mrkeyoor.com_
Sat 15 Aug 13:43 UTC
LLM Toolsevaluationupdated 15 Aug 2026

colleague-skill

dot-skill, formerly colleague.skill, is a bilingual Chinese-English project with a full English README and install guide. It turns messages, documents, notes, or public research into a reusable agent skill meant to imitate how a colleague, close relationship, celebrity, fictional character, or the user thinks and speaks.

Verdict

dot-skill is an inventive, well-presented method for producing richer character instructions than a few adjectives in a prompt. For public figures, fictional characters, your own material, or a fully consented knowledge-transfer exercise, it is worth exploring. Do not point its collectors at private workplace or relationship archives until you have solved consent, credential storage, retention, and human review outside the tool.

Setup3/5The clone is easy; safe collection and evidence cleanup are real work
Docs4/5Clear English guide, host paths, examples, source matrix, and paper
Community4/5Large interest, recent documentation work, and active issue discussion
Maturity2/5The README calls it a demo and sensitive-data safeguards remain open

Who it’s for

Agent users who want a structured persona built from source material instead of a short character prompt.
Teams preserving a departing expert's documented workflows, review standards, and decision habits with permission.
Researchers studying persona and work-knowledge extraction across Claude Code, Codex, Hermes, OpenClaw, or DeepSeek Harness.
Careful hobbyists creating a private skill from their own writing or from public material about a well-documented figure.

Who it’s NOT for

Organizations that cannot obtain informed consent for employee-message collection: the README supports Slack and Feishu API collection, while the project offers no visible consent or retention policy in its main notes.
Users handling valuable workspace credentials on a shared machine: open issues #112 and #113 say collector configs can be written with permissive file modes and secret prompts echo input to the terminal.
Anyone who needs a faithful replacement for a departed colleague or loved one: the README calls this a demo, and the generated behavior is an inference from selected records, not the person.
DingTalk users who expect dependable automatic message collection: the README says the API cannot retrieve message history and issue #105 questions whether the browser route works.
Teams requiring immutable separation between work knowledge and personality: issue #134 shows that the work-only artifact still tells the model to answer in the colleague's style and refers to a Persona section it does not contain.

Setup reality

Installing the skill itself is a clone into the host's skill directory, and manual files or pasted text can get a first persona built without a service deployment. Useful results take much more work: secure permission to use the material, export and clean it, separate first-person evidence from hearsay, review the generated instructions for unsupported claims, and decide where sensitive output may be stored. Automatic Feishu, Slack, and DingTalk collection requires platform access and credentials; Slack needs an administrator-installed bot and the free plan exposes only 90 days. Python 3.9 or newer is required for helper tools, Hermes has an extra installer step, and every generated skill should be inspected before installation.

A persona compiler, not a digital person

dot-skill takes a body of evidence about someone and produces instructions that an agent host can load as a reusable skill. It began as colleague.skill, aimed at retaining the working habits of a departing teammate, and now covers three families: colleagues, relationships, and celebrities or fictional characters. The repository is bilingual Chinese-English, with a full English README, install guide, and translated entry points for several other languages.

The useful idea is to separate more than tone. A colleague skill can contain both a Persona layer and a Work layer that records scope, procedures, output preferences, and decision habits. Relationship templates look for expression patterns, emotional triggers, conflict, and repair. Celebrity research uses works, interviews, decisions, external evaluations, and a timeline. Generated skills can be corrected through conversation, updated with new files, archived by version, and rolled back. That is more disciplined than asking a model to imitate someone from five adjectives.

It is still an imitation built from selected material. The repository's demos are persuasive illustrations, not evidence that the resulting skill predicts a real person's decisions. A generated profile may amplify a narrow period, mistake group-chat performance for private belief, or turn an author's repeated phrase into an absolute rule. The README itself calls the project a demo. Treat the result as an editable interface to recorded patterns, never as the person's testimony or authority.

Source collection is where the real cost lives

The manual path is approachable. Clone the repository into the supported host's skill directory, invoke /dot-skill, choose colleague, relationship, or celebrity, and supply an alias, description, and source. Claude Code, Codex, Hermes, OpenClaw, and DeepSeek Harness have documented locations or installers. PDF files, screenshots, email archives, Markdown, pasted text, Feishu exports, and WeChat database exports can feed the process. Python helper scripts support research cleanup and generated-skill management.

A meaningful profile needs curation. The project correctly ranks long-form first-person writing and decision records above casual chat or second-hand commentary. Users must remove irrelevant conversations, distinguish what the subject wrote from what others wrote about them, and check whether the selected period represents the person fairly. More text is not automatically better evidence.

Automatic collection raises the setup burden further. Feishu requires an app bot in relevant group chats. Slack requires an administrator-installed bot, and its free plan limits history to 90 days. DingTalk lacks a message-history API, so the project describes a browser route; open issue #105 directly questions whether that route works. WeChat data has to be exported first through separate tools, and issue #127 remains an open request around decrypting backup data.

Privacy is the deciding weakness

This project asks for some of the most sensitive material a developer can handle: private messages, work documents, email, family conversations, and credentials for collaboration platforms. The main README explains source quality but does not present an equally visible consent, minimization, deletion, or retention workflow. A company should not interpret technical access to Slack or Feishu as permission to build a behavioral replica of an employee. A personal user should not assume that participation in a chat grants permission to model another participant.

Two open issues make the operational warning concrete. Issue #113 reports that auto-collector setup uses ordinary terminal input for tokens and passwords, allowing secrets to appear on screen and in session recordings. Issue #112 reports that collector configuration files can inherit permissive modes such as 0644 rather than enforcing owner-only access. Pull requests propose masked prompts and 0600 files, but both issues remained open in the activity inspected for this review. Until the fixes land and are verified, use manual sources or isolate the collectors on a private account with restricted tokens and a strict file umask.

Generated skills need protection too. They distill the input into compact statements that may be easier to browse, copy, or accidentally commit than the original archive. Keep them out of shared repositories, inspect host backup and synchronization behavior, and document who can invoke them. Deleting the source files does not remove conclusions already written into a generated skill.

The architecture is clever, with visible seams

The repository follows the AgentSkills directory format, so it can run as instructions plus local Python tools instead of requiring a hosted backend. Users can inspect the prompts, generated Markdown, version archives, collectors, and installers. The MIT license permits modification, and the technical report explains the earlier colleague-specific architecture.

The family expansion is newer than that paper, however, and the split outputs are not perfectly isolated. Issue #134 shows that a work-only skill can still instruct the model to respond in the colleague's style and refer to a Persona section absent from the artifact. This matters for teams that deliberately want documented expertise without impersonation. It also demonstrates a general limit of prompt-built products: labels such as work-only are behavioral intentions until tests verify the exact generated text.

Health and the recommendation

The last push was August 13, 2026, and an issue about WeChat export was updated August 14. The repository has 34 open issues and pull requests combined, more than 22,000 stars, and no formal GitHub release. Recent commits added host support and documentation, while the most recent non-documentation commit in the inspected history was an April compatibility fix. That is active maintenance, but not a conventional release cadence.

The documentation is energetic and unusually visual, with a source matrix, host paths, examples, project layout, technical report, and multilingual links. It is weaker where the consequences are highest: privacy and credential guidance should be as prominent as persona quality.

dot-skill is best approached as a transparent research and prototyping tool. Use your own writing, public sources, fictional characters, or material covered by explicit consent. For organizational knowledge transfer, write down the governance before collecting anything. If all you need is repeatable work instructions, Anthropic's skills examples avoid the imitation problem; if you need a long-lived agent with memory, Mem0 or Eliza addresses a different and often safer requirement.

Alternatives

ProjectWhat it isPick it when
Anthropic SkillsA collection of agent skills and examples focused on repeatable task instructions rather than imitating a person.pick this instead when you need auditable job procedures and domain workflows without personality synthesis or private-message ingestion.
Mem0A memory layer for agents that stores and retrieves user and conversation facts over time.pick this instead when persistent personalized memory matters more than generating a portable character skill from a fixed evidence set.
ElizaA framework for building and operating character-driven agents with plugins, memory, and multiple channels.pick this instead when you want a full agent runtime and deployment ecosystem rather than a skill generator for existing hosts.

What people are saying

  1. [github-trending] titanwings/colleague-skill

Sources

  1. dot-skill repository and English README
  2. dot-skill detailed install guide
  3. Credential file-permission issue 112
  4. Secret prompt exposure issue 113
  5. Work-only persona leak issue 134