网有NETHAVE
AGENT SKILL

spec-governance-lite

InfoQ when-SDD-pays-off targeting: hard multi-constraint work gets staged approved baseline + attributable drift review; easy tasks use reason-first. Never claim specs raise bug recall; claim attribution. Human stays Accountable.

License 许可
MIT
最近更新
2026-11-09
Stars
★ 1
Forks
0

01 前言 Front Matter

name
spec-governance-lite
description
InfoQ when-SDD-pays-off targeting: hard multi-constraint work gets staged approved baseline + attributable drift review; easy tasks use reason-first. Never claim specs raise bug recall; claim attribution. Human stays Accountable.

02 资源文件 4

03 SKILL.md 正文

Skill: spec-governance-lite

Instructions

  1. Classify the task (easy / medium / hard) via scripts/spec_governance_gate.py --task ....
  2. Hard work: Spec Kit artifacts + named invariants; staged baseline then fresh generate; drift findings cite clauses.
  3. Easy work: reason-first; do not inflate ceremony.
  4. Never claim the baseline raises recall; claim attributable, contract-anchored review.
  5. Keep a human Accountable for reconciliation (model may be Responsible for generation).

Examples

python3 scripts/spec_governance_gate.py --json --task "rename typo in README"
python3 scripts/spec_governance_gate.py --json --task "paywall gate with catalog load"
PYTHONPATH=. python3 -m pytest scripts/tests/test_spec_governance_gate.py -q

Performance Notes

  • Pure Python; $0 SaaS.

Troubleshooting

  • block_false_recall_claim → rewrite claim to attribution, not recall.
  • block_inline_spec_prompt → approve specs/<###>/ then generate in a new step.
  • block_unattributed_drift → add invariant: / clause id per finding.

04 同仓库更多 Skills

IgorGanapolsky
IgorGanapolsky/Random-Timer

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

内容创作者写作与文案
★ 1
IgorGanapolsky
IgorGanapolsky/Random-Timer

workflow-economics-lite

Escape AI pilot purgatory: require completion-loop workflows with one owner, baseline, economic metric, system-of-record integration, and audit trail. Block orphan chatbots and interest-as-ROI claims.

Skill与智能体开发
★ 1
IgorGanapolsky
IgorGanapolsky/Random-Timer

verification-before-completion

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

★ 1
IgorGanapolsky
IgorGanapolsky/Random-Timer

value-center-lite

Apply InfoQ Rohrer value-center / VSM five questions (agency + coherence). Use when planning work, shipping releases, or auditing agent autonomy claims. Fail closed on product-only slogans without WQTU/paywall value.

★ 1
IgorGanapolsky
IgorGanapolsky/Random-Timer

using-superpowers

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

★ 1
IgorGanapolsky
IgorGanapolsky/Random-Timer

using-git-worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

★ 1