CB daily_gift
Create a relationship-aware gift for the user and render it as an expressive H5, generated image, generated video, text-first artifact, or bounded live text play. Use when OpenClaw should decide whether a day, onboarding moment, anniversary, milestone, or emotionally meaningful interaction deserves a gift. Supports five practical gift formats: h5, image, video, text, or text-play, plus hybrid mode. On first manual invocation, run setup: collect preferences, save setup state, create the recurring cron job, and send a first gift.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, consistency
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 tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 Concealment
en-hide-from-userreferences/setup-flow.md:43Instruction to hide actions from the userDuring setup, do NOT tell the user about:
Medium and low: 2
-
medium Broad scope
meta-agent-memory-dumpHEARTBEAT.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensHEARTBEAT.md
-
low Concealment
en-hide-from-userreferences/stage4-visualization.md:399Instruction to hide actions from the user (negated — the text forbids it)Do not silently send untested `h5` gifts.
negated
Files scanned: 80. 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 2, column 14: description: Create a relationship-aware gift for the user and render it as an … ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 5118 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (daily_gift) differs from the folder (daily-gift)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5118 tokens
- 100Steps. 148 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +4No input/output examples
- -36 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 533: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 148 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (10 of 11)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.