mcpField
T
team-discover

team-discover

github.com/tikalkAgent workflows143185 installsUpdated today
Repository

About team-discover

team-discover is a user-invoked skill for finding relevant team AI directives in a CDR index. It provides a relevance-rated table and reads full modules for high-relevance matches, complementing the automatic per-prompt matching provided by team-boot.

Key features

  1. 01Scans CDR entries for task matches
  2. 02Rates relevance as High, Medium, or Low
  3. 03Reads high-relevance module bodies
  4. 04Includes relevant project-index matches

Use cases

  1. 01Review directives for a complex feature
  2. 02Audit which directives apply to a task

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/tikalk/adlc-team-skills --skill team-discover

After installing, type/team-discoverin Claude Code to confirm it loaded.

Details

From the project README

team-discover

Overview

The CDR index is injected into the system prompt at session start by team-boot. The LLM natively matches CDR descriptors against the current task and reads full module bodies on demand. This native matching happens per prompt without invoking this skill.

Use /team-discover when you want a structured discovery table with explicit relevance assessments — for example, when starting a complex feature or verifying which directives apply.

Relationship to team-boot

team-boot is the session bootstrap: it injects the CDR index into the system prompt via the session_start event hook. Per-prompt discovery matching is native — the LLM matches the injected CDR index against the current message on its own, so team-boot does not invoke this skill as part of its bootstrap loop.

/team-discover is user-invoked: run it when you want an explicit, structured re-scan with a relevance-rated table (complex features, audits, or verifying which directives apply). It is not required for normal operation.

Process

  1. Extract domain, technology, patterns, and actions from the task.
  2. Scan the CDR index for matching entries.
  3. Assess relevance: High / Medium / Low.
  4. Read full module bodies for High-relevance entries.
  5. Output:
IDModuleTypeDescriptorRelevance
CDR-2026-003context_modules/personas/admin.mdPersonaAdmin personaHigh
  1. Include PDR/ADR/ChDR matches from project indexes if relevant.
  2. Include: _Searched N CDRs, M PDRs, K ADRs, C ChDRs, J matches found._

Absent Context

If no CDR index was injected at session start: report Searched 0 CDRs — index not injected (unconfigured project or hook failure), reading workspace memory directly, proceed against docs/adlc/memory/ on disk, and continue the task. Never present on-disk fallback rows as injected context. Recovery: run /team-diagnose.

Unconfigured projects

If team AI directives are not configured, invoke team-setup.

Comments

Markdown supported