tiered-memory

Three-tier agent memory model (hot/cold/wiki) for context reduction per spawn

Quality

52%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.squad/skills/tiered-memory/SKILL.md

Quality

Content

58%Weight 40%Scale 1-5

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

The content is well-structured and mostly actionable with clear tier definitions and spawn patterns, but it is hampered by duplicated template blocks, repeated caveats, and missing validation checkpoints for batch memory operations. Splitting the spawn template into a reference file and adding validation steps would improve it.

Suggestions

Extract the full 'Spawn Template' block (lines 125-201) into a references file and reference it once, since the same Hot/Cold/Wiki pattern is already shown in the 'Spawn Template Pattern' section.

Add validation checkpoints to the Scribe integration workflow (e.g., verify compressed Cold summary size before promotion, confirm wiki entry deprecation before removal) since memory promotion is a batch operation.

Consolidate the repeated 'design-only / tracked in #1264' caveats into a single Status callout to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with clear tier definitions and tables, but repeats the same spawn-template blocks (Hot/Cold/Wiki) in two sections and restates the design-only caveat multiple times, which could be tightened.	3 / 5
Actionability	It provides concrete, mostly executable guidance: explicit spawn-template snippets, flag names (--include-cold/--include-wiki), and file paths, with only minor gaps since the runtime is unimplemented.	4 / 5
Workflow Clarity	The Scribe integration lists a numbered sequence and there is an implementation checklist, but there are no validation checkpoints for the batch/destructive memory-promotion operations, and the checklist has no feedback loops, capping clarity at 3.	3 / 5
Progressive Disclosure	Structure is reasonable with sectioned tiers and external links to tracking issues, but there are no bundle reference files and a large duplicate spawn template is inlined rather than split out, leaving organization mid-range.	3 / 5
	Total	13 / 20 Passed

Description

46%Weight 40%Scale 1-5

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 is specific and distinctive about what the skill does, but it omits an explicit 'Use when...' trigger and relies on technical jargon rather than natural user language. Adding a concrete trigger clause would lift completeness and trigger-term quality.

Suggestions

Add a 'Use when ...' clause naming natural user phrases (e.g., 'Use when managing agent memory across sessions, reducing context payload size, or loading only relevant history per spawn').

Include user-facing synonyms beyond hot/cold/wiki jargon, such as 'memory tiers', 'session context', 'context budget'.

Clarify the spawn scope so the 'when' is explicit rather than implied by 'per spawn'.

Dimension	Reasoning	Score
Specificity	The description names the domain (three-tier memory model) and specific concrete actions (hot/cold/wiki tiers, context reduction per spawn), listing several specific mechanisms with only minor gaps in coverage.	4 / 5
Completeness	It gives a clear 'what' but entirely lacks a 'Use when...' trigger clause; the 'when' is only weakly implied by 'context reduction', so it is capped below the midpoint per the missing-trigger guideline.	2 / 5
Trigger Term Quality	Keywords are technical ('three-tier', 'hot/cold/wiki', 'context reduction per spawn') with no natural user-facing phrases or synonyms that a user would actually say when needing this skill.	2 / 5
Distinctiveness Conflict Risk	The tiered-memory framing is a clear niche with distinct triggers and minimal overlap risk with other skills, though it is somewhat narrow to the squad context.	4 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: bradygaster/squad
Path: .squad/skills/tiered-memory/SKILL.md
Commit: a0d2563

Reviewed: about 15 hours 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.