memory-discipline

The session loop that makes agentmemory pay off, recall before starting work, save at decision points, learn from corrections. Use when starting a nontrivial task, after settling a decision or debugging a gotcha, or whenever deciding if something belongs in memory.

Quality

88%

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

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.

A dense, actionable discipline skill: concrete tool invocations, a moment-keyed workflow with a built-in feedback loop, and clean single-file structure. The only slack is mild redundancy between the Workflow, Checklist, and Anti-patterns sections.

Suggestions

Fold the Checklist into the Workflow as inline checkpoints, or trim it to only items not already stated as workflow steps, to remove the restatement.

Consider merging the Anti-patterns WRONG/RIGHT pair into the relevant workflow step (it currently rephrases steps 1-2 and 5).

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's intelligence — no tutorial padding, tool calls shown as minimal JSON — but the Checklist and Anti-patterns restate points already made in the Workflow, a minor trim opportunity.	4 / 5
Actionability	Copy-paste-ready JSON tool calls with realistic params (query/project/limit, content/concepts/files) plus named tools (memory_smart_search, memory_save, memory_lesson_recall) cover the common cases.	5 / 5
Workflow Clarity	Five clearly sequenced steps keyed to explicit moments (task start, decision settling, correction, before repeating, session end), with a feedback loop via lesson recall and a reinforcing checklist.	5 / 5
Progressive Disclosure	A single well-organized file with clearly signaled one-level-deep references (../_shared/TROUBLESHOOTING.md, the See also skills); no nesting or buried content, easy to navigate.	5 / 5
	Total	19 / 20 Passed

Description

83%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 tight, well-structured description that states the capability and gives explicit, natural trigger conditions. Slightly abstract verbs ('recall', 'learn from corrections') keep specificity just short of comprehensive.

Suggestions

Sharpen the action verbs toward concrete tool behavior, e.g. 'search memory at task start, save decisions with reasons as they settle, hand corrections to the lesson skill'.

Add one or two common synonyms (e.g. 'remembering decisions', 'project memory') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'recall before starting work, save at decision points, learn from corrections' — naming the domain and specific behaviors, with only minor gaps in coverage.	4 / 5
Completeness	Explicitly answers both what ('The session loop that makes agentmemory pay off...') and when via a concrete 'Use when starting a nontrivial task, after settling a decision or debugging a gotcha...' clause.	5 / 5
Trigger Term Quality	Includes natural phrases a user or agent would say — 'starting a nontrivial task', 'settling a decision', 'debugging a gotcha', 'deciding if something belongs in memory' — with a few synonyms missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (agentmemory discipline) with distinct triggers; minor overlap risk with the closely related recall/remember/lesson skills it explicitly hands off to.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rohitg00/agentmemory
Path: plugin/skills/memory-discipline/SKILL.md
Commit: e04ba88

Reviewed: 4 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.