SKILLEMALL.ai
GitHub ↗ RU Sign in

BD intake

Intake protocol — the craft of turning a vague brief into an approved production plan. Runs phases 1-7 of the agent production contract: 3-5 clarifying questions sized to the user's skill band, content-mode classification, format/template match, memory recall, the reference gate, the style lock, and the plan the user approves before any paid generation. USE WHEN a request opens a NEW project or carries more than one unknown — "make a video about X", "I want one like this <url>", "launch project Y", audience / brand / aesthetic / duration unstated. FIRES BEFORE any other content route. DO NOT FIRE on a follow-up inside a project already scoped, or on an explicit template remix (@template:<slug>) where only the swap is new.

The skillemall take

Skill promises to automate project intake — turn vague briefs into approved production plans through seven clarification phases. Triggers on new projects or when more than one parameter is unknown: audience, style, duration, format. Blocks generation until the user approves the plan.

Files are intact, references check out. No model runs, no sandbox tests. Grade B: content quality 80%, but process logic scored only 39%. The skill hasn't been tested against Claude, Cursor, or the eight other platforms listed. Structure is there, but without live testing it's just a questionnaire.

Install if you need intake automation and can patch gaps yourself.

alecs5am/ralphy Agent Skills author: alecs5am 10 files body ≈ 4 866 tokens Open the sourcegithub.com↗ analyzed 11 h ago

Intake protocol — the craft of turning a vague brief into an approved production plan.

As a process D 39/100 · Unfinished process — References files that are not bundled: ../../../docs/playbooks/agent-production-contract.md, ../art-director/references/location-plate.md, ../scenarist/SKILL.md

ProcedureMarketingAI and agentsMedia and videotype 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
B
92/100
safety, quality, tests
Safety 60%
100
Quality 40%
80
Run on models
none yet
Process rating
D
39/100
Unfinished process
References files that are not bundled: ../../../docs/playbooks/agent-production-contract.md, ../art-director/references/location-plate.md, ../scenarist/SKILL.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

The same skill appears in 1 more place: ralphy

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: 10. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: ../../../docs/playbooks/agent-production-contract.md
  • warning missing-ref reference to a missing file: ../art-director/references/location-plate.md
  • warning missing-ref reference to a missing file: ../scenarist/SKILL.md
  • warning missing-ref reference to a missing file: ../art-director/SKILL.md
  • warning missing-ref reference to a missing file: ../producer/SKILL.md
  • note frontmatter-key unknown frontmatter key "namespace"
  • note edit-residue the text marks something as outdated (lines 11, 143): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 39/100

Will not run. References files that are not bundled: ../../../docs/playbooks/agent-production-contract.md, ../art-director/references/location-plate.md, ../scenarist/SKILL.md
  • 0Tools and files. 5 referenced file(s) missing: ../../../docs/playbooks/agent-production-contract.md, ../art-director/references/location-plate.md, ../scenarist/SKILL.md
  • 0Result and completion. Does not say what the result is
  • 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
  • 30Running it twice. 11 mutating operations with no state check
  • 70Execution cost. Instruction body is 4866 tokens
  • 85Steps. 33 steps, 2 vague phrases
  • 100Failures and branches. 3 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 16 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (11 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)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 3 example trigger phrases
  • +3Description length 731: enough signal without eating the budget
  • +4Structure: 17 headings
  • +3Step-by-step instructions: 33 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (9 of 9)

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