tiered-memory

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

Quality

50%

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

50%

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

The body is a clearly organized design proposal with a useful decision table and concrete file-path conventions, but it is hampered by duplicated template content, non-executable placeholder scaffolding for an unimplemented runtime, and a lack of validation checkpoints in its multi-step processes.

Suggestions

Collapse the duplicate 'Spawn Template Pattern' and 'Spawn Template' sections into one, or move the full template into a separate reference file referenced once from the overview.

Add explicit validation/feedback steps to the Scribe promotion and implementation workflows (e.g., verify the Hot file was written, confirm the Cold summary meets the ~10% verbosity target before promotion).

Mark the placeholder spawn template and '--include-cold'/'--include-wiki' flags as proposed/not-yet-executable inline so it is unambiguous that they are design scaffolding rather than runnable commands.

Dimension	Reasoning	Score
Conciseness	The body is well-sectioned and assumes Claude's competence (no basic-concept padding), but the spawn template is presented twice (the 'Spawn Template Pattern' code blocks and the full 'Spawn Template' section) and the 'design proposal, not shipped' disclaimer repeats at top and bottom, so it could be tightened.	2 / 3
Actionability	It gives concrete structural guidance (file paths like '.squad/memory/hot/{agent}.md', size targets, a decision table), but the spawn templates use unresolvable placeholders ('{hot_context}') and '--include-cold'/'--include-wiki' flags for a runtime that is explicitly not implemented, which is scaffolding rather than executable code.	2 / 3
Workflow Clarity	The Scribe integration steps (1-2-3) and the implementation checklist are sequenced, and the 'When to Load Each Tier' table is clear, but the multi-step processes lack any validation checkpoints or feedback loops, matching 'steps listed but validation gaps'.	2 / 3
Progressive Disclosure	There are no bundle files and the headers are well-organized with no nested references, but the ~95-line inline 'Spawn Template' section duplicates earlier content and could be split into a separate reference file, fitting 'content that should be separate is inline'.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 about the model's structure and purpose but reads as a design noun-phrase rather than action-oriented guidance, and it entirely lacks a 'Use when...' trigger clause. It is moderately distinct but jargon-heavy.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger situations (e.g., 'Use when spawning agents that load large context histories, or when reducing per-spawn context payload').

Reframe the description around concrete actions in third person (e.g., 'Reduces per-spawn context by separating agent memory into hot, cold, and wiki tiers and loading only the relevant tier').

Replace jargon like 'per spawn' and 'hot/cold/wiki' in the lead with more user-natural phrasing while keeping the tier names.

Dimension	Reasoning	Score
Specificity	The description names the concrete structure ('Three-tier agent memory model (hot/cold/wiki)') and purpose ('context reduction per spawn'), but it is a noun-phrase model description rather than a list of concrete actions, matching the 'names domain and some actions but not comprehensive' anchor.	2 / 3
Completeness	It states what the skill is (the three-tier model) but has no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	'agent memory' and 'context reduction' are semi-natural terms, but 'per spawn', 'hot/cold/wiki', and 'tiered' are internal jargon a user would rarely say, fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The hot/cold/wiki tiered-memory niche is fairly specific, but the absence of explicit trigger terms and overlap with general agent-memory/context skills means it is only 'somewhat specific but could still overlap'.	2 / 3
	Total	8 / 12 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: e23dd92

Reviewed: about 22 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.