BF saying-no-kindly
Decline requests without damaging relationships or your standing — the fast-clear-warm formula, the alternative-attached no, the no-to-the-boss version (tradeoffs, not refusal), and scripts for the asks that recur. Use when asked how do I say no to this, turn down a request, decline extra work politely, I say yes to everything and drown, push back on my manager, or protect the roadmap from a pet feature. Produces the decline scripts by relationship, the tradeoff framing, and the exact wording tuned to who is asking.
Decline requests without damaging relationships or your standing — the fast-clear-warm formula, the alternative-attached no, the no-to-the-boss version…
As a process F 49/100 · Will not run — References files that are not bundled: ../task-triage-matrix/SKILL.md, ../meeting-prep-pack/SKILL.md, ../recurring-meeting-pruner/SKILL.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../task-triage-matrix/SKILL.md - warning
missing-refreference to a missing file: ../meeting-prep-pack/SKILL.md - warning
missing-refreference to a missing file: ../recurring-meeting-pruner/SKILL.md - warning
missing-refreference to a missing file: ../office-hours-design/SKILL.md
Process rating: all ten parameters 49/100
- 0Tools and files. 4 referenced file(s) missing: ../task-triage-matrix/SKILL.md, ../meeting-prep-pack/SKILL.md, ../recurring-meeting-pruner/SKILL.md
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 7 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 23 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1248 tokens
- 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
- +1No license
- +2Single-language instructions
- +3Description length 521: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 23 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.