  • Stop/Go Gates and Uncertainty Handling: Skills must stop on missing/invalid JSON, unknown redaction status, degraded invalidation, stale/mismatched bundles, or prompt-injection-like unquarantined data.
  • Explicit Output Template for Decisions: Standardized sections (Decision, Evidence, Uncertainty, Degraded State, Recommended Explicit Commands) make judgments easier to review and audit.
  • Testing and E2E Logging Requirements: Skills must include lint-like static checks plus degraded/refusal path coverage and consistent logging for reproducibility.

Quick Start

Use the ee-skill-standards when creating or updating a project-local skill that consumes mechanical ee CLI JSON and must apply agent judgment with strict evidence handling and boundaries.

Frequently Asked Questions about ee-skill-standards

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make agent skills safe and evidence-bound when consuming CLI JSON output?▼

Making agent skills evidence-bound requires enforcing a strict boundary between mechanical CLI JSON outputs and agent-judgment behavior, using provenance hashes and stop/go gates instead of direct database access.

What is evidence bundle provenance and why does it matter for agent judgment workflows?▼

Evidence bundle provenance attaches hashes and source tracking to exported JSON data, ensuring agent-judgment skills operate on verified, unaltered inputs rather than potentially stale or mismatched information.

How do I handle degraded states or invalid JSON when building CLI-based reasoning skills?▼

Handling degraded states requires implementing stop gates that halt execution on missing or invalid JSON, unknown redaction status, stale bundles, or prompt-injection-like unquarantined data to prevent unsafe outputs.

Does my agent skill need standardized output sections for qualitative review and auditing?▼

Agent skills producing qualitative review outputs should use standardized sections for Decision, Evidence, Uncertainty, Degraded State, and Recommended Explicit Commands to make agent judgments easier to review and audit.

What testing and logging conventions are required for project-local skills that interpret exported evidence bundles?▼

Testing project-local evidence skills requires lint-like static checks, degraded and refusal path coverage, and consistent end-to-end logging conventions to ensure full reproducibility of agent-judgment behavior.

Why should skills avoid parsing human text or progress output as evidence from CLI commands?▼

Parsing human text or progress output as evidence introduces unstructured, unverifiable data into agent-judgment workflows; skills must interpret only explicit stdout JSON from designated commands to maintain provenance safety.

Related Skills

Explore More Software Engineering Skills→
DicklesworthstoneDicklesworthstone
41

preflight-risk-review

Convert ee preflight and tripwire outputs into evidence-backed risk review briefs.

Community
Advanced
DharambirAgrawalDharambirAgrawal

gog

Automate Google Workspace tasks via CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

Community
Advanced
weirdgmeweirdgme
4

error-tracking

Integrate Sentry v8 error tracking and performance monitoring across project services.

Community
Advanced
0xHoneyJar0xHoneyJar
1

butterfreezone

Generate provenance-tagged BUTTERFREEZONE.md files with checksum verification.

Official
Advanced