BC lattice
Initialize and manage Lattice organizations — a file-based operating system for AI agent teams that enables stable, long-running iterative development through an 8-phase pipeline. Core strengths: (1) File-driven state keeps agents on track across sessions — no context loss, no drift, tasks complete reliably over hours or days. (2) Three-tier failure handling (model escalation → peer consult → auto-triage) automatically unblocks stuck agents without human intervention. (3) Per-phase model configuration — use strong models for thinking-heavy phases (planning, review), cost-efficient models for token-heavy phases (implementation, testing), optimizing token cost. (4) Multi-project parallel execution with cron scheduling — run several projects simultaneously, each on its own cadence. Triggers: lattice, org framework, pipeline setup, agent team, multi-agent project, 8-phase pipeline, new org, new project, department setup, pipeline orchestrator, long-running tasks, model escalation, peer consult, auto-triage, token optimization.
As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- 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: 30. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1039 chars, limit 1024
Process rating: all ten parameters 58/100
- 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
- 30Running it twice. 9 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. No external tools needed
- 100Steps. 65 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1977 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (7 tags): a typed call is more reliable
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)
- +3Description length 1038: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 16 headings
- +3Step-by-step instructions: 65 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.