BC pulse
Use this skill when the user wants to share their AI agent with others, sync files/context to Pulse, search/read/create/edit notes, create shareable agent links, manage shared links, keep their agent's knowledge up to date, set up auto-sync, manage note versions, generate daily briefings, monitor inbox activity, talk to someone else's agent (friend direct or share link), request/accept agent access, bridge from share token to friend connection, check their agent network, or get started with Pulse. Triggers on: 'share my agent', 'share link', 'sync to Pulse', 'upload to Pulse', 'add context', 'search my notes', 'update my agent', 'what does my agent know', 'set up Pulse', 'API key', 'snapshot', 'version', 'auto sync', 'schedule sync', 'keep updated', 'daily brief', 'morning brief', 'inbox monitoring', '/v1/briefing', '/v1/conversations', 'talk to their agent', '/v1/agent/message', '/v1/network/request', '/v1/network/accept', '/v1/network/connect', 'check this agent link', 'my network', 'who visited', or any mention of agent-to-agent communication via Pulse.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Dangerous commands
cmd-shell-rcscripts/inbox-monitor-cron.sh:33Writes to a shell startup fileCALLER_ID=$(echo "$IDENTITY" | jq -r '.profile.userId')
-
low Dangerous commands
cmd-cron-mentionREADME.md:179Mentions editing / listing crontab# crontab -e
Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1072 chars, limit 1024
Process rating: all ten parameters 52/100
- 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
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 13 mutating operations with no state check
- 40Consistency. Frontmatter name (pulse) differs from the folder (pulse-skills)
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 42 steps
- 100Execution cost. Instruction body is 3116 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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
- +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 1072: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -33 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 29 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (17 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.