CC cm-release-notes-humanizer
Turn a raw git log, PR title list, or changelog dump into customer-facing release notes that read like a human wrote them. Detects categories (new feature / improvement / fix / breaking change / removed), filters internal/refactor noise, groups items by user value, rewrites every line from "Added X" to user-benefit framing, and generates per-audience versions (in-app changelog, email blast, developer changelog, marketing tweet, status-page note). Covers tone modulation, emoji rules, version numbering schemes, and template patterns from Linear, Stripe, Vercel, Figma, Tailwind, and Notion. Triggers on "release notes", "changelog", "what's new", "version notes", "humanize changelog", "rewrite release", "v1.2 release", "ship notes", "product update post", "patch notes", "semver", "calver".
Turn a raw git log, PR title list, or changelog dump into customer-facing release notes that read like a human wrote them.
As a process C 62/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, consistency
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 · 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
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5163 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 89, 100, 175, 242): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 62/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 26 mutating operations with no state check
- 40Consistency. Frontmatter name (cm-release-notes-humanizer) differs from the folder (release-notes-humanizer)
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5163 tokens
- 85Steps. 59 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100When it triggers. States when to use and when not to
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- -216 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 13 example trigger phrases
- +3Description length 796: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 59 items
- +3Output format is stated explicitly
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.