remember

Explicitly save important knowledge to auto-memory with timestamp and context. Use when a discovery is too important to rely on auto-capture.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./engineering-team/self-improving-agent/skills/remember/SKILL.md

Quality

Content

82%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 content is a strong, actionable single-purpose skill: copy-paste ready commands, a clear sequenced workflow with a real validation checkpoint, and lean prose that assumes Claude's competence. The main slack is minor conciseness overlap between sections and the absence of an explicit error-recovery loop in the workflow.

Suggestions

Consolidate the 'When to Use' table and 'Tips' section, which overlap with the Usage examples, to tighten conciseness toward a 5.

Add a brief error-recovery note to the workflow (e.g., what to do if the MEMORY.md write fails or the file is missing) to strengthen workflow clarity.

Resolve the minor inconsistency where the description mentions 'timestamp and context' but the body says entries 'don't need timestamps, IDs, or metadata'.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with no padding about what memory is; only minor trims are possible (the 'When to Use' table and 'Tips' slightly overlap with the usage examples). Matches anchor 4 ('Efficient; minor instances of over-explanation that could be trimmed') rather than the fully lean anchor 5.	4 / 5
Actionability	Provides copy-paste ready, executable guidance: a concrete MEMORY_DIR path formula, a grep dedup command, an append template, and exact warning/confirmation output blocks covering common cases. Matches anchor 5 ('Fully executable; copy-paste ready code or commands').	5 / 5
Workflow Clarity	A clear 5-step sequence (parse, check duplicates, write, suggest promotion, confirm) with a genuine validation checkpoint (duplicate check prompting user update-vs-add) and a 180-line capacity guard. It lacks an explicit error-recovery loop (e.g., write failure handling), so it sits at anchor 4 rather than 5; the destructive/batch cap does not apply since this is non-destructive.	4 / 5
Progressive Disclosure	No bundle files exist, and the single-purpose content is self-contained with well-organized sections (Usage, When to Use, Workflow, What NOT to use, Tips). At ~95 lines with a sizable 'When to Use' table, structure is good but slightly above the under-50-line simple-skill threshold, so anchor 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

62%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 clearly states what the skill does and provides an explicit 'Use when' trigger, giving it solid completeness and distinctiveness. Its main weakness is specificity and trigger-term quality: it names only one action and uses somewhat internal phrasing ('auto-capture', 'discovery') rather than natural user terms.

Suggestions

Add 1-2 more concrete actions to the description (e.g., 'append to MEMORY.md and check for duplicates') to lift specificity.

Replace or augment internal phrasing ('auto-capture', 'discovery') with natural user terms like 'remember this', 'save this fact', or 'note this for future sessions'.

Make the 'when' clause more concrete with user-utterable trigger phrases (e.g., 'Use when the user says "remember this" or wants a fact preserved across sessions').

Dimension	Reasoning	Score
Specificity	Names the domain (auto-memory) and one concrete action ('save important knowledge') but lists no further specific actions like append/dedup/formatting, matching anchor 3. It does not list several specific actions (4) and is more than minimally naming the domain (2).	3 / 5
Completeness	Answers both 'what' ('Explicitly save important knowledge to auto-memory with timestamp and context') and 'when' ('Use when a discovery is too important to rely on auto-capture'). The 'when' is explicit but abstract rather than concrete user-utterable trigger phrases, so it sits at anchor 4 rather than 5.	4 / 5
Trigger Term Quality	Includes a 'Use when...' trigger with 'discovery' and 'important knowledge', but the phrasing 'too important to rely on auto-capture' leans on Claude-internal jargon and misses natural user synonyms like 'remember' or 'save this fact'. Matches anchor 3 (some relevant keywords, missing common variations).	3 / 5
Distinctiveness Conflict Risk	The explicit-save-to-auto-memory niche is mostly distinct from other skills with only minor overlap risk with general auto-memory tooling, matching anchor 4. It is not fully crisp/concrete enough for anchor 5's 'minimal conflict risk'.	4 / 5
	Total	14 / 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: alirezarezvani/claude-skills
Path: engineering-team/self-improving-agent/skills/remember/SKILL.md
Commit: 19392f7

Reviewed: ~8 hours 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.