BB tokei-agent
Tokei (tokei.io) is a pre-launch, waitlist and giveaway platform — launch pages, competition giveaways, sweepstakes, referral and viral-loop campaigns, Product Hunt launch drives, Gleam-style and KickoffLabs-style entry pages. This CLI controls them from the command line — list, clone, update, publish and unpublish pages, upload images and video, set prizes, reward tiers and deadlines, restyle pages, and read stats, leaderboards, top referrers, signups, survey responses, winner selections and the webhook event catalog, plus manage webhooks (all 5 events) — all via the Tokei v1 REST API.
Tokei (tokei.io) is a pre-launch, waitlist and giveaway platform — launch pages, competition giveaways, sweepstakes, referral and viral-loop campaigns…
As a process B 72/100 · Nearly there — weak spots: execution cost, progress reporting
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
✓ Guard found no suspicious behaviour. 1 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 19. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 12151 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 72/100
- 0Progress reporting. Says nothing while it works
- 40Execution cost. Instruction body is 12151 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 44 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (32 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)
- +2Single-language instructions
- +3Description length 593: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
- +4Has examples (34 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.