evidence skills

xiaojiou176-open/codeflow

Skill Claude CodeCodex

Route the current job to the right Codeflow surface without overclaiming hosted, write-capable MCP, or published plugin support.

AlekseiUL/hermes-researcher-agent

Skill Claude CodeCodex

Convert public research documents and mixed file formats into Markdown before evidence review. Use for PDF, DOCX, PPTX, XLSX, HTML, CSV/JSON/XML, EPUB, ZIP bundles, and document intake before summaries, source ledgers, or research briefs.

AlekseiUL/hermes-researcher-agent

Skill Claude CodeCodex

Use when a Hermes agent must perform public-source research, source scouting, evidence grading, competitor/tool comparison, community-signal analysis, or decision-ready brief writing without private data or credentials.

mrgoonie/fable-thinking

Skill Claude CodeCodex

Reasoning protocol distilled from Claude Fable 5. Makes any model reason like Fable — evidence-grounded claims, multi-hypothesis diagnosis, concrete simulation, adversarial self-review, calibrated outcome-first delivery. Its never-skipped Floor check catches simple-looking trick questions models answer confidently…

yxk-lawyer/litigation-prep-skill-cn

Skill Claude CodeCodex

A Chinese-language preparation guide for a lawsuit, covering the type of claim, the legal basis for requests, required facts, and supporting evidence.

jeffy-Peng/jeffy-skills

Skill Claude CodeCodex

A research workflow for investigating products, companies, technologies, people, markets, industries, and complex events. It produces a traceable report based on sources, evidence, and analysis of how events developed, what forces shaped them, and how the parts work.

jeffy-Peng/jeffy-skills

Skill Claude CodeCodex

A writing guide for turning a person’s intended workplace message into clear, natural wording while keeping their meaning and voice. It covers messages and emails rather than technical reports or long documents.

fall-out-bug/sdp

Skill Claude CodeCodex

System design with progressive disclosure, produces workstream files.

fall-out-bug/sdp

Skill Claude CodeCodex

Feature planning orchestrator (discovery -> idea -> ux -> design -> workstream tree).

fall-out-bug/sdp

Skill Claude CodeCodex

Multi-agent quality review (QA + Security + DevOps + SRE + TechLead + Documentation + PromptOps).

vitas/evidra

Skill Claude CodeCodex

Use this skill when the user asks you to EXECUTE infrastructure mutations — commands that create, modify, or delete real resources. This includes: kubectl apply/delete/patch/create/replace/scale/rollout restart, helm install/upgrade/uninstall/rollback, terraform apply/destroy/import, docker run/rm/stop/kill…

Avyayalaya/agent-council

Skill Claude CodeCodex

Use when you want a per-claim evidence-tier audit on a text artifact before it ships — assign T1-T6 tiers to every load-bearing claim, surface calibration mismatches (high confidence on weak evidence, or honesty-theater under-claiming), and flag P11 (citation-as-decoration), P17 (pile-of-anecdotes-as-evidence), P54…

Stahl-G/briefloop

Skill Claude CodeCodex

Captures brief requirements in chat and writes onboarding.json for workspace initialization. Use when a user wants to set up a real BriefLoop workspace — collect answers in chat, write onboarding.json, then run init --from-onboarding.

Stahl-G/briefloop

Skill Claude CodeCodex

BriefLoop 专属产品经理与产品治理 Skill，代号北极星 Northstar。Use when deciding whether a BriefLoop requirement, PR, technical proposal, roadmap item, Pilot, launch, or postmortem is worth doing, belongs in the current version, needs evidence, or should be rejected; also use when engineering scope or product complexity is growing…

Stahl-G/briefloop

Skill Claude CodeCodex

Use when creating, running, continuing, inspecting, repairing, finalizing, or reviewing a BriefLoop SQLite/Codex workspace, including Solar Stock Periodic, market data, AI Second Opinion, Human observations, approved guidance, and successor runs. Prefer the single-session runtime continue path; use exact Store actions…

Avyayalaya/agent-prime

Skill Claude CodeCodex

Use when synthesizing user research, analyzing interview data, conducting discovery sprints, evaluating evidence quality across sources, or building research-backed feature hypotheses.

Conradgui/loop-craft

Skill Claude CodeCodex

Use when a user wants to design one bounded feedback loop from a goal, assess or upgrade an existing Agent Skill with feedback loops, distill a completed conversation or work record into a candidate workflow and, when compatible, a loop-aware Skill, build an accepted Loop Craft JSON definition, or check an existing…

Conradgui/loop-craft

Skill Claude CodeCodex

Use when an existing result needs a carefully staged repair.

Conradgui/loop-craft

Skill Claude CodeCodex

Follow the original workflow exactly and preserve this body.

DeepCogNeural/html-artifact-report-skill

Skill Claude CodeCodex

Create HTML report artifacts from notes or Markdown with paired JSON manifests for AI-agent audit and reuse.

phenomenoner/ai-agent-thinkroom

Skill Claude CodeCodex

Install and verify Thinkroom skills.

phenomenoner/ai-agent-thinkroom

Skill Claude CodeCodex

Operate Thinkroom research jobs.

phenomenoner/ai-agent-thinkroom

Skill Claude CodeCodex

Choose Thinkroom for consequential uncertainty.

nhppyqys/knowsift

Skill Claude CodeCodex

Compile collected videos, articles, documents, and research into layered, traceable knowledge documents or fail-closed claim certificates. Use when a user needs research synthesis that separates supported knowledge, conditional findings, practitioner experience, viewpoints, anecdotes, disputes, and rejected claims; do…