remember

Capture friction as methodology notes. Three modes — explicit description, contextual (review recent corrections), session mining (scan transcripts for patterns). Triggers on "/remember", "/remember [description]".

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%

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

A thorough, highly actionable skill with clear sequenced workflows and verification checkpoints, but it is verbose and monolithic — duplication and inline philosophy/templates bloat a ~535-line file that would benefit from progressive disclosure.

Suggestions

Split the reusable note/MOC templates and category reference tables into a bundled reference file (e.g., references/TEMPLATES.md) and link to it from the body, reducing the ~535-line monolith and enabling one-level-deep progressive disclosure.

Remove duplication to tighten the body: the category table is repeated (Explicit Mode Step 1 and Methodology Note Design) and Rule Zero is stated twice — consolidate each to one canonical location.

Trim the conceptual/essay sections ('The Methodology Learning Loop', 'Rule Zero: Methodology as Canonical Specification') to the minimum needed for action; they explain system philosophy rather than instruct.

Dimension	Reasoning	Score
Conciseness	Mostly actionable but ~535 lines with repetition (the category table appears twice; Rule Zero is stated twice) and essay-like philosophy sections ('The Methodology Learning Loop') that could be tightened without losing clarity.	2 / 3
Actionability	Provides executable commands ('ls -1 ops/methodology/*.md 2>/dev/null', 'grep -rl "^category: [CATEGORY]" ops/methodology/ ...') and copy-paste note/output templates throughout, with only a single empty placeholder code block (Session Mining Step 6).	3 / 3
Workflow Clarity	Each mode has a clearly numbered step sequence (Explicit 1-6, Contextual 1-5, Mining 1-7) with verification checkpoints (dedup in Step 2/Step 4, 'Wait for user confirmation') and error-recovery edge cases.	3 / 3
Progressive Disclosure	Well-organized into sections but monolithic — all templates, category tables, and philosophy are inline in one ~535-line file with no split into bundled reference files, fitting the 'content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

85%

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, specific description that states concrete capabilities across three modes and includes an explicit trigger clause. Its only gap is trigger-term coverage, which omits the --mine-sessions/--mine activation forms documented in the body.

Suggestions

Add the session-mining trigger forms to the description's trigger clause — e.g., 'Triggers on "/remember", "/remember [description]", "/remember --mine-sessions"' — so all three documented modes have explicit activation cues.

Add one or two natural-language trigger phrases beyond the slash command (e.g., 'when capturing a correction' or 'to remember a workflow fix') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete modes — 'explicit description, contextual (review recent corrections), session mining (scan transcripts for patterns)' — matching the multi-specific-action anchor rather than the single-action anchor 2.	3 / 3
Completeness	States both what ('Capture friction as methodology notes') and when via an explicit trigger clause ('Triggers on "/remember"...'), satisfying the explicit-trigger requirement that prevents a cap at 2.	3 / 3
Trigger Term Quality	Includes the primary natural trigger ('Triggers on "/remember", "/remember [description]"') but omits the documented --mine-sessions/--mine variants, so common activation variations are missing.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (friction capture as methodology notes) with a distinct '/remember' slash-command trigger unlikely to collide with other skills.	3 / 3
	Total	11 / 12 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 (535 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: agenticnotetaking/arscontexta
Path: skill-sources/remember/SKILL.md
Commit: 2acfd5c

Reviewed: 3 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.