implement-direct
Lightweight implementation orchestrator for low-complexity work — fixes, refactors, doc changes, or single-AC features that do not warrant a phase plan or factory decomposition.
implement-factory
Factory loop orchestrator for multi-feature or multi-component implementation manifests. Use for high-complexity work with parallel-eligible workstreams and holdout-scenario evaluation.
implement-incremental
Linear phase-loop orchestrator for single-feature implementation plans. Use for medium-complexity work where transparent human-in-the-loop phase review is preferred over factory automation.
pattern-detection
Identify existing codebase patterns (naming conventions, architectural patterns, testing patterns) to maintain consistency. Use when generating code, reviewing changes, or understanding established practices.
performance-analysis
Measurement approaches, profiling patterns, bottleneck identification, and optimization guidance. Use when diagnosing performance issues, establishing baselines, identifying bottlenecks, or planning for scale. Always measure before optimizing.
platform-operations
Unified platform operations guidance for CI/CD pipeline design, deployment strategies, observability, SLI/SLOs, and incident-ready rollouts. Use when building release workflows, production monitoring, or reliability controls.
project-discovery
Unified codebase discovery across structure navigation, tech-stack detection, and documentation extraction. Use when onboarding to a project, locating implementation paths, identifying frameworks/tooling, or validating docs against code reality.
refactor
Refactor, simplify, or clean up code for improved maintainability without changing business logic
requirements-elicitation
Requirement gathering techniques, stakeholder analysis, user story patterns, and specification validation. Use when clarifying vague requirements, resolving conflicting needs, documenting specifications, or validating requirements with stakeholders.
review
Multi-agent code review with specialized perspectives (security, performance, patterns, simplification, tests)
security-assessment
Vulnerability review, threat modeling, OWASP patterns, and secure coding assessment. Use when reviewing code security, designing secure systems, performing threat analysis, or validating security implementations.
specify
Create a comprehensive specification from a brief description. Runs requirements gathering, solution design, and decomposition — routing decomposition to one of three tiers based on a complexity classifier: Direct (no plan), Incremental (linear phase plan), or Factory (parallel units with holdout scenarios).
specify-factory
Decompose a multi-feature or multi-component specification into factory-consumable artifacts. Use this for high-complexity work — multiple features, three or more components, or parallel-eligible workstreams.
specify-incremental
Decompose a single-feature specification into a linear, phase-by-phase implementation plan. Use this for medium-complexity work — single feature, one or two components — where transparent human-in-the-loop phase review is preferred over factory automation.
specify-meta
Scaffold, status-check, and manage specification directories. Use when creating a new spec, reading spec status, transitioning between phases, or logging decisions on a spec in .start/specs/.
specify-requirements
Create and validate product requirements documents (PRD). Use when writing requirements, defining user stories, specifying acceptance criteria, analyzing user needs, or working on requirements.md files in .start/specs/.
specify-solution
Create and validate solution design documents (SDD). Use when designing architecture, defining interfaces, documenting technical decisions, analyzing system components, or working on solution.md files in .start/specs/.
technical-writing
Create architectural decision records (ADRs), system documentation, API documentation, and operational runbooks. Use when capturing design decisions, documenting system architecture, creating API references, or writing operational procedures.
test
Use when completing implementation, fixing bugs, refactoring code, or any time you need to verify the test suite passes. Also use when tests fail and you hear "pre-existing" or "not my changes" — enforces strict code ownership. Ensures MECE coverage (no overlap, no gaps) and that ALL test categories including E2E are executed.
testing
Writing effective tests and running them successfully. Covers layer-specific mocking rules, test design principles, debugging failures, and flaky test management. Use when writing tests, reviewing test quality, or debugging test failures.
user-research
User research and insight synthesis for interviews, usability testing, personas, journey mapping, and actionable product/design recommendations. Use when planning studies, collecting evidence, synthesizing patterns, or converting findings into prioritized decisions.
validate
Validate in any of six modes — spec quality, single-file review, spec-to-implementation drift, constitution rule enforcement, comparison between two artifacts, or sanity-checking your understanding. Use when checking a spec by ID, validating a file by path, detecting drift, enforcing constitution rules, comparing two sources ("$X against $Y"), or asking a freeform validation question.
writing-skills
Use when creating new skills, editing existing skills, auditing skill quality, converting skills to markdown conventions, or verifying skills before deployment. Triggers include skill authoring requests, skill review needs, or "the skill doesn't work" complaints.
agent-survey-corpus
Download a small corpus of open-access arXiv survey/review PDFs about agentic systems and extract text for style learning.
anchor-sheet
Extract per-subsection “anchor facts” (NO PROSE) from evidence packs so the writer is forced to include concrete numbers/benchmarks/limitations instead of generic summaries.
appendix-table-writer
Curate reader-facing survey tables for the Appendix (clean layout + high information density), using only in-scope evidence and existing citation keys.
argument-selfloop
Build a final, machine-readable argument snapshot from current H3 sections and refresh section fingerprints before merge.
artifact-contract-auditor
Audit one research Workspace for declared Unit outputs and Pipeline target Artifacts, writing `output/CONTRACT_REPORT.md`; use for mid-Run coverage snapshots or final delivery completeness, not deep provenance integrity.
arxiv-search
Retrieve arXiv paper metadata with keyword queries or import an offline arXiv export, and save results as JSONL (`papers/papers_raw.jsonl`).
beamer-compile-qa
Compile the Beamer tutorial deck and write a build report.
beamer-scaffold
Generate a Beamer slide deck from the final tutorial and approved module structure.
bias-assessor
Use when `evidence-review` has an extraction table and needs lightweight risk-of-bias fields.
chapter-briefs
Build per-chapter (H2) writing briefs (NO PROSE) so the final survey reads like a paper (chapter leads + cross-H3 coherence) without inflating the ToC.
chapter-lead-writer
Write H2 chapter lead blocks (`sections/S<sec_id>_lead.md`) that preview the chapter's comparison lens and connect its H3 subsections, without adding new facts.
chapter-skeleton
Build a retrieval-informed chapter skeleton (`outline/chapter_skeleton.yml`) from taxonomy/core scope before stable H3 decomposition.
checkpoint-brief
Project completed stage Artifacts into a concise human-review block in `DECISIONS.md`; use before a Workflow checkpoint, not for Workflow routing or approval.
citation-anchoring
Regression-check citation anchoring (citations stay in the same subsection) to prevent “polish drift” that breaks claim→evidence alignment.
citation-diversifier
PRODUCES a citation-budget plan/report (`output/CITATION_BUDGET_REPORT.md`); does NOT edit the draft. Allocates an in-scope per-H3 budget (NO NEW FACTS) so drafts stop failing the global unique-citation gate; citation-injector applies it.
citation-injector
APPLIES/consumes a `citation-diversifier` budget report (`output/CITATION_BUDGET_REPORT.md`) to inject *in-scope* citations into an existing draft (NO NEW FACTS), so the run passes the global unique-citation gate without citation dumps.
citation-verifier
Generate and verify BibTeX entries from paper notes, writing `citations/ref.bib` and `citations/verified.jsonl`.
claim-evidence-matrix
Seed `outline/claim_evidence_matrix.md` from outline+notes; claim-matrix-rewriter rewrites it later from evidence packs.
claim-matrix-rewriter
Rewrite `outline/claim_evidence_matrix.md` as a projection/index of evidence packs (NO PROSE), so claims/axes are driven by `outline/evidence_drafts.jsonl` rather than outline placeholders.
claims-extractor
Use when a review workspace has manuscript text and needs a traceable claim ledger.
concept-graph
Use when an approved tutorial spec exists and the run needs a deterministic prerequisite graph before module planning.
dedupe-rank
Use when a broad paper candidate pool needs deterministic deduplication and a stable core set.
deliverable-selfloop
Score an existing reader-facing deliverable and emit a deterministic PASS/FAIL scorecard plus bounded repair plan; use after synthesis, not to rewrite content.
draft-polisher
Audit-style editing pass for `output/DRAFT.md`: remove template boilerplate, improve coherence, and enforce citation anchoring.
evaluation-anchor-checker
Audit and rewrite evaluation/numeric claims to ensure they carry minimal protocol context (task + metric + constraint) and avoid underspecified model naming.
evidence-auditor
Use when `paper-review` needs a claim-by-claim evidence gap report grounded in an extracted claim ledger.
evidence-binder
Bind addressable evidence IDs from `papers/evidence_bank.jsonl` to each subsection (H3), producing `outline/evidence_bindings.jsonl`.
Page 303 of 1681 · 84047 results
