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.

75

Quality

93%

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

86%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 body is a well-structured, actionable retrieval workflow with executable commands, a fallback for sandbox lock errors, and a clear output format. The only trim opportunity is the repeated MDIR env-expansion prefix in the 'When unsure' section, and the workflow lacks an explicit validation feedback loop though its read-only nature makes that a minor gap.

Suggestions

Factor the repeated `MDIR="${MEMSEARCH_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.memsearch}"` prefix into a single assignment in the 'When unsure what to search' section so the three example commands share it instead of repeating it verbatim.

Add an explicit checkpoint after the Evaluate step (e.g., 'if fewer than 2 results survive, broaden the query and re-search') to give the workflow a concrete feedback loop rather than only an expand-failure fallback.

DimensionReasoningScore

Conciseness

Largely lean with no concept over-explanation, but the 'When unsure what to search' section repeats the verbatim `MDIR="${MEMSEARCH_DIR:-...}"` prefix three times across consecutive commands — a minor instance of padding that could be factored out; not verbose enough to drop to 3.

4 / 5

Actionability

Fully executable, copy-paste-ready commands with specific flags throughout — `memsearch search "<query>" --top-k 5 --json-output --collection <collection>`, `memsearch expand <chunk_hash> --collection ...`, `bash __INSTALL_DIR__/scripts/parse-rollout.sh <rollout_path>`, plus a fallback `cat <source_file>` — covering the common cases.

5 / 5

Workflow Clarity

Clear numbered sequence (Project Collection → Search → Evaluate → Expand → Deep drill → Return) with an explicit fallback for expand failures, but lacks a formal validate-then-retry feedback loop; the read-only retrieval nature means the destructive/batch cap does not apply, placing this above 3 but below 5.

4 / 5

Progressive Disclosure

Self-contained body under 50 lines with no local bundle files (the `__INSTALL_DIR__/scripts/*` paths are install-dir scripts, not bundle files) and well-organized sections (Project Collection, Steps, When unsure, Output Format), matching the simple-skills exception for clear organization without external references.

5 / 5

Total

18

/

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.

The description is exemplary: it states concrete actions, provides natural trigger phrases users would actually say, answers both what and when, and includes explicit skip guidance that sharply reduces conflict risk. Voice is correctly third person throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Search and recall relevant memories', 'search for 3-5 chunks, expand the most relevant, optionally deep-drill into original transcripts' — matching the comprehensive-coverage anchor; it is not merely 'several specific actions with minor gaps' (4).

5 / 5

Completeness

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...') with concrete trigger phrases and explicit skip guidance, matching the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural terms including synonyms and example user phrasings — 'what did I decide about X', 'why did we do Y', 'have I seen this before', 'historical context, past decisions, debugging notes' — plus the `[memsearch] Memory available` hint; matches the anchor for full coverage including synonyms.

5 / 5

Distinctiveness Conflict Risk

Clear niche (memsearch memory recall) with distinct triggers and explicit skip-when guidance ('Skip when the question is purely about current code state (use Read/Grep)'), minimizing conflict risk; matches the clear-niche anchor.

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.

Validation16 / 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.