Workspace Memory Benchmark Analysis
Use when the user wants to run workspace-memory benchmarks, interpret retrieval results, or map benchmark failures to likely ranking, lineage, or fallback defects before optimizing the system.
Install
$ agentstack add skill-fightzy-simple-skills-workspace-memory-benchmark-analysis ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-fightzy-simple-skills-workspace-memory-benchmark-analysis) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Workspace Memory Benchmark Analysis
Use this companion skill when the job is to run the workspace-memory benchmark suite and turn results into concrete optimization guidance.
Scope
This skill analyzes benchmark output for workspace-memory-skill.
Primary paths:
scripts/benchmarks/workspace_memory/runner.pyscripts/benchmarks/workspace_memory/scoring.pytests/workspace-memory-skill/benchmark_fixtures/.agents/skills/workspace-memory-skill/scripts/query_memory.py
Workflow
- Run the benchmark suite and any focused pytest checks needed for the task.
- Read suite output at both total and bucket levels.
- Inspect failed cases and their
stdoutreasons. - Classify the problem before proposing code changes.
- Recommend the smallest next retrieval change and the exact verification to rerun.
Interpretation Guide
- low
recall_at_k: retrieval did not find the right candidate set - low
mrrortop_hit: ranking is wrong even if recall is acceptable - low
layer_hit: derived layers are losing to raw sessions forbidden_hit: sparse or constrained queries are leaking irrelevant resultsfalse_positive: no-match handling is too permissive
Use bucket names to separate failure families such as:
current-statelineagenorms-orderingnegativeexact-id
Output
For each failure group, report:
- affected cases
- observed retrieval order
- likely cause
- smallest recommended change
- verification command
Do not stop at aggregate pass/fail counts.
Verification
Run:
python -m scripts.benchmarks.workspace_memory.runner tests/workspace-memory-skill/benchmark_fixturespython -m pytest tests/workspace-memory-skill/test_workspace_memory_benchmark.py -q
If optimization work is requested, use these findings to justify the next retrieval edit and rerun the same commands after the change.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: fightZy
- Source: fightZy/simple-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.