dcouple/orchestra

do

Run the full autonomous pipeline against a work item — plan, implement, verify, PR, post-PR review + QA, wrap-up. Takes a work-item reference (issue

Langue du texte source : anglais

prepare-pull-request

Take ad-hoc changes made in-session (outside /do) to a pull request — gate them through Socrates (right approach?) and the PR reviewers (correct?), then commit, push, and open the PR in the repo's standard format. /do handles its own PR prep; this skill is…

Langue du texte source : anglais

arena

Produce one artifact by fanning out N blind candidates, picking the strongest as the base, grafting the best of the losers into it, and verifying the synthesis. Use when a single attempt at a non-trivial artifact — a design, a tricky function, a doc — would…

Langue du texte source : anglais

discussion

Interactive back-and-forth to clarify, understand, or figure something out — an idea, an approach, a tradeoff, or a suspected bug. Use when the user wants to think out loud or explore before committing to anything — e.g. "let's discuss X", "help me understand…

Langue du texte source : anglais

hillclimb

Sustained improvement of one named metric toward a target — measure a baseline, then loop one hypothesis at a time, each with a re-measurement and a keep-or-revert verdict. Use for perf, bundle size, lint count, test time, or any number with a repeatable…

Langue du texte source : anglais

codex

Dispatches one Codex (GPT-5.6) sub-agent via `codex exec` — implementer, backend-verifier, plan-reviewer, code-reviewer, code-researcher, or investigator — and returns its report. Used by /do, /discussion, and /create-brief whenever one of these roles runs;…

Langue du texte source : anglais

refactor-deep

Refactor-deep role in an automated development pipeline: read-only comprehensive analysis of a large diff — per-layer repo-derived conventions plus a correctness hunt over new code paths, writes a prioritized plan. Use when dispatched after the review loop on…

Langue du texte source : anglais

refactor-simple

Refactor-simple role in an automated development pipeline: read-only quality analysis of the branch for small/medium diffs — repo-derived conventions, code smells, writes a plan. Use when dispatched after the review loop.

Langue du texte source : anglais

create-brief

Captures discussed work as a work item ready for /do — a feature brief for changes and additions (single-outcome or multi-phase), a bug brief for defects (running the investigator first if the root cause isn't established). Use when a conversation has…

Langue du texte source : anglais

postmortem

Runs a postmortem on a /do run — after the human reviewed the PR, or as a routine after-run review. Covers two dimensions: how the run RAN (wall-clock, agent-active vs idle-waiting-on-human, stalls, blockers — always) and, when the result fell short of…

Langue du texte source : anglais

implementer

Implementer role in an automated development pipeline: executes an Implementation Plan (plan.md), writing the diff while keeping the plan file true. Use when dispatched to implement a plan or apply review fixes.

Langue du texte source : anglais

sentry-loop

On-demand Sentry triage loop — sweep every project's errors over a time window, classify each issue (new / recurring / regressed, user-impacting / zero-user, real / noise), root-cause only the clusters that matter, file findings into the work tracker under…

Langue du texte source : anglais

investigator

Investigator role in an automated development pipeline: reproduces a reported defect and isolates its root cause with evidence. Use when dispatched to diagnose a bug before it's written up.

Langue du texte source : anglais

postmortem-loop

On-demand postmortem adoption loop — sweeps published postmortem comments for open system-change proposals, dedupes them against the current canonical files, lands the human-approved edits in the canonical skills repo, and posts verdict replies so the state…

Langue du texte source : anglais

investigate

Investigates bugs through a single evidence-driven investigator, scaling from a normal root-cause pass to a deep falsifiable experiment loop. Use when something is broken, failing, or behaving unexpectedly.

Langue du texte source : anglais

investigate

Investigate broken behavior using the shared evidence-driven method, scaling from a normal root-cause pass to a deep falsifiable experiment loop.

Langue du texte source : anglais

backend-verifier

Backend-verifier role in an automated development pipeline: proves backend verification criteria by running the mapped tests, scripts, and commands with quoted evidence. Use when dispatched to verify implemented work.

Langue du texte source : anglais

code-researcher

Code-researcher role in an automated development pipeline: explores the codebase and returns current-state facts with precise file:line references. Use when dispatched to answer a question about what exists in the repo.

Langue du texte source : anglais

code-reviewer

Code-reviewer role in an automated development pipeline: reviews the diff for correctness and security with file:line evidence. Use when dispatched to review an implementation.

Langue du texte source : anglais

plan-reviewer

Plan-reviewer role in an automated development pipeline: audits an Implementation Plan for gaps, repo accuracy, and fidelity to the work item. Use when dispatched to review a plan.

Langue du texte source : anglais

excalidraw-diagram

Create Excalidraw diagram JSON files and PR visual overviews that make visual arguments. Use when the user wants to visualize workflows, architectures, concepts, pull request changes, before/after behavior, or a shareable explainer image for reviewers.

Langue du texte source : anglais