CtrlK
BlogDocsLog inGet started
Tessl Logo

memory-recall

Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this before'. Also use when you see `[memsearch] Memory available` hints injected via SessionStart or UserPromptSubmit. Typical flow: search for 3-5 chunks, expand the most relevant, optionally deep-drill into original transcripts via the anchor format. Skip when the question is purely about current code state (use Read/Grep), ephemeral (today's task only), or the user has explicitly asked to ignore memory.

77

Quality

96%

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

93%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, highly actionable agent prompt: concrete commands for every step, sensible fallbacks for missing tools and vague queries, and a clean section structure with no wasted tokens. The only soft spot is that verification of expanded results is left implicit in the Evaluate/Return steps.

Suggestions

Make result validation an explicit checkpoint: e.g., in the Return step add 'Before returning, confirm each included memory actually addresses the user's question; drop or replace ones that only partially match.'

In the Deep drill step, add a one-line guard such as 'If parse-transcript.py fails or the session file is missing, fall back to the expanded chunk and note the limitation' to close the error-recovery loop.

DimensionReasoningScore

Conciseness

The ~45-line body is lean and assumes Claude's competence — no concept explanations, no padding; every section (collection derivation, steps, unsure-what-to-search fallback, output format) earns its tokens.

5 / 5

Actionability

Fully executable commands throughout: 'memsearch search "<query>" --top-k 5 --json-output --default-collection <collection>', 'memsearch expand <chunk_hash> --default-collection ...', 'python3 __INSTALL_DIR__/scripts/parse-transcript.py <session_id> --turn <turn_id> --context 3', plus concrete ls/grep/cat exploration commands — copy-paste ready for the common cases.

5 / 5

Workflow Clarity

Steps 1-5 are clearly sequenced with an explicit filtering checkpoint ('Evaluate: Skip chunks that are clearly irrelevant') and error-recovery branches (uvx fallback, unfamiliar anchor formats), but validation of expanded results before returning them is implicit rather than an explicit checkpoint — sitting between the 4 and 5 anchors, noticeably above the midpoint.

4 / 5

Progressive Disclosure

A simple, single-purpose skill under 50 lines with no bundle files (no references/, scripts/, or assets/ directories exist; the __INSTALL_DIR__ scripts are install-time paths outside this bundle), and its well-organized sections fully satisfy the simple-skill exception.

5 / 5

Total

19

/

20

Passed

Description

100%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.

An exemplary description: concrete capability listing, literal user-voice trigger phrases, explicit use/skip conditions, and explicit disambiguation from adjacent tools like Read/Grep. All four dimensions sit at the top anchor without padding or over-claiming.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the complete flow — 'Search and recall relevant memories', 'search for 3-5 chunks, expand the most relevant, optionally deep-drill into original transcripts via the anchor format' — which matches the comprehensive-coverage anchor rather than the minor-gaps anchor at 4.

5 / 5

Completeness

It explicitly answers both 'what' ('Search and recall relevant memories from past sessions via memsearch') and 'when' ('Use when the user's question could benefit from historical context... Skip when the question is purely about current code state'), with concrete trigger phrases and explicit skip conditions.

5 / 5

Trigger Term Quality

It includes literal natural user phrasings ('what did I decide about X', 'why did we do Y', 'have I seen this before') plus synonyms ('past decisions, debugging notes, previous conversations, project knowledge, historical context') and even a system-hint trigger ('[memsearch] Memory available'), giving comprehensive natural-term coverage.

5 / 5

Distinctiveness Conflict Risk

It carves out a clear memory-recall niche and explicitly disambiguates from the nearest conflict ('Skip when the question is purely about current code state (use Read/Grep)'), keeping conflict risk minimal.

5 / 5

Total

20

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
zilliztech/memsearch
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.