Tracks when your evidence expires and forces you to decide what to do about it. Every piece of evidence has a valid_until date, and this skill scans your .fpf directory to show what's stale, what's about to expire, and what you've explicitly waived. You get three options: refresh the evidence by rerunning tests, deprecate the whole decision if it's obsolete, or waive it temporarily with a documented rationale and deadline. The weakest link principle applies here, one expired piece of evidence makes the entire decision questionable. Most useful as a weekly maintenance check or right before a release when you need to know if your decisions are still backed by current data.
- skills.sh installs
- 1.2K
- GitHub stars
- 1.8K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add neolabhq/context-engineering-kit --skill decay --agent claude-codeInstalls into .claude/skills of the current project.
Files
Evidence Freshness Management
Manages evidence freshness by identifying stale decisions and providing governance actions. Implements FPF B.3.4 (Evidence Decay).
Key principle: Evidence is perishable. Decisions built on expired evidence carry hidden risk.
Quick Concepts
What is "stale" evidence?
Every piece of evidence has a valid_until date. A benchmark from 6 months ago may no longer reflect current system performance. A security audit from before a major dependency update doesn't account for new vulnerabilities.
When evidence expires, the decision it supports becomes questionable - not necessarily wrong, just unverified.
What is "waiving"?
Waiving = "I know this evidence is stale, I accept the risk temporarily."
Use it when:
- You're about to launch and don't have time to re-run all tests
- The evidence is only slightly expired and probably still valid
- You have a scheduled date to refresh it properly
A waiver is NOT ignoring the problem - it's explicitly documenting that you know about the risk and accept it until a specific date.
The Three Actions
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/neolabhq/context-engineering-kit
- First seen
- Jun 3, 2026
More from neolabhq/context-engineering-kit
All 63- Attach Review To Pr1.2K
- Git Notes1.2K
- Setup Arxiv Mcp1.2K
- Propose Hypotheses1.2K
- Build Mcp1.2K
- Load Issues1.2K
- Create Workflow Command1.2K
- Query1.2K
- Status1.2K
- Reset1.2K
- Setup Context7 Mcp1.2K
- Prompt Engineering1.5K
- Context Engineering1.5K
- Thought Based Reasoning1.4K
- Reflect1.4K
- Write Concisely1.4K
- Kaizen1.4K
- Multi Agent Patterns1.4K
- Memorize1.3K
- Update Docs1.3K
- Critique1.3K
- Brainstorm1.3K
- Judge With Debate1.3K
- Root Cause Tracing1.3K
Recommended
cavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
improveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
karpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs