memory

Search past conversations in the agent's history log.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./nanobot/skills/memory/SKILL.md

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 tight, high-signal body: it warns about the path pitfall, describes the log format, and lays out a concrete search strategy with a parameterized example. Its only shortfall is the minor actionability gap of not showing a concrete date/topic narrowing example.

Dimension	Reasoning	Score
Conciseness	Every sentence carries non-obvious operational detail ("a project-relative memory/history.jsonl may belong to a different workspace", "the log is append-only JSONL ... not loaded into context") with zero padding or explanation of concepts Claude already knows. Lean and efficient — every token earns its place.	5 / 5
Actionability	A concrete grep call with real parameters plus specific flag guidance (output_mode="count", fixed_strings=true, head_limit/offset, context_before/context_after) is mostly copy-paste ready. Not a 5 because the example carries a placeholder path and 'narrow by topic or date' lacks one concrete date-filter example, leaving a minor gap.	4 / 5
Workflow Clarity	This is a simple, single-purpose read-only skill under 50 lines, so the simple-skill exception applies: the sequence (take the exact system-prompt path → start broad with output_mode="count" → narrow by topic/date → page with head_limit/offset → add context when nearby entries matter) is unambiguous. No validation loop is required for non-destructive grep searches, so the destructive-operation cap does not apply.	5 / 5
Progressive Disclosure	The skill is under 50 lines with a single well-organized section and no bundle files (references/, scripts/, assets/ are absent), so nothing needs external splitting. All guidance fits comfortably inline, matching the guideline that short skills with no external-reference needs can score 5 on organization alone.	5 / 5
	Total	19 / 20 Passed

Description

48%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 states a clear, narrow capability but stops there: one generic verb, no trigger guidance, and no synonyms for how users would naturally ask for this. It reads like the 'Processes PDF files' tier — accurate but under-sold.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g., 'Use when the user asks what was previously discussed, wants to recall a past decision, or mentions conversation history or the history log.'

List 1-2 more concrete capabilities to raise specificity, e.g., 'Count, filter, and page through past conversations by topic or date, with surrounding context.'

Include natural synonyms users would actually say ('remember', 'recall', 'what did we talk about', 'chat history') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names its domain ("past conversations in the agent's history log") but offers only a single generic action, "Search" — mirroring the anchor example "Processes PDF files". It does not reach the 3 anchor's level of 1-2 concrete, distinct capabilities (e.g., no mention of filtering by date/topic, recalling prior decisions, or paging results).	2 / 5
Completeness	The 'what' is clear ("Search past conversations in the agent's history log"), but there is no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines. It is not a 4 because 'when' is entirely absent rather than merely under-specified.	3 / 5
Trigger Term Quality	"Search", "past conversations", and "history log" are relevant keywords, but common natural phrases users would say ("what did we discuss", "remember", "recall", "chat history", "previously talked about") are missing. It has some relevant keywords but misses common variations, matching the 3 anchor; it is above 2 because the domain terms are on-target rather than generic filler.	3 / 5
Distinctiveness Conflict Risk	The niche — searching the agent's own append-only history log — is fairly distinct with a clear target artifact, giving minor overlap risk only with closely related memory/recall skills. It is not a 5 because without explicit triggers, generic requests like "search the log" or "remember when" could pull in adjacent skills; it is clearly above 3's broader overlap profile.	4 / 5
	Total	12 / 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: HKUDS/nanobot
Path: nanobot/skills/memory/SKILL.md
Commit: 6eccc28

Reviewed: 5 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.