Use when implementation is complete, all tests pass, and you are about to merge, create a PR, or close out a development branch — enforces an Architecture Decision Record and PATTERN-DEBT lifecycle review before any integration action.
Use after a spec document contains SPECAPPROVED=true in its frontmatter, before invoking writing-plans — or when SPECESCALATION=true is set by specialist-review. Runs a FAST risk audit on the design to surface failure modes before any code is written.
Use when you have a VHEATM audit report and want to extract its findings into Super Skills knowledge — populates Gotchas sections, pattern-debt.md, qbr-calibration.md, and CONTEXT.md from real production audit evidence.
Use before any feature, component, or behavior change — explores user intent and design before implementation. Precondition: domain-alignment should have run if this is a new project or domain area.
Use before any software-development task or skill-applicable workflow — classifies task complexity/risk into C0-C4, selects the minimum required Super Skills, preserves evidence discipline across all tiers, and prevents both under-use and over-use of ceremony.
Use in long sessions, after loading many files, after repeated failed attempts, before phase transitions, or before completion claims — refreshes active goals, skill obligations, evidence anchors, and unresolved T4 assumptions to prevent intra-session instruction drift.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies — dispatches one agent per problem domain concurrently.
Use at the start of a new project, unfamiliar domain, or new product area before brainstorming — creates or updates docs/superskills/CONTEXT.md with vocabulary, actors, invariants, sensitive data, external dependencies, forbidden assumptions, success/failure semantics, and synonyms for KB search.
Use after brainstorming SPECAPPROVED=true to elevate spec into DPS structure. Creates CONTRACTS.md, BLUEPRINT.md, ADR.md canonical files from approved spec. Also usable standalone to initialize DPS for a new project.
Use to advance DPS lifecycle status — from DRAFT to PROOF-READY, PROOF-READY to APPROVED-SSOT, or IMPLEMENTATION-ACTIVE to LIVING-SPEC. Runs promotion checklist before advancing.
Use before major releases, after repeated cycles, or when relying on old ADRs, Gotchas, assumptions, QBR/M.AT calibration, or compound KB entries — automates staleness checks so evidence that was once true is revalidated, downgraded, retired, or escalated instead of silently trusted.
Use when you have a written implementation plan to execute inline with review checkpoints — alternative to subagent-driven-development for environments without subagent support.
Use before releasing, installing, or modifying Super Skills itself — self-audits the framework for broken skill references, YAML errors, stale version drift, nano mismatches, shell guard bugs, missing shared files, and DPS tooling availability.
Use when searching for past decisions, pattern debt entries, risk assessments, or implementation plans — queries the super-skills KB using keyword search across ADRs, pattern-debt registry, and specs.
Use after adr-commit completes — extracts lessons, domain terms, bug patterns, and gotchas from the current cycle into a structured compound wiki, making each cycle permanently improve future cycles.
Use immediately after confirming any bug fix — before committing or moving to the next task. Prevents fixing one instance while leaving identical bugs elsewhere.
Use before any task that touches PII, secrets, credentials, payment data, regulated data, logs, telemetry, external APIs, data export, multi-tenant boundaries, or C4 workflows — classifies data sensitivity, checks disclosure paths, scans for secret leakage, verifies redaction and retention, and blocks unsafe release…
Use when receiving code review feedback, before implementing suggestions — requires technical verification not performative agreement, especially if feedback seems unclear or questionable.
Use before merge, deploy, release branch cut, production traffic enablement, migration, or feature-flag rollout — verifies rollback, smoke tests, observability, data impact, dependency readiness, and post-deploy evidence so code-complete is not mistaken for release-ready.
Use when a session must end before a task is complete, or when transferring work to a new agent session — captures current state compactly so the next session starts with full context rather than blank slate.
Use once when starting a new project with super-skills — creates required directory structure, validates environment, and generates KB scaffolding. Run before any other super-skill.
Use when completing tasks, implementing major features, or before merging — routes code review to the appropriate specialist lens (STRIDE, OWASP, ATAM, TEMPORAL, CPT, MIGRATION, PRIVACY/SECRETS) based on detected signals, with Independent Judge for Tier 3.
Use when executing implementation plans with independent tasks — dispatches fresh subagent per task with specialist review between tasks, pattern-globalize after bugs, adr-commit at finish.
Use when encountering any bug, test failure, or unexpected behavior — before proposing any fix. Requires root cause investigation with evidence anchors before attempting solution.
★not rated 0 2mo agoA34 tokens
originalApache-2.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: