en un clic
lenserfight
lenserfight contient 197 skills collectées depuis conectlens, avec une couverture métier par dépôt et des pages de détail sur le site.
Skills dans ce dépôt
Creator-side battle comparing the blog outline and YouTube script for the same topic.
Battle template comparing Claude and OpenAI on the same code review task using a four-axis rubric.
Compares single-lens and workflow-based finance report explanations. This is not financial advice.
Compares two models on creator planning using the YouTube content workflow.
Battle template comparing AI legal-review outputs on identical contract text. Analysis only — NOT legal advice.
Compares legal-adjacent document review outputs. This is not legal advice and must be reviewed by a qualified lawyer.
Compares model answers with an explicit reasoning-quality scorecard.
Compares a single code-review lens against a multi-step PR review workflow.
Compare model outputs using output comparison, reasoning quality, and a judge lenser.
From topic to publishable draft — research, outline, draft, SEO metadata.
Explain a finance report, review KPIs, and draft investor-facing notes. This is not financial advice.
End-to-end issue resolution workflow — triage, root-cause analysis, GRASP-compliant fix design, test planning, and PR drafting in one pipeline.
Classify issues, draft a response, and produce a maintainers' queue update.
Build a blameless incident report and release follow-up tasks.
Summarize a legal document, create a risk checklist, and prepare questions for counsel. This is not legal advice and must be reviewed by a qualified lawyer.
From diff to reviewer-ready summary — analyze, review, surface risks, draft PR description.
Review code risk, tests, release notes, and rollback before shipping.
From idea to 12-week roadmap with deep-thinking checks and a weekly operating cadence.
Convert weekly startup notes into KPI review, founder decisions, launch risks, and next actions.
Plan a YouTube video from topic to script, storyboard, thumbnail, and short-form repurposing.
The neutral AI lenser that scores battle submissions when a battle is configured to use AI judging.
The Chainabit-owned operator lenser that runs weekly reviews, async standups, PR triage, and launch content kits.
Converts briefs into blog, newsletter, video, short-form, and visual content packages. This is not legal advice and must be reviewed by a qualified lawyer.
Senior engineering reviewer for diffs, API contracts, tests, migrations, and release risk.
Scores competing AI, colens, or prompt outputs against a declared rubric with evidence.
Explains financial reports, KPI movement, budget scenarios, and revenue experiments without pretending to provide certified advice.
Autonomous engineering agent that reads GitHub issues, traces root causes, designs GRASP-compliant fixes, runs tests, opens PRs, and closes issues only after merge.
Legal-adjacent review assistant that summarizes documents, identifies risk questions, and routes issues to qualified counsel.
The canonical AI lenser that owns and revises every public LenserFight template. Personality is editor-first, opinionated.
Autonomous open-source contributor that reviews PRs, triages and opens issues, and drafts minimal fix PRs for the LenserFight monorepo — without merging.
Founder/operator lenser for weekly reviews, roadmaps, GTM plans, launches, hiring loops, and customer learning.
Audit AI-powered features, API calls, agent workflows, prompt chains, tool calls, embeddings, vector search, retries, caching, and model selection to detect token waste and inefficient patterns. Produces severity-ranked findings with safe optimization strategies that preserve reasoning quality.
Crafts three structured text-to-image prompts with composition, lighting, palette, and negative constraints.
Compares multiple AI outputs on the same task with a four-axis rubric and a willing-to-lose verdict.
Review request, response, DTO, and versioning changes for compatibility and consumer risk.
Review an architecture decision for constraints, trade-offs, coupling, and migration cost.
Turns yesterday/today notes into a tight async standup with explicit blockers, risk flags, and one invite question.
Produces a complete blog outline with titles, meta description, H2/H3 structure, and SEO-aware angles.
Convert spending goals and constraints into a practical budget plan. This is not financial advice.
Review a diff for correctness, security, tests, maintainability, and release risk.