More than a skill. Your agent builds the reliability in as it codes, a protocol lets you verify it in CI, and it’s growing into an open standard any tool can adopt — so the workflow survives failure, from a 6am side-project to a bank’s payout run.
They fix what the AI knows. We fix whether the job finishes.
None show up in the demo. All of them show up in week two — so GraphSmith hardens each one at generation time.
Crashes at step 7 of 10 and restarts from step 1 — redoing paid API calls, re-scraping, re-generating.
Every step saves progress; a crash resumes at the exact step it stopped, never from zero.
A retry after a half-finished step sends the same email twice, charges the same card twice.
Recorded effects run once, even after power loss; an uncertain send halts loudly instead of re-firing.
Ask about your own codebase and it invents functions, files, and APIs that don't exist.
Every claim cites a real file via KnoSky, or is flagged as a guess. Your code never leaves your machine.
A workflow that's 85% reliable per step fails four times out of five across ten steps.
A plain-English goal goes into the forge — a hardened, self-defending workflow comes out. Then watch it take a crash and finish anyway.
Say the outcome in plain English. The skill activates on its own.
One screen: workers, handoffs, save points, stop rules. Nothing is built until you approve.
A runnable, zero-dependency project. Runs immediately with no API keys.
A chaos test kills the run mid-flight and verifies it recovered — no duplicated work.
It SIGKILLs the run mid-flight, restarts, and asserts it resumed from the last save point with zero duplicated effects. Verification is executable — not "the AI says it's fine."
They held the release twice until every finding was fixed or disclosed. Full reports — dissents preserved — live in the repo.
Verified integrity · hash-pinned, gated core · isolated evaluation · local-by-default · observable & killable. A deterministic check runs at every boundary.
Capability profiles — resumable, effect-reconciled, integrity-verified, adversarially-tested — with linked evidence, via a GitHub Action or GitLab template.
One install. The full build-and-run lifecycle — plus the v0.2.0 Protocol and the v0.3.0 attestation standard (GSA) — all local, all readable in minutes. Pick a stage:
A runnable, zero-dependency project: deterministic manager, worker steps, save points, resume, capped retries, structured logs — runs immediately with no API keys.
A one-screen plan — workers, handoffs, save points, stop rules — that you approve before a single line is written.
Scans existing JS / TS / Python for the classic failure patterns — unbounded loops, missing persistence, unsafe side effects — ranked by severity, self-tested against a bundled corpus.
Maps "it forgets / duplicates / loops forever" to the exact broken rule, with file and line — and proposes the minimal fix without rewriting what works.
Kills the run mid-flight and asserts recovery: kill test, double-run, power-loss probe, lock probes, and a loud safety-halt path.
Capability profiles (resumable, effect-reconciled, integrity-verified, adversarially-tested) enforceable on every PR via a GitHub Action or GitLab template.
A local pointer index your AI cites from — claims about your code carry a real file reference, or are flagged as guesses. A map, not an oracle. Nothing leaves your machine.
KnoSky re-indexes each session and degrades gracefully offline — pinned and content-hash verified, never a silent global install.
Lanes (one writer each), task claims with leases, frozen contracts, no self-certification, and risk-tiered human gates — so parallel agents never collide.
Optional, for production teams: registry, PRD-to-task traceability, adversarial QA charter, release & rollback runbooks, and agent eval scorecards.
Verified integrity, a hash-pinned gated core, isolated evaluation, local-by-default operation, and observable & killable runs — a deterministic check enforces each at every boundary.
graphsmith verify --profiles emits R/E/B/T/G/Q/X — each verified · unavailable · failed · not-applicable with linked evidence, never a blended score. Unavailable is never green.
Every change clears static analysis → behavioral sign-test → human adoption → an observation-window canary before it's trusted.
JSON schemas for every artifact (each carries schema_version), plus a conformance lab a second implementation can validate itself against.
A GitHub Action (and GitLab template) runs verify on every PR across a 3-OS matrix — with a badge that carries its evidence, not just a colour.
A broken workflow gets a diagnosis and a smallest-fix repair, staged with evidence and one-command rollback — never a silent rewrite of your logic.
Bounded, project-local improvements that must clear an executable gate and a human before adoption. It can't learn past its own safety rules.
Architectural, unit, smoke, regression & adversarial batteries against your workflows, with tamper-evident evidence.
Tells you exactly when to move up to SQLite, a framework checkpointer, or a durable engine — and when not to.
Not sure where to start? Ask the assistant in the corner — it answers what GraphSmith can do, how to install it, and more.
v0.2.0 turns the discipline into a protocol — five invariants a deterministic check enforces at every boundary. v0.3.0 ships GSA — a signed, replayable, tamper-evident attestation of every run.
A deterministic check runs at every boundary; injected text can't reach control flow.
A constitutional core no automated process can edit; every change passes a four-gate pipeline.
Every candidate change is tried first in a disposable, mocked-effect copy.
Healing, learning, evolution stay on your machine. No telemetry, ever.
Every run declares budgets, streams to a live view, and is safe to kill and resume.
Researches new leads and drafts emails. A crash never re-pays for the enrichment calls it already made.
Recorded effects run once (replay-verified) so a retry never double-charges — and an uncertain send halts for a human instead of guessing.
Resumes at the failed step instead of re-scraping and re-enriching the whole dataset from zero.
KnoSky citations mean it never edits a file or API it hallucinated into existence.
Lanes, task claims with leases, and frozen contracts — parallel speed without parallel chaos.
Risk-tiered human gates and evidence packets for the workflows you can't afford to get wrong.
Works identically via the Agent Skills open standard — plain Node 18+, macOS, Linux, and Windows.
npx skills add SathiaAI/graphsmith
Then, in any agent: “Build me an agent that researches new leads and drafts outreach emails.” · Free. MIT. No API keys. No telemetry.