CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-memory

Cross-interface persistent memory for project context, decisions, conventions, and session handoffs. Use when the user asks 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 mentions persistent memory across Codex, Claude Code, Cursor, VS Code, Craft Agent, or other file-reading agents.

76

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 well-structured, lean, and highly actionable with concrete paths, guards, and validation loops for destructive operations, plus clean one-level-deep reference navigation. The only weakness is mild redundancy across the capability/command/menu listings.

Suggestions

Consolidate the Capabilities table, Commands table, and the 'If no keyword is given' menu into a single operation reference to reduce redundancy and token cost.

The Migrate table and Build step 4 both restate old-format handling; cross-reference Migrate from Build instead of repeating the rules.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence without explaining basic concepts, but the operations appear in three overlapping forms (Capabilities table, Commands table, and the "If no keyword is given" menu) that could be consolidated to trim tokens.

4 / 5

Actionability

Concrete executable guidance throughout — exact directory names, file paths, frontmatter fields, a migration-mapping table, and numeric staleness thresholds (30/60/90 days) — fully actionable for an instruction-only skill.

5 / 5

Workflow Clarity

Each operation is clearly sequenced with explicit validation checkpoints and feedback loops: the Overwrite guard, Migration guard (show planned paths and confirm), and Maintain's ask-before-delete flow satisfy the level-5 anchor for destructive/batch operations.

5 / 5

Progressive Disclosure

Clear overview in SKILL.md with well-signaled one-level-deep references to real bundle files (references/templates.md, display-conventions.md, troubleshooting.md) listed in a Reference Files table with their contents.

5 / 5

Total

19

/

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: third-person voice, explicit what-and-when structure, and an unusually comprehensive set of natural trigger phrases tied to named agents. Minor specificity gap is the only thing keeping it from a perfect profile.

DimensionReasoningScore

Specificity

Names the domain and several concrete memory areas ("project context, decisions, conventions, and session handoffs"), but these are subject domains more than a fully comprehensive list of discrete actions, leaving minor coverage gaps versus the level-5 anchor.

4 / 5

Completeness

Explicitly answers both what ("Cross-interface persistent memory for project context, decisions, conventions, and session handoffs") and when ("Use when the user asks to..." with concrete trigger phrases), satisfying the level-5 anchor.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases ("manage project memory", "initialize .agent-memory", "migrate memory", "save session learnings", "sync memory", "run memory maintenance", "check memory status") plus concrete agent names and file extensions, matching the level-5 anchor's synonym/extension coverage.

5 / 5

Distinctiveness Conflict Risk

Clear niche of cross-interface persistent memory with named-agent triggers and the `.agent-memory` identifier, minimizing overlap risk with other skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
t4sh/skills4sh
Reviewed

Table of Contents

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.