team-manager
Create and maintain TeamMember entities — humans and named AI personas that participate in the project with persistent identity, personality, and tiered memory. Use when adding a new persistent team-member (human or named AI), managing the name pool, scaffolding memory trees, or exporting/importing a team-member bundle. Replaces the deprecated actor-profile skill (DEC-20260422_0233-SpryTulip).
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- team-manager
- metadata
- { "processkit": { "id": "SKILL-team-manager", "uses": [ { "skill": "event-log", "purpose": "Log events to keep the audit trail accurate after every write." }, { "skill": "index-management", "purpose": "Query existing entities and keep the SQLite index fresh after writes." }, { "skill": "id-management", "purpose": "Allocate unique entity identifiers via central ID generation." }, { "skill": "role-management", "purpose": "Resolve default_role references against the Role catalog." } ], "layer": 1, "created": 1776816000000, "version": "1.0.0", "category": "processkit", "provides": { "mcp_tools": [ "create_team_member", "get_team_member", "list_team_members", "get_active_interlocutor", "set_active_interlocutor", "update_team_member", "deactivate_team_member", "reactivate_team_member", "reserve_name", "release_name", "list_available_names", "suggest_name", "init_memory_tree", "export_team_member", "export_claude_subagent", "export_claude_subagents", "import_team_member", "check_consistency", "check_all_consistency" ], "templates": [ "team-member-human", "team-member-ai-agent" ], "primitives": [ "TeamMember" ] }, "replaces": [ "SKILL-actor-profile" ], "apiVersion": "processkit.projectious.work/v2" } }
- description
- Create and maintain TeamMember entities — humans and named AI personas that participate in the project with persistent identity, personality, and tiered memory. Use when adding a new persistent team-member (human or named AI), managing the name pool, scaffolding memory trees, or exporting/importing a team-member bundle. Replaces the deprecated actor-profile skill (DEC-20260422_0233-SpryTulip).
02 资源文件 14
- 资产文件assets/agent-card.schema.json869 B
- 资产文件assets/memory-file-header.schema.json897 B
- 资产文件assets/team-member-ai-agent.yaml1.0 KB
- 资产文件assets/team-member-human.yaml1021 B
- 参考文档data/name-pool.yaml1.2 KB
- 参考文档mcp/mcp-config.json207 B
- 参考文档mcp/SERVER.md5.3 KB
- 脚本mcp/server.py107.4 KB
- 脚本scripts/apply_migration_2139.py14.1 KB
- 脚本scripts/consistency.py15.5 KB
- 脚本scripts/export_import.py7.2 KB
- 脚本scripts/memory_tree.py3.6 KB
- 脚本scripts/name_pool.py4.6 KB
- 脚本scripts/test_team_manager.py87.8 KB
03 SKILL.md 正文
Team Manager
Intro
TeamMembers are the persistent participants in the project — named AI personas, services, consultants, and explicitly managed human aliases — that accumulate identity, personality, and tiered memory over time. This skill owns their lifecycle: creation, memory tree scaffolding, a curated international name pool, A2A-compatible Agent Cards, export/import bundles, and consistency checks.
Unlike ephemeral worker invocations (role+seniority dispatches resolved on
the fly and never persisted), TeamMembers live as directory trees on disk:
persona.md + card.json + team-member.md (entity) + tiered memory
subdirectories + optional private/ (gitignored).
Human TeamMembers are privacy-sensitive. Do not auto-create them from
ambient host, git, or harness identity. create_team_member(type="human", ...) stores only the slug as the committed display name by default and
drops email/handle; pass allow_committed_pii=true only after the
human explicitly agrees that their name or contact details may live in
repo-visible files. Store local-only human details under private/, not
in team-member.md.
MCP server. This skill ships a self-contained MCP server at
mcp/server.py(PEP 723 script — requiresuvand Python ≥ 3.10 on PATH). Agent harnesses reach its tools by reading a single MCP config file at startup, so the contents ofmcp/mcp-config.jsonmust be merged into the harness's MCP config and placed at the harness-specific path before this skill is usable.
Overview
Invocation surface
This skill is not a CLI; it is reached entirely via MCP tools served
by mcp/server.py. Tools cluster into six capability groups
(lifecycle, session identity, name pool, memory scaffolding,
export/import, consistency). Every write tool logs an event-log
entry and updates the SQLite index automatically — callers do not log
or reindex by hand. Read tools (get_team_member,
list_team_members, get_active_interlocutor,
get_interlocutor_runtime_binding, list_available_names,
suggest_name, get_team_member_runtime, list_team_member_runtimes,
check_consistency) are side-effect-free and safe to call from any
agent context.
Capability groups
| Group | Tools | Use when |
|---|---|---|
| Lifecycle | create_team_member, get_team_member, list_team_members, update_team_member, deactivate_team_member, reactivate_team_member |
Adding, editing, retiring or restoring a persistent team-member entity |
| Session identity | get_active_interlocutor, get_interlocutor_runtime_binding, set_active_interlocutor |
Showing which persistent TeamMember, if any, is the current harness interlocutor, plus the resolved runtime binding when available |
| Runtime launch | launch_team_member, launch_workitem_assignee, get_team_member_runtime, list_team_member_runtimes, stop_team_member_runtime |
Creating and tracking a harness-consumable TeamMember runtime request with explicit model, status, and write policy |
| Name pool | reserve_name, release_name, list_available_names, suggest_name |
Choosing or rotating an AI persona name; the pool is the canonical source of truth for AI-agent slugs |
| Memory scaffolding | init_memory_tree |
Creating the six tier subdirectories + frontmatter-validated headers under context/team-members/<slug>/ |
| Export / import | export_team_member, export_claude_subagent, export_claude_subagents, import_team_member |
Moving a TeamMember between projects or generating provider-specific adapter files; tarball export redacts confidential/PII memory |
| Consistency | check_consistency, check_all_consistency |
Pre-release health-check; CI validation; ad-hoc audits, including human committed-PII warnings |
Common workflows
Adding a human contributor. Prefer an ephemeral Actor/reference unless
the project really needs a persistent human TeamMember. When persistence
is needed, use a privacy-preserving slug such as human-user or
project-owner: create_team_member(type="human", name="human-user", slug="human-user", ...) → init_memory_tree(slug). No name-pool
interaction; humans use any valid kebab-case slug. Real names, emails,
and handles require allow_committed_pii=true and explicit human consent.
Adding a named AI persona. suggest_name(kind="neutral") →
create_team_member(type="ai-agent", slug=<name>, ...) (auto-reserves
the name) → init_memory_tree(slug) → write persona.md and the
A2A-compliant card.json. The name is now drawn from the pool and
must remain in data/name-pool.yaml until released.
Retiring a persona. deactivate_team_member(slug, reason) (sets
active: false; preserves history) → optionally
release_name(name) to return the slug to the pool. To bring the
persona back, call reactivate_team_member(slug).
Migrating a persona between projects.
export_team_member(slug) → ship the tarball → at the destination
import_team_member(tarball_path). Schema and Agent Card are
re-validated on import; signature presence is required (crypto
verification is deferred).
Showing the active interlocutor.
set_active_interlocutor(id) writes
context/team/session-identity.json with the TeamMember that should be
presented as the harness's main speaker. get_active_interlocutor()
returns a compact label and speaker prefix for status briefings and
session-start UI. This is session identity, not lifecycle state:
TeamMember.spec.active continues to mean whether a TeamMember is
eligible to participate at all.
Use get_interlocutor_runtime_binding(observed_model?, observed_effort?) when the caller can supply the harness's actual
runtime. The tool returns the provider-neutral TeamMember identity, the
model-recommender candidate after local provider gates, the negotiated
harness mode, and an informational mismatch report. processkit cannot
hot-swap an already running primary harness session; unsupported
harnesses therefore fall back to identity-only behavior while still
growing memory on the configured TeamMember.
Launching TeamMember runtimes.
launch_team_member(id, harness?, ...) creates a runtime record under
context/team/runtime-sessions.json and returns a harness-specific
dispatch payload. launch_workitem_assignee(workitem_id, ...) resolves
the WorkItem's TEAMMEMBER-* assignee first and then records the same
runtime contract. Runtime state is separate from WorkItem state:
queued, running, failed, and stopped describe the harness
session, not the work lifecycle.
The MCP server does not spawn host harness processes directly. For
Claude, the dispatch payload names the subagent_type and refreshes the
.claude/agents/<slug>.md adapter by default. For Codex, Aider, and
OpenCode, the payload carries the TeamMember identity, resolved model,
effort, write scope, and MCP/context-write policy for the outer harness
adapter to consume. Use list_team_member_runtimes(active_only=true)
and stop_team_member_runtime(handle) to report and update status.
Exporting Claude Code subagents.
export_claude_subagent(slug) writes one generated adapter to
.claude/agents/<slug>.md; export_claude_subagents() exports all
active non-human TeamMembers by default. The generated file uses
Claude Code's Markdown + YAML frontmatter format, sets model: inherit, and omits tools so Claude Code inherits the main session's
model and permissions. Pass model_policy="resolved" to emit a Claude
model and effort only when processkit routing resolves to an Anthropic
candidate. TeamMember remains the canonical, provider-neutral identity;
.claude/agents/*.md is only an adapter.
Pre-release audit. check_all_consistency() → triage findings by
severity. Errors block release; warnings are advisory. Treat
team.privacy.committed_pii as release-blocking for derived-project
templates and installer output: rotate the TeamMember to an alias or move
the personal data into private/.
Mental model
A TeamMember is a directory tree on disk, not a row in a database.
The entity file (team-member.md / team-member.yaml frontmatter)
is the SQLite-indexed object; persona.md, card.json, and the six
tier subdirectories live alongside it as durable, human-editable
context. Humans/services have no name-pool requirement; AI personas
do. TeamMembers are distinct from ephemeral worker invocations —
those are resolved on the fly by task-router against role+seniority
and never persist as TeamMembers.
Pointers to the full reference
The ## Full reference section below covers the MCP tool contract,
the SQLite-index schema fields, the data/name-pool.yaml document
format, the consistency check codes in greater detail, the export
bundle layout, the migration path from actor-profile
(DEC-20260422_0233-SpryTulip), and the corner cases for memory
sensitivity tagging. Read it before extending the skill or changing
any tool's contract.
ID convention
TeamMember IDs follow a single shape:
TEAMMEMBER-<slug>
where <slug> is the team-member's canonical kebab-case name (e.g.
atlas, alice-chen, thrifty-otter). The slug starts with a letter and
uses only [a-z0-9-]. It is also the directory name under
context/team-members/<slug>/.
For type=ai-agent, the slug must be drawn from the team-manager name
pool (see Name pool below). For type=human and type=service, any
valid kebab-case slug is accepted.
TeamMember types
| type | Example | When to create |
|---|---|---|
human |
Project owner, contributors, reviewers | The first time the person is assigned work, makes a decision, or gets a Binding |
ai-agent |
Atlas, Aria, Kai (named personas) | A persistent AI persona you want to grow over time — with memory, personality, and accumulated lessons |
service |
GitHub Actions, CI bots, deploy pipelines | Automated agents that perform repeat actions and need a stable identity for audit trails |
Do not promote every mention of a person into a TeamMember. And do not create a named AI persona for a one-off dispatch — use an ephemeral role+seniority invocation instead.
Memory tiers
Every team-member directory contains six tier subdirectories under
context/team-members/<slug>/:
| Tier | What lives here | Cadence |
|---|---|---|
working/ |
Task-local scratchpad, active session context | Ephemeral |
journal/ |
Daily journal, episodic entries | Daily consolidation |
knowledge/ |
Semantic knowledge, stable facts, domain notes | Weekly promotion from journal |
skills/ |
Procedural recipes, working style, patterns | As learned |
relations/ |
Per-teammate relationship notes (one file per known teammate) | On interaction |
lessons/ |
Reflected lessons; A-MemGuard-style consensus defense against memory poisoning | Per-task |
Plus private/ (optional, developer-local, gitignored) and three
top-level files: persona.md (identity + personality prompt),
card.json (A2A Agent Card), team-member.md (the entity itself).
Every memory file under a tier subdirectory must carry a frontmatter
block validated against assets/memory-file-header.schema.json —
required keys: tier, source, sensitivity, created.
Name pool & international naming policy
The name pool lives at data/name-pool.yaml (managed by this skill).
It contains three gender-bucket lists (feminine, masculine, neutral) of
international, short, human-friendly first names — ~60 total. Names
from the pool are the canonical identifier source for AI personas.
Reservation lifecycle
suggest_name(kind?)— pick a random available name, optionally filtered by gender bucket. Does not reserve.reserve_name(name, team_member_slug)— mark a name taken by a specific slug. Writes todata/name-pool.yamlatomically.release_name(name)— remove the reservation (e.g. on team-member deletion or re-export).list_available_names(kind?)— enumerate non-reserved names.
For create_team_member(type="ai-agent", ...), the slug must
correspond to a name currently in the pool. The tool auto-reserves on
success.
Consistency checks
check_consistency(slug) returns findings for a single team-member;
check_all_consistency() aggregates across every team-member.
Each finding is {severity, code, team_member, path, message}. Codes:
| Code | Severity | What it checks |
|---|---|---|
team.drift.schema |
error | team-member.yaml frontmatter validates against SCHEMA-team-member |
team.drift.tier_missing |
error | Expected subdirs (knowledge, journal, skills, relations, lessons) exist |
team.drift.dangling_ref |
error | default_role resolves to an existing Role; relationships[].with resolves to known slugs/IDs |
team.name_collision |
error | No two active team-members share name or slug |
team.name.off_pool |
warning | For type=ai-agent, the name must be in the name pool |
team.drift.orphan_file |
warning | No files outside expected tier subdirs / persona.md / card.json / team-member.md / private/ |
team.sensitivity.leak_risk |
warning | Memory files with sensitivity: confidential or pii must live under private/ |
team.private.not_ignored |
warning | Each private/ directory is covered by a .gitignore rule |
team.memory.bad_header |
warning | Memory files under tier subdirs carry required frontmatter keys |
team.card.stale |
warning | card.json name/role/seniority match team-member.yaml |
Export / import
export_team_member(slug, output_path?) builds a tar.gz bundle at
<slug>-export-<YYYY-MM-DD>.tar.gz containing:
persona.mdcard.json(A2A Agent Card, conforms toassets/agent-card.schema.json)team-member.md(the entity)knowledge/,skills/,lessons/
Excludes journal/, relations/, private/ by default. During the
memory-file walk, any file whose frontmatter declares
sensitivity: confidential or sensitivity: pii is redacted (skipped).
import_team_member(tarball_path) extracts to a temp dir, validates the
team-member.yaml against SCHEMA-team-member, validates card.json
against the A2A Agent Card schema, and checks that a signature field
is present on the card (crypto verification is deferred — signature
field presence is a hand-off marker for future work). On success it
copies the tree into context/team-members/<slug>/ and logs
team_member.imported.
Deprecation note
This skill replaces actor-profile (DEC-20260422_0233-SpryTulip).
The ACTOR-<slug> ID class and the create_actor/get_actor/etc.
tools are deprecated in v0.19.0. A migration on context/actors/ runs
in a separate phase; do not modify actor-profile from here.
Gotchas
- Creating a TeamMember for every mention. Reserved for persistent participants — the same rule as Actor. If they have no upcoming WorkItem/Binding/decision, don't promote them.
- Drawing an AI persona name outside the pool.
team.name.off_poolwill warn. Usesuggest_nameorlist_available_namesfirst. - Putting confidential info outside
private/.team.sensitivity.leak_riskcatches it. The tier subdirectories are git-tracked; onlyprivate/is safe for developer-local sensitive context. - Hand-editing
data/name-pool.yaml. Usereserve_name/release_name— the tool preserves the document frontmatter and writes atomically. - Forgetting
init_memory_treeafter create.create_team_memberwrites the entity but does not scaffold the tier subdirectories. Callinit_memory_tree(slug)right after (or passinit_memory=Trueat create time, if implemented). - Putting role+seniority dispatches here. Ephemeral worker
invocations are NOT TeamMembers — they are resolved on the fly via
task-router. Only persistent personas live inteam-members/.
Full reference
MCP tool contract
All fifteen tools are served by mcp/server.py. Their tool
annotations follow the processkit convention checked by
release-audit.mcp_annotations:
| Tool | readOnlyHint | destructiveHint | idempotentHint | openWorldHint |
|---|---|---|---|---|
create_team_member |
false | false | false | false |
get_team_member |
true | false | true | false |
list_team_members |
true | false | true | false |
update_team_member |
false | false | false | false |
deactivate_team_member |
false | true | true | false |
reactivate_team_member |
false | false | true | false |
reserve_name |
false | false | false | false |
release_name |
false | true | true | false |
list_available_names |
true | false | true | false |
suggest_name |
true | false | false | false |
init_memory_tree |
false | false | true | false |
export_team_member |
true | false | true | false |
import_team_member |
false | false | false | false |
check_consistency |
true | false | true | false |
check_all_consistency |
true | false | true | false |
mcp/SERVER.md documents each tool's full input/output schema
including the JSON shape of create_team_member (slug, type,
default_role, name, gender_kind, …) and the Finding schema for
consistency checks ({severity, code, team_member, path, message}).
Entity schema
The TeamMember frontmatter is validated against
SCHEMA-team-member (registered in context/schemas/). Required
fields:
| Field | Type | Notes |
|---|---|---|
id |
string | Must match TEAMMEMBER-<slug> |
slug |
string | [a-z][a-z0-9-]*; equals directory name |
name |
string | Display name; uniqueness enforced by team.name_collision |
type |
enum | human | ai-agent | service |
active |
bool | false after deactivate_team_member |
default_role |
string | null | Resolved against the Role catalog by team.drift.dangling_ref |
created |
ISO8601 | Stamped by create_team_member |
relationships |
list | [{with: <slug-or-id>, kind: <string>, since: <ISO>}]; references resolved by drift check |
Optional fields used by templates: card_path (relative path to
card.json), persona_path (relative path to persona.md),
memory_root (relative path; defaults to the directory itself).
data/name-pool.yaml document format
---
schema: name-pool.v1
managed_by: SKILL-team-manager
updated: <ISO8601>
---
feminine:
- name: aria
reserved_by: TEAMMEMBER-aria # null if available
reserved_at: <ISO8601> # null if available
masculine:
- name: atlas
reserved_by: null
reserved_at: null
neutral:
- name: kai
reserved_by: null
reserved_at: null
Atomic writes are produced by scripts/name_pool.py using a
write-then-rename pattern; the document frontmatter (schema,
managed_by, updated) is always preserved on round-trip. Hand
edits silently break atomicity guarantees and are caught only by
the next consistency check.
Memory tier directory layout
context/team-members/<slug>/
├── persona.md # Identity + personality prompt
├── card.json # A2A Agent Card (assets/agent-card.schema.json)
├── team-member.md # Entity file (frontmatter is the schema target)
├── working/ # Ephemeral, task-local
├── journal/ # Daily entries; consolidated weekly → knowledge/
├── knowledge/ # Stable semantic facts
├── skills/ # Procedural recipes / patterns
├── relations/ # One file per known teammate slug
├── lessons/ # A-MemGuard-style consensus lessons
└── private/ # Optional, gitignored, developer-local
Every memory file under journal/, knowledge/, skills/,
relations/, lessons/, or private/ carries a frontmatter block
validated by assets/memory-file-header.schema.json. Required keys:
tier, source, sensitivity, created. Allowed sensitivity
values: public, internal, confidential, pii. Files tagged
confidential or pii outside private/ raise
team.sensitivity.leak_risk.
Consistency check matrix (recap)
The 10 codes are split between hard errors (block release) and
warnings (advisory). The corresponding implementation lives in
scripts/consistency.py:
| Code | Severity | Implementation function |
|---|---|---|
team.drift.schema |
error | check_schema(slug) |
team.drift.tier_missing |
error | check_tier_dirs(slug) |
team.drift.dangling_ref |
error | check_refs(slug) |
team.name_collision |
error | check_collisions() (cross-slug) |
team.name.off_pool |
warning | check_pool_membership(slug) |
team.drift.orphan_file |
warning | check_orphans(slug) |
team.sensitivity.leak_risk |
warning | check_sensitivity(slug) |
team.private.not_ignored |
warning | check_gitignore(slug) |
team.memory.bad_header |
warning | check_memory_headers(slug) |
team.card.stale |
warning | check_card(slug) |
check_all_consistency() aggregates over list_team_members(active=true)
and returns {summary: {errors, warnings}, findings: [...]}. Use the
summary for CI gating; iterate findings for human-readable triage.
Export bundle layout
<slug>-export-<YYYY-MM-DD>.tar.gz
└── <slug>/
├── persona.md
├── card.json
├── team-member.md
├── knowledge/
├── skills/
└── lessons/
Excludes working/, journal/, relations/, private/. During
the memory walk, any file with frontmatter sensitivity: confidential or sensitivity: pii is skipped (redacted) regardless
of which exported tier it lives in. Implementation:
scripts/export_import.py::export_bundle().
Import contract
import_team_member(tarball_path):
- Extract to a temp dir (cleaned on failure).
- Validate
team-member.yamlagainstSCHEMA-team-member. - Validate
card.jsonagainstassets/agent-card.schema.json. - Require a
signaturefield on the card (presence-only; cryptographic verification is a future-work hand-off marker). - Require the slug to be free locally (no collision with an existing TeamMember entity or active name-pool reservation).
- Copy the tree to
context/team-members/<slug>/. - For
type=ai-agent,reserve_name(name, slug)is called as part of step 6. - Log
team_member.importedviaevent-log.
Failures at any step abort cleanly — the temp dir is removed and no target-side state is mutated.
Migration from actor-profile (DEC-20260422_0233-SpryTulip)
actor-profile is deprecated as of v0.19.0; it is replaced by this
skill. Do NOT modify actor-profile from here. The migration
strategy is:
- New write traffic targets
create_team_memberexclusively. - Existing
ACTOR-<slug>IDs continue to be readable via theactor-profileMCP tools through the deprecation window. - A separate migration phase (tracked by its own MIG-* entity)
converts each Actor under
context/actors/into a TeamMember undercontext/team-members/<slug>/, preserving ID history viareplacescross-references. - After the migration completes, the
actor-profileskill is removed entirely; release-audit will then start flagging any remainingACTOR-*references as dangling.
The frontmatter replaces: [SKILL-actor-profile] records the
relationship; downstream skills should depend on team-manager,
not actor-profile, in their uses: blocks.
Referenced source files
| Path | Purpose |
|---|---|
mcp/server.py |
MCP server entry point (PEP 723) |
mcp/SERVER.md |
Per-tool input/output schema reference |
mcp/mcp-config.json |
Harness merge block for stdio launch |
scripts/consistency.py |
All 10 consistency check implementations |
scripts/export_import.py |
Tarball build + import validation pipeline |
scripts/memory_tree.py |
init_memory_tree scaffolding logic |
scripts/name_pool.py |
Atomic reserve/release/list/suggest |
scripts/test_team_manager.py |
Pytest suite covering tools + scripts |
data/name-pool.yaml |
The canonical name pool document |
assets/agent-card.schema.json |
A2A Agent Card schema |
assets/memory-file-header.schema.json |
Memory file frontmatter schema |
assets/team-member-human.yaml |
Template for type=human |
assets/team-member-ai-agent.yaml |
Template for type=ai-agent |
Extension points
- New TeamMember type. Add a new value to the
typeenum inSCHEMA-team-member, ship a template underassets/, extend the name-pool policy if a curated slug source is needed, and update theteam.name.off_poolcheck to skip the new type if no curated pool applies. - New memory tier. Add the directory to
init_memory_tree, document it in the Memory tiers table, and extendcheck_orphansto recognise it. Decide whether export should include or redact it. - New consistency check. Add a function in
scripts/consistency.pyreturninglist[Finding], register it in the dispatcher, and document the code + severity in the matrix above. CI surfaces it on the next release-audit run.
Corner cases
- Slug collision on import. Hard error; the importer never
overwrites an existing TeamMember directory or reservation. To
re-key a persona on import, rename the export tarball's inner
directory +
team-member.mdslug field before importing. - Name reserved with no TeamMember. Possible if a previous
create_team_memberfailed afterreserve_namebut before entity write. Surfaced bycheck_all_consistency()asteam.drift.dangling_refagainst the pool. Resolve byrelease_name(manual triage, not auto-cleanup). private/not gitignored.team.private.not_ignoredwarning. Addcontext/team-members/<slug>/private/(or a glob parent) to.gitignore. The skill never writes.gitignoreautomatically — the warning is the action prompt.- Card / entity drift.
team.card.stalewarning whencard.json'sname/role/seniorityno longer matchteam-member.mdfrontmatter. Re-export and re-import is the blunt fix; targeted re-write ofcard.jsonis the surgical fix. - Reactivating a deactivated member whose name was released.
reactivate_team_memberwill re-reserve the name if it is still free; if another persona has taken it, the call errors and the caller must pick a new slug (or wait for the colliding persona to be deactivated).
04 同仓库更多 Skills
standard-ui-design
暂无简介
standard-agent-use
Company standard for working with AI agents. Use when deciding what to delegate to agents, capturing open work, keeping agent memory or knowledge notes, improving an agent workflow, or introducing agent work in a team or for a client.
standard-agent-building
暂无简介
skill-management
Manage Skill package manifests as v1 ontology entities.
schema-management
Manage generated processkit schema contracts through deterministic MCP rebuild and inspection workflows.
proposition-management
Record claims, risks, beliefs, world facts, WSJF estimates, and assumptions through the Proposition interface.