AF alter-agent-channel
Use when an agent needs to coordinate with itself across restarts and across its own concurrent sibling sessions. Covers persisting session state so a later session picks up where this one stopped, advisory locks over shared files and branches, asking your own principal a structured question and collecting the answer, watching a live event stream, and handing units of work between your own sessions and trusted specialist daemons. Trigger phrases include "hand off to my next session", "persist my session state", "coordinate with my other sessions", "claim a lock on this file", "ask my principal a question", "delegate this unit of work", "what other sessions are running".
Covers persisting session state so a later session picks up where this one stopped, advisory locks over shared files and branches, asking your own principal a…
As a process F 30/100 · Will not run — weak spots: steps, result and completion, when it triggers
How to improve
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 30/100
- 0Steps. Prose only: no discrete steps
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1998 tokens
- 100Progress reporting. Reports progress
- low 10 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 678: enough signal without eating the budget
- +4Structure: 11 headings
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.