plugins

ALWAYS invoke this skill when diagnosing the health of a spec-tree or spx environment, when checking whether the SessionStart hook fired for the current session, or when troubleshooting a missing session identity, worktree claim, or unreachable spx CLI. NEVER guess why session state is missing without running these checks first.

ALWAYS invoke this skill when diagnosing the health of a spec-tree or spx environment, when checking whether the SessionStart hook fired for the current session, or when troubleshooting a missing session identity, worktree claim, or unreachable spx CLI. NEVER guess why session state is missing without running these checks first.

ALWAYS invoke this skill when diagnosing the health of a spec-tree or spx environment, when checking whether the SessionStart hook fired for the current session, or when troubleshooting a missing session identity, worktree claim, or unreachable spx CLI. NEVER guess why session state is missing without running these checks first.

ALWAYS invoke this skill when writing or fixing tests for Python. NEVER write or fix Python tests without this skill.

ALWAYS invoke this skill when selecting the next executable slice to implement or deciding which spec-tree nodes /apply should build next from an implementation plan. NEVER choose the next nodes by ad hoc selection — this skill scopes an existing plan to demonstrable value before /apply runs.

ALWAYS invoke this skill when writing or fixing tests for Python. NEVER write or fix Python tests without this skill.

ALWAYS invoke this skill when writing or fixing tests for Python. NEVER write or fix Python tests without this skill.

SKILL.md audit methodology preloaded by the skill-auditor agent. The main conversation reaches this audit only through that agent.

Subagent-configuration audit methodology preloaded by the subagent-auditor agent. Dispatch subagent-auditor to audit subagent configuration files; the main conversation reaches this audit only through that agent.

ALWAYS invoke this skill when creating, editing, or improving SKILL.md files.

ALWAYS invoke this skill when creating, editing, or configuring subagents. NEVER create subagents without this skill.

Skill authoring standards enforced across all creating and auditing skills. Loaded by other skills, not invoked directly.

Python testing standards enforced across all skills. Loaded by other skills, not invoked directly.

ALWAYS invoke this skill before implementing any spec-tree work item. NEVER write code, tests, or architecture for a spec-tree node without this skill.

ALWAYS invoke to close a spec-tree session or merge lifecycle closeout — archive claimed sessions, decide session-file creation, prepare continuation context, and produce operator-useful closeout — only once its goal is met with no continuation remaining, the user halted work, context is exhausted, or an external blocker prevents the next action. NEVER invoke while do-able in-scope work remains, and NEVER create a spec-tree session file without this skill.

ALWAYS invoke this skill at the beginning of each session, after every compaction, and before answering spec-tree workflow or session-continuity questions when the live SPEC_TREE_FOUNDATION marker is absent. NEVER read, create, or modify any file in this repository other than CLAUDE.md without loading this skill and all its references first.

Agent prompt writing conventions enforced across all creator and auditor skills. Loaded by other skills, not invoked directly.

SKILL.md audit methodology preloaded by the skill-auditor agent. The main conversation reaches this audit only through that agent.

Custom agent-configuration audit methodology preloaded by the subagent-auditor agent. Dispatch subagent-auditor to audit custom agent configuration files; the main conversation reaches this audit only through that agent.

ALWAYS invoke this skill when creating, editing, or improving SKILL.md files.

ALWAYS invoke this skill when creating, editing, or configuring custom agents. NEVER create custom agents without this skill.

Skill authoring standards enforced across all creating and auditing skills. Loaded by other skills, not invoked directly.

ALWAYS invoke this skill before implementing any spec-tree work item. NEVER write code, tests, or architecture for a spec-tree node without this skill.

ALWAYS invoke to close a spec-tree session or merge lifecycle closeout — archive claimed sessions, decide session-file creation, prepare continuation context, and produce operator-useful closeout — only once its goal is met with no continuation remaining, the user halted work, context is exhausted, or an external blocker prevents the next action. NEVER invoke while do-able in-scope work remains, and NEVER create a spec-tree session file without this skill.

ALWAYS invoke this skill at the beginning of each session, after every compaction, and before answering spec-tree workflow or session-continuity questions when the live SPEC_TREE_FOUNDATION marker is absent. NEVER read, create, or modify any file in this repository other than AGENTS.md without loading this skill and all its references first.

SKILL.md audit methodology preloaded by the skill-auditor agent. The main conversation reaches this audit only through that agent.

{{! term('configured_agent') | capitalize !}}-configuration audit methodology preloaded by the subagent-auditor agent. Dispatch subagent-auditor to audit {{! term('configured_agent') !}} configuration files; the main conversation reaches this audit only through that agent.

ALWAYS invoke this skill when creating, editing, or improving SKILL.md files.

ALWAYS invoke this skill when creating, editing, or configuring {{! term('configured_agents') !}}. NEVER create {{! term('configured_agents') !}} without this skill.

Skill authoring standards enforced across all creating and auditing skills. Loaded by other skills, not invoked directly.

ALWAYS invoke this skill before implementing any spec-tree work item. NEVER write code, tests, or architecture for a spec-tree node without this skill.

ALWAYS invoke to close a spec-tree session or merge lifecycle closeout — archive claimed sessions, decide session-file creation, prepare continuation context, and produce operator-useful closeout — only once its goal is met with no continuation remaining, the user halted work, context is exhausted, or an external blocker prevents the next action. NEVER invoke while do-able in-scope work remains, and NEVER create a spec-tree session file without this skill.

ALWAYS invoke this skill at the beginning of each session, after every compaction, and before answering spec-tree workflow or session-continuity questions when the live SPEC_TREE_FOUNDATION marker is absent. NEVER read, create, or modify any file in this repository other than {{! file('root_guide') !}} without loading this skill and all its references first.

Agent prompt writing conventions enforced across all creator and auditor skills. Loaded by other skills, not invoked directly.

ADR audit methodology preloaded by the adr-auditor agent. Dispatch adr-auditor to audit an ADR; the main conversation reaches this audit only through that agent.

PDR audit methodology preloaded by the pdr-auditor agent. Dispatch pdr-auditor to audit a PDR; the main conversation reaches this audit only through that agent.

Spec-node audit methodology preloaded by the spec-auditor agent. Dispatch spec-auditor to audit a spec node; the main conversation reaches this audit only through that agent.

Test-evidence audit methodology preloaded by the test-evidence-auditor agent. The test-evidence-auditor audits test evidence against spec assertions; the main conversation reaches this audit only through that agent.

PDR audit methodology preloaded by the pdr-auditor agent. Dispatch pdr-auditor to audit a PDR; the main conversation reaches this audit only through that agent.

Test-evidence audit methodology preloaded by the test-evidence-auditor agent. The test-evidence-auditor audits test evidence against spec assertions; the main conversation reaches this audit only through that agent.