BC win-loss-review
Every month the CRM's closed deals are audited and what they say lands in context/ as one pull request: the ICP verified against won versus lost with a disqualifier, dated insights with counts and denominators, objections from recorded lost reasons, and a client file per closed-won account; a five-line Slack digest says what changed. Never edits a persona, nor the ICP after the first pass. Triggers: "verify our ICP against won and lost deals", "what do closed-lost deals say about who we should not sell to", "keep the context repo current from the CRM every month", "our lost reasons should become objections", "run a monthly win-loss review". Cargo CDK, harness claudeCode, HubSpot, Salesforce, Attio, Slack. Skip when: there is no CRM yet and the context should come from the website, which is web-capture; or you want one account researched before a call, which is research-account.
Every month the CRM's closed deals are audited and what they say lands in context/ as one pull request: the ICP verified against won versus lost with a…
As a process C 56/100 · 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: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5623 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 56/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Result and completion. Does not say what the result is
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 5623 tokens
- 100Steps. 38 steps
- 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 The response is described with custom markup (6 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 890: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Structure: 10 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.