BC client-manager
When user asks to track clients, manage projects, create invoices, log payments, track earnings, manage leads, track time, generate proposals, set follow-up reminders, or view a freelance dashboard. Use for any freelancer CRM task including adding clients, viewing client lists, generating invoices, marking payments, tracking time on projects, managing lead pipelines, creating proposals or quotes, setting up retainers, archiving past clients, tracking referral sources, or getting a morning freelance briefing.
When user asks to track clients, manage projects, create invoices, log payments, track earnings, manage leads, track time, generate proposals, set follow-up…
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8403 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 51/100
- 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
- 40Consistency. Frontmatter name (client-manager) differs from the folder (smart-content-repurposer)
- 40Execution cost. Instruction body is 8403 tokens: crowds the task out of the window
- 60Steps. 180 steps, 5 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 8 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 32 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)
- +3Output format is not stated: the model decides each time
- -215 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 513: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 180 items
- +4Has examples (39 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.