Context

Use the pk-doctor skill to run the aggregator health check and resolve

Append-only event log — the probabilistic record of everything that happened in the project. Use whenever something notable happens that the project should remember — work items created/transitioned, decisions recorded, bindings changed, incidents occurred, releases shipped.

Aggregator health-check for a processkit-managed repository. Runs a fixed suite of detect-only checks over the live context/ tree plus src/context/ drift and surfaces ERROR / WARN / INFO findings in a single report. Use when the user invokes `/pk-doctor`, asks "is this repo healthy", or has just finished an upgrade and wants a sanity pass. Detect-only by default; `--fix` / `--fix-all` opt in to scoped repairs that route through existing MCP write tools only — doctor never hand-edits files under `context/`.

Semantic versioning releases — version bumps, changelogs, tags, publishing. Use when preparing a new release: deciding the version bump, drafting the changelog, tagging the commit, and publishing to the project's distribution channel.

Aggregator health-check for a processkit-managed repository. Runs a fixed suite of detect-only checks over the live context/ tree plus src/context/ drift and surfaces ERROR / WARN / INFO findings in a single report. Use when the user invokes `/pk-doctor`, asks "is this repo healthy", or has just finished an upgrade and wants a sanity pass. Detect-only by default; `--fix` / `--fix-all` opt in to scoped repairs that route through existing MCP write tools only — doctor never hand-edits files under `context/`.

Project processkit agent-card Artifacts into canonical public agent-card JSON files. Use when publishing an agent identity, endpoint, capability, or interoperability card from repository context into a runtime-visible file.

Aggregator health-check for a processkit-managed repository. Runs a fixed suite of detect-only checks over the live context/ tree plus src/context/ drift and surfaces ERROR / WARN / INFO findings in a single report. Use when the user invokes `/pk-doctor`, asks "is this repo healthy", or has just finished an upgrade and wants a sanity pass. Detect-only by default; `--fix` / `--fix-all` opt in to scoped repairs that route through existing MCP write tools only — doctor never hand-edits files under `context/`.

Session-start meta-skill that enforces the 1% rule: before any action on a processkit entity or context/ file, if there is even a 1% chance a processkit skill applies, you MUST check skill-finder first. Load this skill at the start of every session that may involve processkit work. Use when beginning a new task, when unsure which skill applies, or when you are about to edit context/, create an entity, or run an MCP tool.

Aggregator health-check for a processkit-managed repository. Runs a fixed suite of detect-only checks over the live context/ tree plus src/context/ drift and surfaces ERROR / WARN / INFO findings in a single report. Use when the user invokes `/pk-doctor`, asks "is this repo healthy", or has just finished an upgrade and wants a sanity pass. Detect-only by default; `--fix` / `--fix-all` opt in to scoped repairs that route through existing MCP write tools only — doctor never hand-edits files under `context/`.

Reconcile repository issues, pull requests, merge requests, local git state, commits, and pushes across GitHub, GitLab, Gitea, Forgejo, Codeberg, Bitbucket, Azure DevOps, and SourceHut.

Session-start meta-skill that enforces the 1% rule: before any action on a processkit entity or context/ file, if there is even a 1% chance a processkit skill applies, you MUST check skill-finder first. Load this skill at the start of every session that may involve processkit work. Use when beginning a new task, when unsure which skill applies, or when you are about to edit context/, create an entity, or run an MCP tool.

Route a task description to the right processkit skill, project-specific process override, and MCP tool in a single deterministic call — use this at the start of every processkit domain task.

Session-start meta-skill that enforces the 1% rule: before any action on a processkit entity or context/ file, if there is even a 1% chance a processkit skill applies, you MUST check skill-finder first. Load this skill at the start of every session that may involve processkit work. Use when beginning a new task, when unsure which skill applies, or when you are about to edit context/, create an entity, or run an MCP tool.

Navigation aid for the processkit skill catalog — maps natural-language cues and task types to the right skill. Read this when you are unsure which skill applies to the current task, when the user names a task without naming a skill, or at session start when orienting to an unfamiliar project. Always the first skill to consult; never the last.

Semantic versioning releases — version bumps, changelogs, tags, publishing. Use when preparing a new release: deciding the version bump, drafting the changelog, tagging the commit, and publishing to the project's distribution channel.

Compose a provider-neutral AI team by tiering accessible models on cost-efficiency, capability, latency, and governance, then mapping the 8 processkit role archetypes onto catalog Roles + RoleSlots inside a chartering Scope. Use when bootstrapping a new project team, rotating after a provider change, or quarterly rebalancing. Triggers: "create my AI team", "compose a team", "rebalance the team", "review the team".

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).

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).

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).

Create and maintain Actor entities — humans and AI agents that participate in the project. Use when adding a new collaborator (human or agent) to the project, updating their preferences/expertise, or querying who does what.

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).

Expose the processkit MCP tool surface through a single stdio server. Use for harnesses that eagerly start every configured MCP server, such as Codex, while keeping per-skill MCP servers available.

Compose a provider-neutral AI team by tiering accessible models on cost-efficiency, capability, latency, and governance, then mapping the 8 processkit role archetypes onto those tiers. Use when bootstrapping a new project team, rotating after a provider change, or quarterly rebalancing. Triggers: "create my AI team", "compose a team", "rebalance the team", "review the team".

Generate unique entity IDs following the project's configured format. The write-side foundation that every entity-creating skill depends on. Use whenever a new entity is being created and needs an ID, or when validating an ID format, or to inspect the project's ID configuration.

Generates a post-release blameless retrospective from project signals — synthesizing DORA-like metrics, WorkItem outcomes, session timeline, and drift deltas into a structured Artifact + LogEntry. Use at the end of a release cycle when asked to run a retro, "post-release review", "retrospective", or "post-mortem".

Detect-only pre-release validation sweep over the processkit content tree. Walks entity files, SKILL.md definitions, MCP server tools, and cross-references, then emits a single human-readable report with ERROR / WARN / INFO counts. Use when the user invokes `/pk-release-audit`, before tagging a release, or any time you need a comprehensive structural health check beyond what pk-doctor covers. Detect-only; never modifies any file under `context/`.

Expose the processkit MCP tool surface through a single stdio server. Use for harnesses that eagerly start every configured MCP server, such as Codex, while keeping per-skill MCP servers available.

Generates a post-release blameless retrospective from project signals — synthesizing DORA-like metrics, WorkItem outcomes, session timeline, and drift deltas into a structured Artifact + LogEntry. Use at the end of a release cycle when asked to run a retro, "post-release review", "retrospective", or "post-mortem".

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).

Inspect, plan, and invoke safe cleanup for runtime-manager-owned state without binding the workflow to a specific host orchestrator or agent provider.

Inspect, plan, and invoke safe cleanup for runtime-manager-owned state without binding the workflow to a specific host orchestrator or agent provider.

Author a new processkit skill end-to-end — use-case interview, frontmatter, body sections, Gotchas, and trigger-phrase generation.

Facilitates team or project retrospectives — what worked, what didn't, action items. Use at the end of a sprint, milestone, or project phase to reflect on what went well, what didn't, and what to try next.

Audit an existing processkit skill against the 5 Skill Killers, the Agent Skills standard, and Anthropic's troubleshooting playbook, producing a categorized findings report and draft Gotchas.

Record decisions with rationale, alternatives, and consequences — the ADR pattern as a primitive. Use when a consequential choice is made — architecture, tooling, process, scope, trade-off. Capture WHY, not just WHAT.

Manage Gate entities — validation checkpoints that WorkItems, scopes, or policy applications must pass (code review, security scan, tests). Use when defining or updating a checkpoint for v2 workflow surfaces — code review, tests green, security scan, stakeholder approval.

Captures, reviews, and promotes Note entities — the lightweight knowledge capture primitive in processkit. Notes are quick-capture units (thoughts, insights, questions, references) that are reviewed periodically and promoted to WorkItems, DecisionRecords, or other primitives when they ripen. Use when the user says "remember this", "note that", "I had an idea", or when running a periodic note review session.

Build and maintain a structured personal-context portfolio for the project owner — identity, working style, goals, team, decision patterns. Includes both an interview protocol for bootstrapping and observable-signal patterns for incremental refinement. Use to bootstrap an owner profile (interview), to refine an existing profile (target one file), or to incrementally update the profile based on observed patterns from a normal session (the agent watches for signals and proposes additions when evidence accrues).

Create and maintain Role entities — named sets of responsibilities that actors can fill. Use when defining a new role in the project (developer, reviewer, tech-lead, release-manager) or updating an existing role's responsibilities.

Writes a structured standup update as a session.standup LogEntry — capturing what was done, what is in progress, what comes next, and any blockers. Use when the user says "write a standup", "standup update", "what did I do today", "write a status update for the team", or at the end of a session on projects that run daily standups.

Generates a concise status briefing after session-start reconciliation — synthesizing current state, open decisions, key risks, and today's priority actions. Use at session start, for "pk-resume", a briefing, catch-up, or today's focus.

Orchestrate multi-agent workflows with task decomposition, role assignment, handoff protocols, and per-session context budgeting.

Review and prune the project context — archive completed work, summarize stale entries, and propose disabling unused skills.

SQLite-backed index over all entity files in the project. The read-side foundation for every other MCP server. Use whenever an agent needs to look up entities by ID, kind, state, or text — instead of grepping the filesystem.

Manage Scope entities — bounded containers grouping related work (sprint, milestone, project, quarter). Use when creating or updating a grouping boundary — sprint, milestone, quarter, project, release — that other entities will reference.

Write an end-of-session handover LogEntry capturing current state, open threads, next action, and git context for session continuity.

Plan and execute hot-to-cold processkit context archiving while keeping archived entity metadata queryable through the shared index.

Systematic refactoring with Fowler's catalog, GoF patterns, and code smell detection. Use when restructuring code without changing behavior — cleaning up smells, applying patterns, reducing duplication, or preparing a module for an upcoming feature.

Recommend the right AI model for a task by scoring candidates across six dimensions (Reasoning, Engineering, Speed, Breadth, Reliability, Governance) and displaying a spider-chart profile.

Manage Binding entities — scoped, temporal, many-to-many relationships between v2 entity surfaces. Use when a relationship needs scope, time, or its own attributes — e.g. 'Alice is the tech lead for project X from Jan to June' or 'the security gate applies to this release WorkItem only on the main branch'.

Systematically challenges a plan, decision, or proposal — identifying assumptions, failure modes, and stronger alternatives. Use when asked to critique a plan, stress-test an idea, find weaknesses in a proposal, or when the user says "what am I missing" or "argue against this."

Legacy/migration guidance for v1 Process entities — declarative workflow definitions with roles, gates, and a definition of done. In v2, use process-instance WorkItems plus Artifact-backed definitions instead of creating new Process records.

Provider-neutral processkit MCP gateway. Use when a harness should see one processkit MCP surface while processkit keeps per-skill servers canonical and available.

Discover supply-chain manifests, run structured supply-chain audits, and export SBOMs through a dedicated MCP surface.

Create, retrieve, query, and update Artifacts — tangible deliverables produced by the project. Use when storing or retrieving documents, designs, datasets, build outputs, slide decks, or any completed deliverable that should be registered in the project catalog.

Manage Category entities — taxonomies and classification schemes that group other entities by type, area, tier, etc. Use when defining a new classification axis (priority levels, bug severity, feature tier, product area) that other entities will be tagged with.

Turn observed run outputs into eval-spec Artifacts, paired Gates, and policy bindings. Use when creating or calibrating automated, human, or LLM-as-judge eval gates for processkit workflows.

Legacy/migration guidance for v1 Schedule entities. In v2, define recurring cadences as Binding(type=time-window) records with recurrence conditions instead of creating new Schedule records.

Create, transition, query, and link WorkItems — tasks, stories, bugs, epics. Use when the user asks to add, update, query, or link work items — backlog items, tasks, bugs, user stories, or epics.

Manage Migration entities — pending, in-progress, and applied transitions between upstream source versions. Use when an upstream source bumps version (processkit, a host installer, or a community package), when a user wants to draft a migration plan, when an agent needs to reason about pending migrations, or when working through an in-progress migration.