agentleFS
ZhixiangLuoZhixiangLuo/10xProductivity/.cursor/skills/colleague-distillation/SKILL.md

colleague-distillation

Skill472 starsChanged 8 months agoMITView on GitHub

Distill a colleague into a reusable AI skill (work + persona) using tool connections — Slack, Slack AI, Jira, GHE, Bitbucket, Confluence, SharePoint, Teams, Outlook, Notion, Linear, Google Docs, and more — without manual paste. Use when the user wants a colleague skill, digital twin of a coworker, or capture of someone's technical voice from workplace systems. Requires tool_connections + 10xProductivity verified_connections (or equivalent .env).

  • Reads credentials

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the same slug and folder layout in both.

    line 41
  2. Distinctive:

    Before searching, pin who the colleague is:

    line 55
  3. Very specific:

    Persona (persona.md): Use a layered structure compatible with colleague-skill:

    line 108
  4. Distinctive:

    Grounding: Prefer quoted paraphrases with source pointers.

    line 116
  5. Very specific:

    Do not exfiltrate secrets, PII bundles, or restricted content into colleagues/ — redact tokens, customer data, and health/financial …

    line 171
  6. Distinctive:

    When unsure whether content is allowed in a repo, ask the user before writing.

    line 172

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

10xProductivity skill: This file is the Cursor entry point for colleague distillation when working in this repo.

Colleague distillation (tool-backed)

Purpose

Produce a colleague skill: structured work knowledge (systems, standards, review style) plus persona (tone, decisions, interpersonal habits), using APIs and search already wired in tool_connections / 10xProductivity — not hand-pasted exports.

Output layout matches the open colleague-skill convention so results can coexist with that generator:

  • colleagues/{slug}/work.md
  • colleagues/{slug}/persona.md
  • colleagues/{slug}/meta.json
  • colleagues/{slug}/SKILL.md (merged invocable skill)

Optional: Clone colleague-skill for its prompts/work_analyzer.md, persona_analyzer.md, work_builder.md, persona_builder.md if you want identical extraction templates; this skill defines what to fetch and where to write.


Prerequisites

  1. Load the relevant 10xProductivity connection docs under tool_connections/ and any allowed private recipes under $TENX_PRIVATE_DIR/personal/.
  2. Load $TENX_PRIVATE_DIR/verified_connections.md — only call tools listed there (or documented in 10xProductivity/tool_connections/ / personal/).
  3. For Jira, use the verified Jira connection documentation and recipes in this repo.
  4. Credentials: source or load $TENX_PRIVATE_DIR/.env (or project .env) before curl / scripts. Never commit secrets.

Cursor vs Claude Code

EnvironmentWhere to put generated filesHow this skill is loaded
CursorRepo root: colleagues/{slug}/.cursor/skills/colleague-distillation/SKILL.md
Claude CodeSame colleagues/{slug}/ under the active project.claude/skills/colleague-distillation/SKILL.md

Use the same slug and folder layout in both; only the skill install path differs.


Slug rules

  • Slug = unique directory name: michael_donnelly, michael_donnelly_2, … (ASCII, underscores).
  • Collisions: Same slug overwrites an existing colleague folder. Disambiguate with _2, _3, or a distinct codename.
  • Store display name and aliases in meta.json, not only in the slug.

Phase 1 — Resolve identity

Before searching, pin who the colleague is:

  1. Active Directory (if configured in tool_connections): resolve email, manager chain, department — use for Jira/Slack account mapping when IDs are unknown.
  2. Slack: From verified_connections.md, use Slack API recipes to resolve @handle → user id (U…) for from:@user / from:U… search syntax.
  3. Jira: Resolve accountId (assignee, reporter, comment author) via Jira user search API — see jira skill.

Record: slack_user_id, jira_account_id, email, ad_cn (as available).


Phase 2 — Pull source material (priority order)

Gather raw excerpts (save under colleagues/{slug}/knowledge/raw/ as .md or .json snippets) with source + URL/ticket/channel + date in each chunk header. Cap volume per source (e.g. last 90–180 days) unless the user asks for full history.

Tier A — Highest signal for “how they work and sound”

SourceWhat to fetchWhy
Slacksearch.messages: from:user, date range, in:#relevant-channels; thread URLs they participated inTone, decisions, pushback, on-call voice
Slack AI (Slackbot DM)Targeted questions: e.g. “Summarize how [Name] argues for design decisions in threads about [topic]”Fast synthesis over large Slack corpus
JiraJQL: assignee, reporter, comment ~, component/team filters; descriptions, comments, status transitionsWork scope, prioritization, written precision
GHEPRs authored, reviewed (/pulls, review comments API); issues filedCode review voice, technical standards
Bitbucket ServerSame pattern as GHE when Bitbucket Server is the primary Git hostSame

Tier B — Depth and standards

SourceWhat to fetchWhy
ConfluencePages created by or substantially edited by them (CQL / search); team runbooks they ownLong-form standards, architecture voice
NotionPages they authored or commented onLong-form async thinking, project context
SharePointDocs and wikis they own or editedStandards docs, team handbooks

Tier C — Optional / role-specific

SourceWhen
Google DriveDocs/slides they own (if verified in verified_connections.md)
PagerDutyOncall/incident behavior
Console / IAHubRelease/ops ownership if building an ops-heavy persona
Microsoft Teams / OutlookIf verified — email/thread tone (handle consent carefully)
Gmail (personal recipe)Only if user explicitly wants email and connection is verified

Tier D — Do not rely on for persona without extra care

  • Raw git blame without PR context — noisy.
  • HR systems — use only for title/team if needed, not personality inference.

Phase 3 — Synthesize (work vs persona)

Work (work.md): Systems, stacks, coding/review conventions, doc habits, Jira/workflow patterns, incident/release behavior — cite patterns, not one-off jokes.

Persona (persona.md): Use a layered structure compatible with colleague-skill:

  1. Layer 0 — Hard rules (non-negotiables: respect, no slurs, no real harassment simulation beyond professional friction the user explicitly asked for).
  2. Identity — role, scope, team context.
  3. Expression — vocabulary, sentence length, directness, humor.
  4. Decisions — risk posture, escalation, “how they say no.”
  5. Interpersonal — meetings, async, conflict.

Grounding: Prefer quoted paraphrases with source pointers; flag low-confidence traits when sample size is small.


Phase 4 — Write artifacts

meta.json (minimal)

{
  "name": "Display Name",
  "slug": "michael_donnelly",
  "created_at": "<ISO8601 UTC>",
  "updated_at": "<ISO8601 UTC>",
  "version": "v1",
  "profile": {
    "company": "",
    "level": "",
    "role": "",
    "email": ""
  },
  "ids": {
    "slack_user_id": "",
    "jira_account_id": ""
  },
  "knowledge_sources": ["slack", "jira", "ghe"],
  "corrections_count": 0
}

SKILL.md (invocable)

YAML frontmatter:

---
name: colleague_{slug}
description: "<Name> — distilled work + persona (tool-sourced)."
user-invocable: true
---

Body: short intro + full work.md + full persona.md + run rules:

  1. Persona decides attitude; work block executes the task.
  2. Output matches persona expression.
  3. Layer 0 never violated.

Optional: also write work_skill.md / persona_skill.md with names colleague_{slug}_work / colleague_{slug}_persona if your host expects split invocations (see colleague-skill skill_writer.py).


Consent and safety

  • Build skills only for legitimate work purposes and policy-compliant use of company tools.
  • Do not exfiltrate secrets, PII bundles, or restricted content into colleagues/ — redact tokens, customer data, and health/financial identifiers.
  • When unsure whether content is allowed in a repo, ask the user before writing.

Outputs checklist

  • colleagues/{slug}/ created with knowledge/raw/ containing sourced excerpts
  • work.md and persona.md complete
  • meta.json with ids and source list
  • SKILL.md merged and invocable
  • User told how to invoke (/{slug} or host-specific command) and how to disambiguate duplicates (_2, _3)

Related skills

  • team_learner — team/domain bootstrap (similar tool sweep, different output shape).
  • skill_creation — promote reusable methodology after validation.
  • jira, tool_connections — all authenticated access.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.