decay

Manage evidence freshness by identifying stale decisions and providing governance actions

Quality

41%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./plugins/fpf/skills/decay/SKILL.md

Quality

Content

64%

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

The skill provides strong actionable guidance with concrete file templates, clear naming conventions, and realistic example workflows. Its main weaknesses are unnecessary conceptual explanations that pad the content and the absence of validation checkpoints for operations like file moves and deprecation. The content would benefit from trimming the explanatory sections and adding explicit verification steps.

Suggestions

Remove or drastically shorten the 'Quick Concepts' section — Claude doesn't need explanations of what 'stale evidence' or 'waiving' means conceptually; just define the thresholds and actions.

Add validation checkpoints: verify hypothesis file exists before moving, confirm waiver date is in the future, and include a confirmation prompt before destructive deprecation operations.

Consider extracting the detailed record templates (waiver and deprecation markdown) into a separate reference file to keep the main skill leaner.

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary explanatory content that Claude already understands (e.g., 'What is stale evidence?', 'What is waiving?', the analogy about benchmarks and security audits). The tables and examples are useful but the conceptual explanations could be trimmed significantly. The 'Quick Concepts' section is largely unnecessary padding.	2 / 3
Actionability	The skill provides concrete file paths, specific markdown templates for waiver and deprecation records, exact bash commands for file moves, and complete example workflows showing user-agent interaction. The guidance is specific and copy-paste ready with clear file naming conventions and frontmatter schemas.	3 / 3
Workflow Clarity	The three-step process (generate report → present → handle actions) is clearly sequenced, and each action (refresh, deprecate, waive) has defined steps. However, there are no explicit validation checkpoints — for example, no verification that the hypothesis file exists before moving it, no check that the waiver date is in the future, and no confirmation step before destructive operations like deprecation.	2 / 3
Progressive Disclosure	The content is reasonably well-structured with clear sections and headers, but it's all inline in a single file with no references to supporting documents. The 'Quick Concepts' section, detailed record templates, and common workflows could be split into separate reference files. For a skill of this length (~150 lines of substantive content), some progressive disclosure would improve navigability.	2 / 3
	Total	9 / 12 Passed

Description

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 uses domain-specific jargon without explaining what concrete actions the skill performs or when it should be triggered. It lacks a 'Use when...' clause and natural user-facing keywords, making it difficult for Claude to reliably select this skill. The niche domain provides some distinctiveness, but the vague language undermines its effectiveness.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about outdated decisions, evidence review schedules, or needs to audit decision freshness.'

Replace jargon like 'governance actions' with specific concrete actions, e.g., 'flags decisions older than a threshold, recommends re-evaluation, archives obsolete evidence, generates freshness reports.'

Include natural trigger terms users might say, such as 'outdated decisions', 'review schedule', 'decision audit', 'expired evidence', or 'refresh decisions.'

Dimension	Reasoning	Score
Specificity	Names the domain ('evidence freshness') and some actions ('identifying stale decisions', 'providing governance actions'), but 'governance actions' is vague and the specific concrete actions are not comprehensively listed.	2 / 3
Completeness	The description provides a partial 'what' but has no 'Use when...' clause or equivalent explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' itself is also weak, so this scores a 1.	1 / 3
Trigger Term Quality	Terms like 'evidence freshness', 'stale decisions', and 'governance actions' are domain-specific jargon that users are unlikely to naturally say. Missing common user-facing trigger terms that would help Claude match this skill.	1 / 3
Distinctiveness Conflict Risk	The concept of 'evidence freshness' and 'stale decisions' is somewhat niche, reducing broad conflict risk, but 'governance actions' is generic enough to overlap with other governance or compliance-related skills.	2 / 3
	Total	6 / 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: 3711edf

Reviewed: 20 days 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.