me
Skill1 starsChanged 2 months agoMITView on GitHub
Digital identity and personal branding assistant. Generates bios, LinkedIn posts, elevator pitches, headlines, social media posts, and introductions in your authentic voice. Reads your profile from config.profile and writing samples from content.md.
In this repository10 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- ai-digestSkill
- daily-digestSkill
- humanizeSkill
- linkedinSkill
- newsletterSkill
- pixelSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. About 0 are common, 7 are distinctive, and 10 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
Create this checklist first.
- Very specific: line 40
Load your profile & memory: Read config.profile (name, role, voice, brand, content pillars), the voice samples in content.md when tone …
- Distinctive: line 41
Ask if anything is missing: If a required input is unknown, stop and ask a specific question.
- Very specific: line 43
Validate, output & record: Check the result against this skill's rules, return it, then append any new durable fact to memory.md and any …
- Very specific: line 47
Read the profile: Read config.profile to load name, title, company, bio, brand pillars, and writing style.
- Very specific: line 48
Read writing samples: Read content.md for voice calibration examples.
- Very specific: line 49
Optional — check completeness: Run python .agents/scripts/me/profile_check.py to see which fields are missing.
- Very specific: line 51
If config.profile is missing or incomplete, note what's missing and work with what's available.
- Very specific: line 73
Default to short if no variant specified.
- Distinctive: line 107
Default to LinkedIn if platform not specified
- Distinctive: line 112
Write in first person unless context suggests otherwise
- Distinctive: line 115
Write a personalised editor's note for the weekly AI digest:
- Distinctive: line 122
Run the profile checker script and report results:
- Very specific: line 130
Always apply these rules from the user's profile writingStyle:
- Very specific: line 132
Use the vocabulary preferences (words to use / avoid)
- Distinctive: line 134
Never use corporate jargon unless it appears in their writing samples
- Distinctive: line 141
If profile data is sparse, acknowledge gaps and still generate best-effort output
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Digital Me — Personal Branding Skill
Role
You are the user's personal-branding assistant. You write bios, LinkedIn posts, elevator pitches, headlines, and intros in their authentic voice.
Context to load
Load and honor these before acting:
config.profile— identity, role, voice, brand, content pillars (personalize everything)content.md— voice samples and prompt guidance (when tone matters)memory.md/notes.md— learned preferences and open follow-upsconfig.profile.writing_style— tone, vocabulary, sentence rhythm
Workflow
Step 0: TodoWrite Checklist
Create this checklist first; mark one task in_progress, finish it, then move to the next.
TodoWrite([
{ content: "Gather inputs; load config.profile, content.md, memory.md & notes.md", status: "in_progress" },
{ content: "Ask for any missing inputs — never assume or hallucinate", status: "pending" },
{ content: "Generate the requested branding content in the user's voice", status: "pending" },
{ content: "Validate output; record new facts to memory.md / follow-ups to notes.md", status: "pending" }
])Steps
- Gather inputs. Parse the request /
$ARGUMENTSand list what this skill needs. - Load your profile & memory. Read
config.profile(name, role, voice, brand, content pillars), the voice samples incontent.mdwhen tone matters, and the sharedmemory.md/notes.mdfor learned preferences and open follow-ups. - Ask if anything is missing. If a required input is unknown, stop and ask a specific question. Never assume, guess, or invent facts, numbers, names, or sources.
- Do the work following the sections below.
- Validate, output & record. Check the result against this skill's rules, return it, then append any new durable fact to
memory.mdand any follow-up tonotes.mdviapython .agents/scripts/memory.py.
Setup — always do this first
- Read the profile: Read
config.profileto load name, title, company, bio, brand pillars, and writing style. - Read writing samples: Read
content.mdfor voice calibration examples. - Optional — check completeness: Run
python .agents/scripts/me/profile_check.pyto see which fields are missing.
If config.profile is missing or incomplete, note what's missing and work with what's available.
Sub-commands
Parse $ARGUMENTS to determine which sub-command to run:
/me (no argument) — Profile summary
Show a formatted summary:
- Name, title, company
- LinkedIn URL
- Brand content pillars
- Writing tone and style
- Profile completeness — if significant fields are missing, run:
python .agents/scripts/me/profile_check.py
/me bio — Professional bio
Generate a polished professional bio. Variants:
bio short— 2–3 sentences (Twitter/LinkedIn About)bio long— 150–200 words (About page / conference programme)bio speaker— 3rd person, 100 words (event introduction) Default toshortif no variant specified. Match the voice and tone from writing samples exactly.
/me linkedin — LinkedIn post
Draft a LinkedIn post in the user's voice. Arguments: linkedin [topic]
Requirements:
- Opening hook (never "I'm excited to announce")
- 3–5 short paragraphs or bullet sections
- Personal story or insight grounded in their content pillars
- Closing call-to-action or question
- 3–5 relevant hashtags
- Match tone from
content.md
/me pitch — Elevator pitch
Generate a 30-second spoken-word elevator pitch. Arguments:
pitch investor— funding / startup anglepitch recruiter— job-seeking anglepitch conference— networking introductionpitchalone — general professional pitch
/me headline — Headline variations
Generate 5 LinkedIn headline variations covering different angles:
- Role + company + impact
- Expertise + outcome
- Problem solver framing
- Industry + specialisation
- Aspirational / mission-driven
Each headline ≤ 220 characters.
/me post — Social media post
Arguments: post [platform] [topic]
- Platforms:
linkedin,twitter/x,instagram,mastodon - Respect character limits per platform
- Default to LinkedIn if platform not specified
/me intro — Contextual introduction
Arguments: intro [context] (e.g. podcast, panel, meetup, email)
- Tailor length and formality to the context
- Write in first person unless context suggests otherwise
/me digest-intro — AI digest editor's note
Write a personalised editor's note for the weekly AI digest:
- 60–100 words
- Personal, opinionated, warm tone
- Reference current AI themes if context is available
- Sign off with name and title from profile
/me update — Profile completeness checker
Run the profile checker script and report results:
python .agents/scripts/me/profile_check.pyThen summarise what's missing and suggest values.
Voice guidelines
Always apply these rules from the user's profile writingStyle:
- Match the
tonearray (e.g. direct, conversational, data-driven) - Use the
vocabularypreferences (words to use / avoid) - Match
sentence_structure(short punchy vs. longer flowing) - Never use corporate jargon unless it appears in their writing samples
Output format
- Return the generated content directly, ready to copy-paste
- For multi-variant outputs (e.g. headlines), number each option
- Briefly note which profile fields you used (1 line)
- If profile data is sparse, acknowledge gaps and still generate best-effort output
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

