team-discover
Skill145 starsChanged 21 days agoMITView on GitHub
Use when explicit manual re-discovery of team context modules is wanted beyond the injected CDR index (/team-discover) — produces a structured match table with relevance assessments.
In this repository48 other files it gives its agents.
- architect-analyzeSkill
- architect-bootSkill
- architect-clarifySkill
- architect-implementSkill
- architect-initSkill
- architect-specifySkill
- writing-skillsSkill
- change-bootSkill
- change-clarifySkill
- change-initSkill
- change-publishSkill
- change-specifySkill
- evals-analyzeSkill
- evals-clarifySkill
- evals-implementSkill
- evals-initSkill
- evals-specifySkill
- evals-validateSkill
- factory-cleanSkill
- factory-initSkill
- factory-intentSkill
- factory-learnSkill
- factory-missionSkill
- factory-orchestratorSkill
- factory-queueSkill
- factory-releaseSkill
- factory-reviewSkill
- factory-runbookSkill
- factory-setupSkill
- factory-ticketsSkill
- mission-briefSkill
- product-analyzeSkill
- product-bootSkill
- product-clarifySkill
- product-implementSkill
- product-initSkill
- product-roadmapSkill
- product-specifySkill
- team-bootSkill
- team-constitutionSkill
- team-diagnoseSkill
- team-initSkill
- team-levelupSkill
- team-repairSkill
- team-setupSkill
- team-skillsSkill
- workspaceSkill
- tech-radar-bootSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Use /team-discover when you want a structured discovery table with explicit relevance assessments — for example, when starting a complex …
- Distinctive: line 36
Read full module bodies for High-relevance entries.
- Very specific: line 48
If no CDR index was injected at session start: report Searched 0 CDRs — index not injected (unconfigured project or hook failure), reading …
- Very specific: line 52
If team AI directives are not configured, invoke team-setup.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
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
- Extract domain, technology, patterns, and actions from the task.
- Scan the CDR index for matching entries.
- Assess relevance: High / Medium / Low.
- Read full module bodies for High-relevance entries.
- Output:
| ID | Module | Type | Descriptor | Relevance |
| CDR-2026-003 | context_modules/personas/admin.md | Persona | Admin persona | High |
- Include PDR/ADR/ChDR matches from project indexes if relevant.
- 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.
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.