decay

Manage evidence freshness by identifying stale decisions and providing governance actions

Quality

40%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/fpf/skills/decay/SKILL.md

Quality

Discovery

17%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies a specific domain (evidence freshness and stale decisions) but relies on jargon that users are unlikely to use naturally. It lacks a 'Use when...' clause, concrete action details, and natural trigger terms, making it difficult for Claude to reliably select this skill at the right time.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases, e.g., 'Use when the user asks about outdated decisions, expired evidence, decision review schedules, or staleness checks.'

Replace vague terms like 'governance actions' with specific concrete actions such as 'flag expired decisions for re-review, notify stakeholders, archive outdated evidence, generate freshness reports.'

Include natural language variations users might say, such as 'outdated decisions', 'old evidence', 'decision expiry', 'review cycle', or 'decision audit'.

Dimension	Reasoning	Score
Specificity	Names the domain ('evidence freshness') and some actions ('identifying stale decisions', 'providing governance actions'), but the actions are not very concrete—'governance actions' is vague and doesn't specify what those actions actually are (e.g., flagging, archiving, notifying, re-reviewing).	2 / 3
Completeness	The description addresses 'what' at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1.	1 / 3
Trigger Term Quality	The terms 'evidence freshness', 'stale decisions', and 'governance actions' are domain-specific jargon that users are unlikely to naturally say. Common user phrases like 'outdated decisions', 'review old decisions', 'expired evidence', or 'decision audit' are missing.	1 / 3
Distinctiveness Conflict Risk	The concept of 'evidence freshness' and 'stale decisions' is somewhat niche, which helps with distinctiveness, but the vague 'governance actions' could overlap with other governance or compliance-related skills.	2 / 3
	Total	6 / 12 Passed

Implementation

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill provides a well-structured governance workflow with clear action types and good example outputs, but suffers from verbosity in its conceptual explanations and lacks fully executable code for the core freshness-checking logic. The workflow sequencing is strong, but the actionability is weakened by describing steps rather than providing runnable implementations.

Suggestions

Remove or drastically shorten the 'Quick Concepts' section — Claude doesn't need explanations of what 'stale' means or when to use waivers; a one-line summary per action in the table suffices.

Provide executable code (Python or shell script) for Step 1's freshness classification logic rather than describing it in prose — e.g., a script that parses YAML frontmatter and compares valid_until to the current date.

Consider extracting the detailed markdown templates for deprecation and waiver records into a referenced TEMPLATES.md file to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary explanatory content (e.g., 'What is stale evidence?' and 'What is waiving?' sections explain concepts Claude can infer). The waiver explanation is particularly verbose. However, the action sections and tables are reasonably efficient.	2 / 3
Actionability	The skill provides concrete markdown templates and file paths, but the core Step 1 ('List all evidence files, read valid_until, compare with current date') is described rather than implemented with executable code. The bash command for moving files is concrete, but the freshness classification logic is pseudocode-level.	2 / 3
Workflow Clarity	The three-step workflow (generate report → present report → handle actions) is clearly sequenced. Each action (refresh, deprecate, waive) has explicit steps with file creation examples. The WLNK principle provides a clear validation rule, and the common workflows section gives context-specific sequences.	3 / 3
Progressive Disclosure	The content is well-structured with clear sections and tables, but it's a fairly long monolithic document with no references to external files. The 'Quick Concepts' section could be separated or omitted, and the detailed markdown templates for deprecation/waiver records could be in a reference file. No bundle files exist to offload content to.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: NeoLabHQ/context-engineering-kit
Commit: dedca19

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.