gauntlet-loop
/gauntlet-loop
Improve a product or artifact through repeated construction, independent critique, measured comparison, and regression checks. Use for sustained iteration when a single implementation pass cannot establish the required quality.
- Author
- rubenmarcus ↗
- Repository
- agent-skills ↗
- Licence
- MIT
- Last repository change
- 31.10.2026
Assessment and security
- Files in this package
- 3
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 31.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Improve a product or artifact through repeated construction, independent critique, measured comparison, and regression checks. Use for sustained iteration when a single implementation pass cannot establish the required quality.
Original author description
Improve a product or artifact through repeated construction, independent critique, measured comparison, and regression checks. Use for sustained iteration when a single implementation pass cannot establish the required quality.
How it works
- Establish the bar
- Run one useful round
- Decide the next round
SKILL.md preview
--- name: gauntlet-loop description: Improve a product or artifact through repeated construction, independent critique, measured comparison, and regression checks. Use for sustained iteration when a single implementation pass cannot establish the required quality. --- # Gauntlet loop Start with a baseline and explicit quality bar. The builder produces candidates; independent evaluation determines whether the evidence supports keeping them. ## Establish the bar Translate the desired outcome into observable behavior. Record the input, environment, baseline artifact, measurement method, and budgets. Explain where thresholds come from. Keep technical correctness, runtime evidence, visual judgment, and user acceptance distinct. A green suite establishes only the contracts it exercises. ## Run one useful round 1. Give a builder a bounded change and ownership of affected files. 2. Capture the actual result in the same scenario as the baseline. 3. Ask an independent critic to compare raw artifacts against the specification. 4. Check for regressions and metric gaming. 5. Keep, revise, or reject the candidate using evidence. Parallel builders need separate worktrees or non-overlapping ownership. Sequence work with dependent outputs. Use the user's selected browser and environment for visual verification; coordinate captures so competing sessions do not distort results. An expensive result should survive a cheaper diagnostic first. Do not broaden work merely because another iteration is possible. ## Decide the next round Fix regressions before adding polish. Compare the same inputs, viewport, load, revision, and measurement window. Record unavoidable differences. Use [a round record](references/round-record.md) to preserve the comparison and next hypothesis. Retain a failed candidate's useful evidence without mixing its changes into the accepted result. Continue toward acceptance within the agreed scope and budget. If progress stalls, change the hypothesis or run a discriminating experiment. Stop when the objective is met, the user stops work, an agreed limit is reached, or an actual blocker prevents meaningful progress. Report missing evidence explicitly.
Files in this package (3)
- SKILL.md 2 KB
- agents/openai.yaml 1 KB
- references/round-record.md 1 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · rubenmarcus/agent-skills | 90 | MIT |
| emaraschio/cursor-commands | 100 | MIT |
| mintuz/claude-plugins | 100 | MIT |
| robonuggets/gauntlet-loop | 100 | CC-BY-4.0 |
| aaronwjordan/gauntlet-loop | 95 | CC-BY-4.0 |
| aaronwjordan/gauntlet-loop | 95 | CC-BY-4.0 |
| aaronwjordan/gauntlet-loop | 95 | CC-BY-4.0 |
| aaronwjordan/gauntlet-loop | 95 | CC-BY-4.0 |
| aaronwjordan/gauntlet-loop | 90 | CC-BY-4.0 |
Database snapshot: 13.11.2026 · package version d9e3c2900c3b (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100gauntlet-loop-max
Two-gate quality loop for work that tests alone can't prove is good - UI, animation, dashboards, landing pages, copy, scripts, titles, thumbnails, docs, decks. Gate 1 proves it works (spec + quality review by an independent reviewer, fix rounds, severity-ranked findings). Gate 2… - 90gauntlet-performance
Use when a human asks how gauntlet runs perform across the recorded telemetry - explicit invocation only (/skill:gauntlet-performance [--dir <path>]... [--since <version>]). - 100setup
Set up a Gauntlet Loop for a project: define the goal, the reference bar the work must beat, judging criteria beyond looks, how each piece is captured and judged (the harness), and the stop rules, then write and validate a gauntlet.json spec. Use for 'gauntlet this', 'set up a… - 100run
Run a Gauntlet Loop from a gauntlet.json spec: split the work into pieces, build each with a fresh hotline callee, capture the real output, judge it blind against the reference with an independent critic callee, commit each round, and loop until it wins, a stop rule fires, or… - 100running-the-gauntlet
Use when "done" is a quality or completeness judgment rather than an enumerable task list — polish targets, parity with an exemplar, UI completeness, best-practices adherence. Defines a ratified bar first, then loops builder/critic agents against it until a blind critic is satisfied, with evidence. - 90gauntlet-proof-audit
Use to audit the gauntlet records, "are the ROUNDS.md records honest", "verify the proof corpus", "check each run record against its evidence", "audit the gauntlet corpus", "is the gauntlet proof trustworthy", or a scheduled run. NOT for re-running probes or rounds…