AF workplace
Manage multiple workplaces (project directories) with multi-agent orchestration, isolated memory, and inter-agent communication. Use when the user mentions: workplace init/list/switch/scan/status/agents/export/import, managing projects, switching between codebases, multi-agent workflows, agent handoff, kernel agent, workspace structure, deploy environments, or any variation of "workplace" commands. Also triggered by /workplace slash command. Auto-detects .git folders as workplaces. Each workplace has its own agents, memory, skills, and deployment configs in a .workplace/ directory. Syncs context to Cursor, Claude Code, and OpenCode. Interactive Telegram/Discord UI with inline buttons for switching workplaces, starting agents, and deploying.
As a process F 51/100 · Will not run — References files that are not bundled: assets/bin/workplace-server-{os}-{arch}
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Dangerous commands
cmd-pipe-to-shellscripts/build.sh:18Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)echo "❌ Rust toolchain not found. Install via: curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh"
detectorcode literal
Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: assets/bin/workplace-server-{os}-{arch}
Process rating: all ten parameters 51/100
- 0Tools and files. 1 referenced file(s) missing: assets/bin/workplace-server-{os}-{arch}
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 15 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Steps. 45 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2399 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (9 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)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 750: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.