AF team-projects
Multi-agent project management with task boards, @-mention routing, WBS, and orchestrated team collaboration. Includes a Control UI plugin tab with project dashboard and a right-edge Team Chat drawer for live activity. Enables a coordinator agent to plan projects, break down work into phases and tasks, assign to specialist agents, dispatch via sessions_spawn, and track progress to completion. Use when: (1) managing work across multiple OpenClaw agents, (2) creating project plans with work breakdown structures, (3) assigning and tracking tasks across agents, (4) coordinating multi-agent workflows with dependencies, (5) running team-based projects with progress tracking.
As a process F 44/100 · Will not run — References files that are not bundled: scripts/write-plugin-sdk-entry-dts.ts
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: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/write-plugin-sdk-entry-dts.ts
Process rating: all ten parameters 44/100
- 0Tools and files. 1 referenced file(s) missing: scripts/write-plugin-sdk-entry-dts.ts
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 13 mutating operations with no state check
- 55Failures and branches. 1 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4239 tokens
- 100Steps. 48 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (6 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
- +1No license
- +2Single-language instructions
- +3Description length 677: enough signal without eating the budget
- +4Structure: 43 headings
- +3Step-by-step instructions: 48 items
- +4Has examples (20 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.