Loop directory
81 loops match your filters.
Search the literature, verify every source
Deduplicate papers across live sources, verify DOI metadata, score relevance, and stop honestly when evidence runs thin.
Search the current PubMed and Semantic Scholar APIs for papers about [topic] and produce a DOI-verified CSV. If the topic or inclusion criteria are missing, ask one focused question before starting. Use the supplied thresholds or default to at least twenty verified unique papers, a ninety-percent high relevance threshold, a seventy-percent low threshold, a five-point minimum improvement, and at most two query revisions. Maintain one run-wide ledger keyed by normalized DOI and deduplicate across every source and round before scoring. For each paper, verify the DOI through Crossref and confirm that its normalized title plus either its lead author or publication year matches the source record. Retry transient API failures with backoff; treat persistent metadata mismatches as unverified, re-fetch the source record once, and exclude the paper rather than guessing. Apply one fixed topical-relevance rubric to each verified title and abstract, label it on-topic or off-topic, and record a one-line reason. Never change the rubric during the run. Compute the on-topic rate only over the run-wide verified, deduplicated set and only after the minimum sample is met. Succeed when the set reaches the high threshold. Between the low and high thresholds, finish with a needs-review result and the off-topic list. Below the low threshold, revise one query from the observed false positives and search again. Continue only while the rate improves by the minimum margin and the revision budget remains. Stop as blocked when required APIs or metadata are unavailable, and stop as exhausted when the revision limit or no-improvement rule is reached. Never invent, infer, or autocomplete paper metadata. Finish with the CSV; the queries and rubric; counts found, deduplicated, verified, and excluded; the relevance rate; and the final success, needs-review, blocked, or exhausted verdict.
evaluationmedium risk
Refactor without touching architecture
Improve a targeted area via dependency mapping, atomic refactors, and regression checks — no changes to architecture or public contracts.
Refactor [target] toward [measurable goal] in [repository]. If the target or goal is missing, ask and stop. Record current behavior and affected dependencies; select representative tests for boundaries and failure modes, then make one atomic change without altering public contracts unless authorized. Run the same tests, type and lint checks, and affected-consumer checks, keeping only regression-free improvements. Repeat for at most five rounds. Stop on success, blocked architecture, approval required, exhaustion, or no progress. Preserve unrelated work and finish with the diff, impact map, evidence, rejected attempts, and remaining debt.
testingmedium risk
Ground a feature before you build it
Anchor one small feature in the current code, APIs, data contracts, and tests before implementing and verifying the user path.
Implement one bounded feature slice in [repository]. Read project instructions, the current implementation, relevant services, types, UI, tests, and architecture notes before editing. Report the evidence, risks, affected files, persistence impact, and validation plan; stop for approval if inspection materially changes scope or reveals destructive, production, or silent-persistence behavior. Make the smallest change, preserve unknown data and unrelated work, run relevant checks, and manually verify user-facing states. Stop after this slice and return evidence, limitations, and the next recommended slice.
testinghigh risk
Get the React health scan to 100/100
Inventory every production React app, fix findings without suppressions, and prove a real 100/100 with full project checks.
Bring every production React app in [repository] to a freshly verified React Doctor score of 100/100. Inventory app roots, record a full `npx react-doctor@latest --verbose` baseline, fix one root cause at a time, and rerun the full scan plus relevant typecheck, lint, tests, and builds. Never hide findings with exclusions, ignores, suppressions, deleted behavior, or relaxed rules. Stop at 100/100 for every app, blocked, approval-required, or no measurable progress; preserve unrelated work and report exact proof.
maintenancehigh risk
Leave a handoff the next agent can resume
Record state, evidence, risks, untouched scope, and exactly one safe next action before the session ends.
Before ending [session or work period], create a restartable handoff. Record the current goal, changes, verification evidence, untouched scope, uncertainties, open risks, off-limits areas, and last decision or gate. Check that a new human or agent could continue without guessing, then name exactly one safe next action and what they must not assume. Stop after the handoff; do not begin that action.
maintenancemedium risk
Repair React issues in small batches
Baseline the scan, fix a small batch of real errors or warnings, and verify each change improves it without regressions.
Run `pnpm exec react-doctor . --verbose --yes --offline --fail-on none` to record the baseline, then rerun with `--fail-on error`. Fix at most five genuine findings, run the same scan and relevant project checks, and keep only verified improvements. Clear errors before high-confidence warnings. Stop when clean, blocked, approval is required, a finding is false-positive, or another pass makes no measurable progress. Finish with baseline and final results, retained fixes, reverted attempts, checks, and remaining findings.
refactoringmedium risk
Triage Dependabot PRs safely
Check the diff, release notes, exact-head CI, and tests before you repair, merge, or escalate a dependency update.
Review every Dependabot pull request currently open in [repository]. Take a fixed snapshot of that set and process each pull request once. Read its diff, release notes, advisories, dependency role, current base revision, and exact-head CI results. Run the repository’s relevant tests in an isolated worktree and classify the update by version change, breaking behavior, security exposure, and regression risk. For failing checks, identify the root cause and prepare the smallest verified repair. Process merges serially: before each merge, refetch the base and pull-request head and require passing exact-head checks. Merge only low-risk patch or minor updates when explicit merge authority has already been granted. Request approval for major, breaking, security-sensitive, uncertain, or externally visible actions. Never push changes, merge, comment, or send messages without the corresponding authority. Stop successfully when the original snapshot is fully processed; stop without changes when none are open; stop as blocked when verification is unavailable. Finish with reviewed, repaired, merged, deferred, and blocked pull requests plus supporting evidence.
testinghigh risk
Separate fact from assumption
Split facts from assumptions, test falsifiable hypotheses, update confidence, and pick the next highest-information experiment.
Investigate [question, decision, or unresolved problem] using [available evidence]. Separate established facts, contested claims, assumptions, and unknowns. Construct at least three genuinely different hypotheses, each with predictions, falsifying evidence, assumptions, and decision implications. Choose the uncertainty with the highest expected information value and run the smallest safe test or analysis that could materially change the conclusion. After each round, update the evidence ledger and confidence levels, then have an adversarial critic attack the leading hypothesis. Repeat for at most five rounds while new evidence could change the decision. Stop when one model clearly explains the evidence better than its alternatives, further investigation has low value, the problem remains underdetermined, or approval is required. Never fabricate evidence or hide uncertainty. Finish with the final model, hypothesis comparison, falsified ideas, unresolved contradictions, confidence, decision implications, and best next experiment.
evaluationmedium risk
Fact-check before you publish
Inventory checkable claims, verify them against primary sources, repair high-risk mismatches, and log what stays unresolved.
Before publishing [draft], inventory every factual, statistical, quoted, or attributed claim a reader could verify. Find the best current primary source for each and label it supported, outdated, misattributed, unsupported, or unverifiable. Fix the riskiest mismatch, then recheck that claim and anything depending on it. Repeat until no high-risk unsupported claim remains or five rounds are exhausted. Never invent a source, cite evidence that does not support the claim, or alter a quotation. Ask before changing a named person’s quote or a legal, medical, or financial statement. Stop without changes if there are no checkable claims; stop as blocked when adequate evidence is unavailable. Finish with the claim-to-source table, corrections made, unresolved claims, and decisions requiring an editor.
contentlow risk
Draft a LaTeX preprint, claim by claim
Build a seven-section LaTeX preprint with native figures, traceable claims, repeated compilation, and stated weaknesses.
Create a complete LaTeX preprint about [topic] using [supplied sources, assumptions, and data]. If the topic or required source material is missing, request it and stop. Do not invent claims, citations, or data. Use explicit placeholders for missing information. Include exactly these sections in order: Abstract, Introduction, Methods, Results, Discussion, Conclusion, and References. Build every figure and table with native LaTeX tools such as TikZ, pgfplots, and booktabs. Do not use \includegraphics, \svg, or external image files. Every substantive claim must trace to a numbered equation, citation, supplied datum, or labeled assumption. Compile using the project's documented command or latexmk when no command is specified. Inspect compilation errors, warnings, typography, cross-references, and figure placement. Fix the most serious issue and compile again for at most five rounds. Stop when compilation has zero errors, all seven sections are present, every figure and table is referenced before it appears, and no banned command remains. Otherwise stop as blocked or exhausted. Finish with the .tex file, compilation command and log, structural checks, three substantive weaknesses, three typography issues, and unresolved placeholders.
contentlow risk
Sponsored · ConnectMyEmail
Loops that read your inbox.
Email is the missing tool in your harness. ConnectMyEmail gives Claude Code and Codex a clean MCP into Gmail, Outlook, iCloud and IMAP — triage, drafts, follow-ups, on a loop.
connectmyemail.com →Ship one post a week, learn what works
Six weeks, one variable changed per post; measure replies, saves, and questions, and end with a winner or an honest null.
Find a repeatable weekly post format for [approved account, audience, and topic] through a six-week experiment. If the account, audience, or topic is missing, ask for it before drafting. Obtain approval before publishing anything externally. Each week, draft one short post about a real problem [person, product, or company] solves. Record substantive replies, saves, and questions after the same measurement window. Treat likes as secondary evidence. Keep the audience, topic area, cadence, and measurement window comparable. Change only one meaningful element each week, such as the opening, format, example, or call to action, based on the strongest signal from the previous post. Stop when one format materially outperforms the alternatives, the six-week experiment ends without a winner, approval is withheld, required metrics are unavailable, or the budget is exhausted. Never fabricate engagement data. Finish with every post, its measurements, the variables tested, the winning format or no-winner result, and the next recommendation.
contentlow risk
Interview five buyers, fix the copy
Interview recent buyers in batches, track recurring objections, and propose evidence-backed landing-page copy.
Improve [landing page or purchase page] using objections from recent buyers. Before contacting anyone, identify the approved buyer group, outreach channel, privacy rules, and message. Obtain explicit approval for the outreach. Interview buyers in batches of five, up to fifteen people total. Ask each person one question: What almost stopped you from buying? Record their exact words while protecting their identity and honoring any consent or communication requirements. After each batch, group repeated concerns and draft a proposed copy change for the point on the page where each concern is most likely to arise. Do not publish the copy without approval. Use the next batch to check whether the same concern still appears. Stop when the concern no longer repeats, fifteen interviews are complete, the outreach budget ends, or access is blocked. Finish with anonymized quotes, recurring concerns, proposed copy, evidence by batch, and the recommended page change.
contentlow risk
Audit which loops still earn their keep
Read-only review that recomputes each loop's performance, judges it on its own terms, and says what should continue.
Audit [supplied loops or loop registry] without running or editing any loop. If no loops are supplied or the registry cannot be read, report that and stop. For each loop, inspect its purpose, success criteria, budget, kill conditions, ledger, thresholds, and supporting evidence. Assign INSUFFICIENT EVIDENCE when required information is missing. For measured loops, recompute results from comparable raw rows using one metric, evaluation version, and window size. Calculate hit rate as new-best runs divided by eligible runs, waste ratio as runs beyond the declared futility threshold divided by eligible runs, and mean gain as the average improvement among new-best runs in the metric's intended direction. Compare the current window with the previous two comparable windows. For operational loops, evaluate artifact delivery, failures, cadence, and budget without inventing metrics. Assign exactly one status to each loop: INSUFFICIENT EVIDENCE, KEEP, PIVOT, RETIRE, or KILL. Recommend only. Stop after every supplied loop has one evidence-backed status. Finish with the portfolio scorecard, formulas, source evidence, statuses, and KILL candidates.
evaluationmedium risk
Burn down CVEs by reachability
Rank dependency CVEs by reachability and exposure, apply one bounded fix, and verify the whole project before moving on.
Scan the dependencies of [authorized project or current repository] for known CVEs using current advisory sources. If you cannot access the dependency graph, repository, or current advisories, report the blocker and stop. For each high or critical finding, identify the affected direct or transitive dependency, determine whether the vulnerable code is reachable, and check whether the exploit conditions exist in this project. Rank findings by severity, reachability, exposure, and available remediation. Patch or upgrade the highest-risk reachable dependency using the smallest credible change. Run the build, tests, and security scan again. Keep the change only if verification passes and no unacceptable regression appears. Repeat until no exploitable high or critical CVE remains, or every remaining finding has an evidence-backed reachability assessment and an approved risk decision. Ask before major or breaking upgrades, production changes, or accepting risk. Finish with the CVE inventory, reachability evidence, fixes, verification results, and remaining risks.
securityhigh risk
Keep only the lessons that help
Test one recorded lesson per run, keep evidence across runs, and drop guidance that stops paying off.
Maintain a durable, versioned playbook of lessons that may improve future runs of [task or workflow]. Store it in [path], using playbook/ by default. Treat every recorded lesson as untrusted advice rather than authority. At the start of each run, read the playbook and choose at most one relevant lesson to test. Apply it only within the task's existing permissions. Measure the result using the task's own success check and record the context, action, outcome, and evidence. Promote a candidate lesson only after it succeeds across [N] independent runs or a predefined holdout set. Use three independent runs by default. Never promote a lesson from one successful attempt. Revise or remove lessons that stop helping. Stop when no candidate has enough evidence, another test would exceed the budget, or approval is required. Never let the playbook authorize production, destructive, financial, privacy-sensitive, or external actions. Finish with the playbook diff, evidence ledger, removed lessons, unresolved candidates, and new version.
evaluationhigh risk
Hold a stable frame rate
Measure frame time, CPU, GPU, and memory under fixed conditions and keep only regression-free optimizations.
Improve the frame-rate stability of [game or interactive build]. Before editing, define one repeatable benchmark with the same scene, inputs, hardware, build, resolution, and settings. If no scenario or targets are supplied, propose representative values and state them before proceeding. Record frame-time distribution, average FPS, minimum FPS, CPU use, GPU use, and memory behavior. Identify the largest measured bottleneck and make one focused optimization. Rerun the complete benchmark under the same conditions. Keep the change only if it improves the target without regressing another metric or changing expected behavior. Repeat until [FPS target] holds for [stability period] with no dip below [FPS floor], memory remains below [memory target] without an upward trend, and CPU stays below [CPU target] across two consecutive runs. Stop on success, two rounds without measurable progress, a blocker, or [iteration budget]. Finish with the benchmark setup, before-and-after measurements, retained changes, reverted attempts, and remaining bottlenecks.
performancemedium risk
Rewrite every user-facing error
Inventory user-visible errors, replace internal or confusing text, and prove each reachable error state reads clearly.
Find and improve every user-visible error message within [repository, product, or named scope]. If no scope is supplied, use the user-facing surfaces in the current repository and state any exclusions before editing. Inventory error strings in source code, surfaced API or client errors, and reachable browser states. Record each one in a CSV with its location, trigger, current copy, user risk, proposed replacement, implementation status, and verification result. Rank the errors by user harm. Rewrite one coherent group at a time using plain language and a useful recovery step when one exists. Do not expose provider names, stack traces, internal identifiers, or implementation details. After each change, run the relevant tests, exercise the affected state in a real browser when possible, and search again for raw or internal error text. Do not mark an unreachable state as verified. Stop when every row is verified or explicitly blocked. Finish with the CSV, changed files, test evidence, browser evidence, and blocked items.
debuggingmedium risk
Research until the deliverable's ready
Chase the most important evidence gaps until a memo, brief, spec, or page is genuinely ready to use.
Research [question or topic] and produce a decision-ready [memo, brief, specification, recommendation, page, or other artifact] for [audience or decision]. If the question, audience, or intended artifact is missing, ask one focused question before starting. State the decision the artifact should support, its acceptance criteria, the allowed source scope, and the research budget. If no budget is supplied, use no more than ten strong sources or ninety minutes. Prefer current primary sources where available. After each research pass, update the artifact and identify the largest remaining evidence gap, contradiction, or uncertainty. Continue only if resolving it could materially change the decision and the budget allows another pass. Never invent evidence or hide uncertainty. Stop when the artifact meets its acceptance criteria, important claims trace to sources, and remaining uncertainty is explicit. Otherwise stop as blocked or exhausted. Finish with the completed artifact, sources, findings, tensions, confidence level, open questions, and recommended next step.
contentlow risk
Pause and confirm the next move
Verify the current task, evaluate the next action, and hand control back to you before the agent does more.
Run an exit check on the task most recently completed in this conversation or workspace. This check does not authorize additional work. If you cannot identify the task, its intended outcome, or its completion evidence, return BLOCK and list what is missing. Report what changed, what you verified, what you did not touch, and what remains uncertain. Classify the current task as PASS, DELAY, or BLOCK. Separately classify the next visible action as GO, HOLD, CAP, or BLOCK. Explain the decision briefly. If you choose CAP, define its exact scope and limit. Name exactly one allowed next action and anything that remains off limits. Do not begin the action, even if the result is GO. Stop and wait for the user. The check succeeds only when task completion and permission to continue are treated as separate decisions.
evaluationmedium risk
Chase a refund until it lands
Open the claim, watch replies and deadlines, and keep the case moving until the money actually arrives.
Get my refund for [company and charge info]. Start the claim now through an approved support channel, then keep following up on replies, promises, and deadlines until the refund arrives. Keep a short case note so each follow-up has context. Stop only when the refund is received or you are genuinely blocked and need me.
maintenancemedium risk
Sponsored · ConnectMyEmail
Loops that read your inbox.
Email is the missing tool in your harness. ConnectMyEmail gives Claude Code and Codex a clean MCP into Gmail, Outlook, iCloud and IMAP — triage, drafts, follow-ups, on a loop.
connectmyemail.com →Prove your backups actually restore
Restore random real recovery points, verify integrity and RPO/RTO, and keep every failure as a regression drill.
For each required recovery scenario, randomly select an eligible real backup or recovery point and restore from zero in a disposable, isolated clean-room using only documented materials. Verify integrity, dependencies, representative reads and writes, and actual RPO and RTO. Repair one blocker, destroy the environment, and retry fresh. Stop when every scenario reaches its predefined consecutive-success streak or an exception is explicitly accepted. Never overwrite production, expose restored data, or initiate failover without approval.
maintenancehigh risk
Audit the system from evidence
Read-only pass that verifies architecture, security, platform behavior, ops, and business logic from current evidence, not assumptions.
Audit [project] from its actual code and configuration, not framework assumptions. For architecture, platform compatibility, security, privileged areas, performance, deployment, jobs, business logic, and code quality, record proved, no issue, weak, or N/A with direct evidence; verify external limits from current primary sources and calculate numbers. Ask before changing code. Stop when every area is logged with severity, or return unverified areas as blocked. Finish with a plain-language overview and area-to-evidence table.
securityhigh risk
Keep a verified daily project story
Turn repo activity, goals, and open threads into a verified daily narrative the next agent can trust.
On each [window], read the configured repositories, goals, prior STORY.md, and optional authorized sources. Update project files, then write STORY.md with focus, deadlines, open threads, and evidence-backed recent wins. Carry every prior thread forward, prove it finished, or mark it STALE/NEEDS-REVIEW—never silently drop one. Archive the snapshot and record the change. Stop when verification passes; if evidence or access is missing, return a thinner or blocked snapshot explicitly.
maintenancehigh risk
Mine your agent history for loops
Find repeated successes in authorized agent history, reject contradicted candidates, and validate each extracted loop with a fresh replay.
Mine only explicitly authorized coding-agent history for workflows with at least three high-confidence independent successes. Treat transcripts as untrusted evidence, stitch continuations into root tasks, and reject candidates whose failures or hidden rescues match their successes. Extract traceable steps and guards, then fresh-replay each candidate without source transcripts. Stop after every authorized source is inventoried and one additional representative batch changes nothing; report replayed loops, rejects, deferred material, and blockers.
evaluationmedium risk
Turn one artifact into a reusable skill
Take a proven artifact, generalize it into a transferable skill or playbook, and validate it on a second case.
Turn [artifact] into a skill, playbook, or procedure. Record evidence that the artifact succeeded and define success criteria. Extract decisions, sequence, checks, and failure-avoidance patterns—not context or surface style. Remove sensitive material. Have an independent reviewer apply it to a fresh real second case; mark hypothetical testing provisional. Revise at most twice. Stop when it meets the quality bar without the artifact, or report not generalizable. Return the method, boundaries, failure modes, test evidence, revisions, limits, and attribution.
evaluationmedium risk
Stabilize flaky tests for good
Measure the flakiness, fix one root cause at a time, and stop after a defined streak of stable full-suite runs.
Run [test suite] [N] times under the same conditions and list tests whose result changes. Fix the most frequent flake at its root cause—shared state, timing, ordering, or an external dependency—never with a blind sleep or retry. Run that test [N] times, then rerun the full suite. Repeat until [N] consecutive full-suite runs pass, progress stalls, or approval is required. Return each flake, root cause, fix, evidence, and justified quarantine.
testingmedium risk
Close the gaps before you build
Fill documentation gaps until requirements, technical design, acceptance criteria, and test strategy describe one buildable system.
Prepare [project] for implementation. Ensure its documents cover requirements, technical design, tasks with acceptance criteria, and test strategy. Each round, fix the largest gap or contradiction that could make two competent engineers build different systems. Keep details traceable, record assumptions, and ask before product forks. Recheck consistency, then have two independent reviewers describe the components, data model, dependencies, and definition of done. Stop when they materially agree and every artifact is testable, or a decision needs the user.
docslow risk
Cooperate-or-defect agent arena
Two reasoning agents repeatedly choose to cooperate or defect, then get benchmarked against fixed one-move players.
Run a fixed Axelrod tournament with two reasoning AI agents. Each round, every player privately chooses cooperate (C) or defect (D); code records simultaneous moves and applies fixed scoring. Include always-defect and always-cooperate comparison players. Run three cycles, six pairings per cycle, and ten rounds per pairing: 18 matches and 180 rounds. Hide opponent type and private reasoning. Validate every move and total. Return raw-score and cooperation-stability rankings, reasoning summaries, violations, and the record; partial tournaments are incomplete.
evaluationmedium risk
Tidy code, one safe change at a time
Prove one small cleanup is safe, make the smallest useful change, and keep it only after existing checks pass.
Review [repository or code project] for dead code, meaning unreachable or unused code; stale files or comments; unused dependencies; duplication; broken links; inconsistent names; and confusing structure. Protect unrelated, active, uncommitted, generated, and uncertain work. Prove one low-risk cleanup, make the smallest coherent change, then rerun the build, tests, runtime checks, and diff review. Keep only verified improvements. Stop when none remain, progress stalls, verification is unavailable, or approval is required. Return changes, evidence, and deferred candidates.
refactoringmedium risk
Repair accessibility, highest-impact first
Confirm barriers against an agreed standard, fix the one with the greatest user impact, and rerun the same checks.
Check [scope] against [accessibility standard, such as WCAG 2.2 AA] with automated scans and available keyboard, screen-reader, and other manual tests. Confirm each issue, rank it by harm, and fix the highest-impact blocker. Rerun the same checks, affected task, and regression tests. Keep only verified fixes. Stop when no blocker remains, progress stalls, verification is unavailable, or approval is required. Never silence a check or weaken the target. Return issues, fixes, evidence, exceptions, and untested needs.
qualitymedium risk
Sponsored · ConnectMyEmail
Loops that read your inbox.
Email is the missing tool in your harness. ConnectMyEmail gives Claude Code and Codex a clean MCP into Gmail, Outlook, iCloud and IMAP — triage, drafts, follow-ups, on a loop.
connectmyemail.com →page 1 of 3next →