agent-memory

Persist project decisions, conventions, and session handoffs as reviewable markdown in `.agent-memory/`. Use when asked to "manage project memory", "initialize .agent-memory", "migrate memory", "build memory from docs", "save session learnings", "sync memory", "run memory maintenance", "check memory status", or "onboard a new developer"; when `.agent-memory/` or `AGENTS.md` memory pointers are in play; when sharing project context with another developer or reviewing project memory in a pull request; or when context "forgets between sessions". Sync reconciles files already in the checkout. Not for memory leaks, RAM usage, or human memory.

Quality

83%

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

Quality

Content

71%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 a well-structured, actionable instruction-only skill with strong progressive disclosure and concrete operational detail. Its main weakness is redundancy across the Capabilities/Commands and Initial Assessment/Assessment Checklist sections, and the absence of explicit validate-retry feedback loops for destructive operations.

Suggestions

Merge the Capabilities and Commands tables into a single table (keyword, operation, outcome) to remove the near-duplicate rows.

Collapse the Initial Assessment and Assessment Checklist sections into one list of routing questions to eliminate the overlapping prompts.

For destructive operations (Migrate, Maintain), add an explicit validate→fix→retry feedback loop alongside the existing ask-for-confirmation gates.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept over-explanation, but the Capabilities table and Commands table are near-duplicates, and the Initial Assessment section overlaps heavily with the Assessment Checklist — these padded redundancies could be merged.	3 / 5
Actionability	Gives concrete, executable guidance — specific directory lists (user/, feedback/, decisions/...), staleness thresholds (context/ >30 days, sessions/ >60 days), and frontmatter fields — but delegates the frontmatter schema and templates to references rather than inlining the key specifics.	4 / 5
Workflow Clarity	Each operation has a clear numbered sequence with confirmation checkpoints (overwrite guard, migration guard, deletion confirmation), but the destructive ops rely on ask-before-act gates rather than explicit validate→fix→retry feedback loops.	4 / 5
Progressive Disclosure	The body is a clear overview with a Reference Files table and inline links to four one-level-deep reference files (all verified present) plus an evals catalog; detail is appropriately split out and navigation is easy.	5 / 5
	Total	16 / 20 Passed

Description

95%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 strong: it states concrete capabilities, provides abundant natural trigger phrases, answers both what and when, and disambiguates adjacent domains. Its only minor gap is not surfacing the full migrate/build/maintain capability list inline.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — "Persist project decisions, conventions, and session handoffs as reviewable markdown" and "Sync reconciles files already in the checkout" — but stops short of enumerating the full capability set (migrate, build, maintain) that the body exposes.	4 / 5
Completeness	Explicitly answers both what ("Persist project decisions, conventions, and session handoffs as reviewable markdown in `.agent-memory/`") and when ("Use when asked to...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Lists nine natural trigger phrases ("manage project memory", "save session learnings", "onboard a new developer", etc.) plus contextual triggers like "forgets between sessions", covering the phrases a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (reviewable project memory in `.agent-memory/`) and adds a "Not for memory leaks, RAM usage, or human memory" disambiguation, minimizing wrong-skill triggering.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: t4sh/skills4sh
Path: skills/agent-memory/SKILL.md
Commit: fe99a33

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.