memory-management

Use when the user asks to "remember project context", "save SEO data", "track campaign progress", "store keyword data", "manage project memory", "remember this for next time", "save my keyword data", or "keep track of this campaign". Manages a two-layer memory system (hot cache + cold storage) for SEO/GEO project context, tracking keywords, competitors, metrics, and campaign status with intelligent promotion/demotion.

Quality

73%

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 ./.agents/skills/memory-management/SKILL.md

Quality

Content

56%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 body is highly actionable with concrete templates, specific triggers, and real validation checklists, but it is materially over-long for a memory-management skill: redundant tips and lengthy mock examples pad the context, and large templates that belong in separate reference files are inlined with no bundle structure to offload them.

Suggestions

Move the full CLAUDE.md hot-cache template and glossary template into separate reference files (e.g. references/claude-template.md, references/glossary-template.md) and replace the inlined copies with short summaries plus one-level-deep links, improving both conciseness and progressive disclosure.

Cut the three mock-conversation examples down to one compact worked example, or collapse them into a short table of input→action→updated-files rows, to remove the largest block of padding.

Delete or merge the "Tips for Success" section into "Practical Limitations" since the two already repeat the line-count, dating, and archiving guidance verbatim.

Dimension	Reasoning	Score
Conciseness	At ~740 lines the body is noticeably verbose: three full mock-conversation examples, a 10-item "Tips for Success" that rehashes the "Practical Limitations" section, and large inlined templates are padded sections that could be trimmed without losing substance.	2 / 5
Actionability	Provides concrete, copy-paste-ready templates (directory tree, CLAUDE.md hot cache, glossary) and specific numeric triggers ("3+ conversations within 7 days", "5+ position change") with exact file paths; minor gaps come from placeholder-heavy and tool-connected-vs-manual conditional branches.	4 / 5
Workflow Clarity	Lookup, promotion/demotion, update-trigger, and archive workflows are clearly numbered, and a dedicated "Validation Checkpoints" section supplies checklists for the batch/destructive operations (so the cap does not apply); falls short of 5 only because explicit validate→fix→retry feedback loops are not spelled out.	4 / 5
Progressive Disclosure	Section headings are well organized and cross-skill references (CONNECTORS.md, benchmark files) are one level deep and clearly signaled, but no bundle files exist and the heavy CLAUDE.md/glossary templates are inlined rather than split into reference files.	3 / 5
	Total	13 / 20 Passed

Description

91%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.

A strong description that pairs a clear capability statement with an unusually rich set of natural-language triggers, fully answering both "what" and "when". The only softness is minor overlap risk with generic memory skills and light buzzword use.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — "Manages a two-layer memory system (hot cache + cold storage)", "tracking keywords, competitors, metrics, and campaign status", "promotion/demotion" — with only minor buzzword softness ("intelligent promotion/demption"); not quite a 5 because the actions hang off a single "Manages" verb rather than a fully enumerated list.	4 / 5
Completeness	Explicitly answers both: "when" via the "Use when the user asks to..." trigger clauses, and "what" via "Manages a two-layer memory system... with intelligent promotion/demotion", matching the score-5 anchor of concrete trigger phrases plus a clear capability statement.	5 / 5
Trigger Term Quality	Eight natural user phrases are quoted verbatim ("remember project context", "save SEO data", "track campaign progress", "save my keyword data", "remember this for next time", "keep track of this campaign"), giving comprehensive coverage of the phrasings a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The SEO/GEO two-layer-memory niche is mostly distinct, but generic phrases like "remember this for next time" and "save my keyword data" create minor overlap risk with general memory/notes skills, keeping it just below a 5.	4 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (772 lines); consider splitting into references/ and linking	Warning
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 31 suspicious	Warning

	Total	13 / 16 Passed

Repository: teeclaw/phorm-nft
Path: .agents/skills/memory-management/SKILL.md
Commit: 02adecb

Reviewed: 6 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.