SKILLEMALL.ai
GitHub ↗ RU Sign in

AC voice-builder

Build a personalised voice profile inside a Codex or Claude project from a short interview plus 3 to 5 sample pieces of writing. Works for any content format: LinkedIn posts, newsletters, essays, emails, blog posts, tweets, or any other published writing. Use this skill at the start of any project where the user wants the assistant to learn who they are and how they write before drafting new content. Trigger whenever the user says "build my voice", "learn my voice", "set up my content system", "onboard me", "train on my writing", "train on my posts", "I want Claude to sound like me", or drops a batch of writing samples into chat at the start of a project. Also trigger for first-time users who need a voice foundation before writing anything. Always produces two files (about-me.md and voice.md) saved into the project root.

charlie947/social-media-skills Agent Skills author: charlie947 MIT 2 files body ≈ 3 057 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Build a personalised voice profile inside a Codex or Claude project from a short interview plus 3 to 5 sample pieces of writing.

As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

GeneratorWriting and documentsAI and agentsSoftware developmenttype 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
96/100
safety, quality, tests
Safety 60%
100
Quality 40%
90
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

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

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 59/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 12 mutating operations with no state check
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 60Failures and branches. 2 branches
    • 85Steps. 44 steps, 1 vague phrases
    • 100When it triggers. States when to use and when not to
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3057 tokens
    • 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

    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 832: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 7 example trigger phrases
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 44 items
    • +4Has examples (4 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.