SKILLEMALL.ai
GitHub ↗ RU Sign in

CB idea-to-blueprint

Turn a raw product, app, bot or feature idea into one evidence-backed build blueprint (researched stack, epics, Given/When/Then criteria, tests) that coding agents build one epic per session.

The skillemall take

The skill promises to transform a raw idea into a full build blueprint: tech stack, epics, BDD criteria, tests. Fourteen files, one script, nearly six thousand body tokens. Grade C on review: quality 72, process 73. No critical errors, though medium and low findings aren't detailed in the report. No model runs or sandbox testing.

Ready for Claude and Hermes. The concept works—structure an idea into tasks for an agent to write one epic per session. Files are in place, syntax is clean. Scores aren't high but not critical. Install if you need this kind of upfront planning. If you need guaranteed output, wait for a fresher version.

sickn33/agentic-awesome-skills Hermes author: sickn33 MIT 14 files · 1 script body ≈ 5 976 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Turn a raw product, app, bot or feature idea into one evidence-backed build blueprint (researched stack, epics, Given/When/Then criteria, tests) that coding…

As a process B 73/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice

ProcedureSoftware developmentAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code Hermes Agent
JSON
Technical rating
C
89/100
safety, quality, tests
Safety 60%
100
Quality 40%
72
Run on models
none yet
Process rating
B
73/100
Nearly there
Inputs and preconditions w 11
0
Running it twice w 4
30
Result and completion w 14
40
the three weakest of ten parameters · all ten

The same skill appears in 2 more places: agentic-awesome-skills, agentic-awesome-skills

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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: 14. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 191 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning body-long SKILL.md body ≈ 5976 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "risk"
  • note frontmatter-key unknown frontmatter key "source"
  • note frontmatter-key unknown frontmatter key "source_type"
  • note frontmatter-key unknown frontmatter key "source_repo"
  • note frontmatter-key unknown frontmatter key "date_added"
  • note frontmatter-key unknown frontmatter key "tools"
  • note frontmatter-key unknown frontmatter key "license_source"

Process rating: all ten parameters 73/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 14 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 65Failures and branches. 3 branches
  • 70Execution cost. Instruction body is 5976 tokens
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 71 steps
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 191: enough signal without eating the budget
  • +4Structure: 26 headings
  • +3Step-by-step instructions: 71 items
  • +4Has examples (6 code blocks)
  • +4Reference files are cited in the instructions (10 of 10)
  • +3All 1 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.