CC myr
Capture, search, verify, export, import, and synthesize Methodological Yield Reports (MYRs) for OODA-based intelligence compounding. Use when: (1) installing MYR on a node, (2) storing yield from OODA cycles, (3) searching prior yield before new work, (4) operator-reviewing MYR quality, (5) exporting/importing signed MYRs between nodes, (6) running the HTTP server for live peer sync, (7) managing network peers, (8) verifying remote peers, (9) generating weekly digests, (10) integrating MYR with an agent memory system, or (11) configuring auto-approval for verified peers. Triggers: "install MYR", "store a MYR", "what did we learn about", "weekly yield", "export yield", "import yield", "methodological yield", "MYR", "peer sync", "start MYR server", "verify peer", "announce to peer".
As a process C 55/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 3
-
high Dangerous commands
cmd-persistenceSKILL.md:162Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/com.myr.server.plist
Medium and low: 2
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:26Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/JordanGreenhall/myr-system/main/install.sh | bash
-
medium Dangerous commands
cmd-persistenceSKILL.md:127Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)Create `~/Library/LaunchAgents/com.myr.server.plist`:
quoted
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 3, column 14: description: Capture, search, verify, export, import, and synthesize Methodolog… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 55/100
- 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. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 100Steps. 42 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3031 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 18 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)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +3Description length 791: enough signal without eating the budget
- +4Structure: 36 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (28 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.