SKILLEMALL.ai
GitHub ↗ RU Sign in

AF utility-pm-skill-builder

Guides contributors from a PM skill idea to a complete Skill Implementation Packet aligned with pm-skills conventions. Runs gap analysis, validates through a Why Gate, classifies by type and phase, generates draft files, and writes to a staging area for review before promotion.

product-on-purpose/pm-skills Agent Skills author: product-on-purpose Apache-2.0 5 files body ≈ 4 631 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Guides contributors from a PM skill idea to a complete Skill Implementation Packet aligned with pm-skills conventions.

As a process F 54/100 · Will not run — References files that are not bundled: ../../site/src/content/docs/guides/creating-pm-skills.md, scripts/check-trigger-fixtures.mjs, scripts/check-output-eval-assets.mjs

AnalyzerGitHubData and analyticsAI and agentsOperations and projectstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
100
Quality 40%
80
Run on models
none yet
Process rating
F
54/100
Will not run
References files that are not bundled: ../../site/src/content/docs/guides/creating-pm-skills.md, scripts/check-trigger-fixtures.mjs, scripts/check-output-eval-assets.mjs
Tools and files w 18
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: ../../site/src/content/docs/guides/creating-pm-skills.md
  • warning missing-ref reference to a missing file: scripts/check-trigger-fixtures.mjs
  • warning missing-ref reference to a missing file: scripts/check-output-eval-assets.mjs

Process rating: all ten parameters 54/100

Will not run. References files that are not bundled: ../../site/src/content/docs/guides/creating-pm-skills.md, scripts/check-trigger-fixtures.mjs, scripts/check-output-eval-assets.mjs
  • 0Tools and files. 3 referenced file(s) missing: ../../site/src/content/docs/guides/creating-pm-skills.md, scripts/check-trigger-fixtures.mjs, scripts/check-output-eval-assets.mjs
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 13 mutating operations with no state check
  • 70Failures and branches. 4 branches
  • 70Execution cost. Instruction body is 4631 tokens
  • 100Steps. 84 steps
  • 100Result and completion. Output format and completion criterion are stated
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • high The skill tells the model to perform an irreversible action with no human approval

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 278: enough signal without eating the budget
  • +4Structure: 19 headings
  • +3Step-by-step instructions: 84 items
  • +3Output format is stated explicitly
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.