AF hierarchical-agent-memory
Scalable memory architecture with hybrid topic-based working memory and optional time-based episodic recall. Provides structured MEMORY.md routing table, topic files for active projects, contact files, and configurable daily/weekly/monthly/yearly distillation layers. Use when the agent needs durable, organized long-term memory that survives compaction and scales across projects, contacts, and time horizons. For per-channel session isolation, install the companion skill agent-session-state. Upgrading from v2.x? Existing files are preserved — the agent will guide you through adding topic-based working memory alongside your current structure.
As a process F 44/100 · Will not run — References files that are not bundled: topics/bluecat-mcp.md, topics/rpz-article.md, contacts/jane-doe.md
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: topics/bluecat-mcp.md - warning
missing-refreference to a missing file: topics/rpz-article.md - warning
missing-refreference to a missing file: contacts/jane-doe.md
Process rating: all ten parameters 44/100
- 0Tools and files. 3 referenced file(s) missing: topics/bluecat-mcp.md, topics/rpz-article.md, contacts/jane-doe.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 70Failures and branches. 16 branches
- 100Steps. 33 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3412 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 647: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.