improv.sh vs Skills

improv.sh and Skills are both cli coding agents tracked by AIDiveForge. Below is a side-by-side comparison of pricing, capabilities, platforms, and ownership — sourced from each tool's live website and verified before publishing.

improv.sh

improv operates as a task harness: the @im call pulls repo context, detects your test commands, writes acceptance criteria, and packages shell validation steps into one spec the agent can implement on turn one. The loop infrastructure is the distinguishing piece — judges run your actual exit-code commands (npm test, typecheck, build), so done means your tests pass, not that the agent says it's done. The tool installs locally via curl with no external API keys required, and the Chrome extension brings the same engine into web-based chat interfaces. The 920-skill library and daily auto-research loop suggest the routing layer will keep growing — but the page offers no independent benchmarks to validate the token-savings figures cited.

Skills

Orbit is a CLI harness that wraps any JSON-speaking coding agent — Claude, Codex, Cursor, or your own — in a bounded loop: one task selected from a dependency-ordered backlog, executed by the agent, then checked against tests, lint, and type validation before the orbit closes. If the agent cannot prove the work, the run does not advance. Every orbit writes structured JSON artifacts and a human-readable progress log, so you are reviewing evidence rather than re-reading diffs and guessing. The harness runs entirely locally, requires no API key for the replay demo, and is MIT licensed. Where it breaks: teams whose validation needs go beyond tests and lint — custom scoring rubrics, multi-step human approval workflows, or large parallel backlogs — will find the intentionally small surface area a ceiling rather than a feature.

Attribute	improv.sh	Skills
Pricing	Free	Free
Free trial	No	No
Open source	Yes	Yes
Has API	No	No
Self-hosted option	Yes	Yes
Platforms	VS Code, Cursor, Claude Code, terminal, Chrome	Cross-platform (Python 3.6+)
Pros	Repo-aware spec compilation pulls your actual test commands and package scripts into the task before the agent starts, which means the agent implements against your real constraints instead of inventing them mid-run. Exit-code judges close the loop on real shell commands — npm test, typecheck, build — so you are not relying on the agent's self-assessment of whether it finished. Task memory persisted under .improv/tasks/ survives session boundaries, so an agent restarted mid-task picks up status and spec instead of starting the discovery cycle again. Local-first install with no external API keys required, which means the harness runs in air-gapped or locked-down environments where cloud tooling is blocked. Chrome extension and VS Code/Cursor Marketplace extension share the same local engine, so the spec compilation and judge loop work whether you are in the IDE or a browser-based chat interface — without switching tabs.	Validation gates block an orbit from closing unless tests, lint, and type checks pass, so you stop merging agent output that ran without error but failed to do what the task required. Four structured artifacts per run — result, evaluation, review recommendation, and a progress log — give you an auditable evidence trail, so post-mortem debugging is reading JSON rather than reconstructing what the agent did from git history. Agent-neutral CLI contract means you can run Claude and Codex against the same task and backlog, comparing scored artifacts directly instead of running separate experiments with incomparable outputs. Dependency-ordered backlog selection keeps each orbit focused on one task at a time, so the agent cannot silently absorb scope from adjacent work and produce diffs that are hard to attribute. MIT licensed with a no-API-key replay demo, so you can evaluate the full validation loop against a real artifact chain without committing credentials or incurring cost.
Cons	Task state is written to .improv/tasks/ on the local machine. Teams with more than one developer working the same codebase have no shared task state — there is no sync layer described on the page — so parallel agent runs on different machines produce divergent task records with no reconciliation path. The tool exposes no API surface, so teams that want to trigger improv from a CI pipeline or wrap it in a custom orchestration layer cannot. Teams hitting this wall move to harness frameworks that expose programmatic interfaces — at which point they are maintaining the prompt compilation logic themselves. The token-savings figures on the page (~613 tokens median) are vendor-reported with no independent reproduction methodology described. Teams making adoption decisions based on cost reduction should treat these numbers as illustrative until they run their own baseline comparison. Chrome extension installation requires either the Chrome Web Store or a manual sideload script — neither path is available in Firefox or Safari. Teams on non-Chromium browsers are limited to the terminal install, losing the browser chat integration entirely.	Validation is limited to tests, lint, and type checks as described on the vendor page — teams whose definition of 'done' includes semantic correctness, security scanning, or domain-specific rules have to build that checking outside the harness and wire it in manually, adding a second system to maintain. The harness executes one orbit at a time; teams running large backlogs where tasks are independent and could parallelize will hit a throughput ceiling and move to a more capable orchestration layer or build parallelism themselves. There is no built-in multi-step human approval workflow beyond the accept/iterate/stop recommendation in `review.json` — teams that need a formal sign-off gate before code advances to staging will need to script that around the harness or switch to a tool that treats human review as a first-class execution step.

Bottom line

improv.sh and Skills are closely matched on pricing model, openness, and API availability — pick by feature set and platform support in the table above.

Frequently asked questions

What is the difference between improv.sh and Skills?

improv.sh is Free and open source, while Skills is Free and open source. Compare pricing, free trial, API, platforms, and pros/cons in the table above on AIDiveForge.

Is improv.sh better than Skills?

It depends on your workflow. Use the side-by-side attributes (pricing, open source, API, self-hosted, platforms) to decide. AIDiveForge does not rank a universal winner — we publish verified facts so you can choose.