[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79F97TPJTQKXEN2HTWXBG35":3,"skill-same:01M79F97TPJTQKXEN2HTWXBG35":60},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":14,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M79F97TPJTQKXEN2HTWXBG35","prompts-check-for-signal",null,"Apply the \"Check for Signal\" prompt-library workflow: given a hypothesis or claim, design and execute (or scaffold the execution of) a decisive test that definitively proves or falsifies the claim — never artificially. Create a new isolated folder under experiments\u002F (or equivalent), document everything in FINDINGS.md that **leads with the conclusion**, followed by technical supporting evidence. Do not modify artifacts outside the new folder. Use when the user says \"check for signal on this claim\", \"design a decisive test for\", \"falsify this hypothesis\", \"prove or disprove\", \"use check-for-signal\", or runs \u002Fprompts-check-for-signal.","zfifteen\u002Fskills-catalog","zfifteen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F221906715?v=4","01M79CQFXDZM5J5CJTCECPFA66","Dionisio Alberto Lopez III","01M79CQFY4C62PN8A2T5KDAHGA",1,"MIT","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fprompts-check-for-signal\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: prompts-check-for-signal\ndescription: >\n  Apply the \"Check for Signal\" prompt-library workflow: given a hypothesis or claim, design\n  and execute (or scaffold the execution of) a decisive test that definitively proves or\n  falsifies the claim — never artificially. Create a new isolated folder under experiments\u002F\n  (or equivalent), document everything in FINDINGS.md that **leads with the conclusion**,\n  followed by technical supporting evidence. Do not modify artifacts outside the new folder.\n  Use when the user says \"check for signal on this claim\", \"design a decisive test for\",\n  \"falsify this hypothesis\", \"prove or disprove\", \"use check-for-signal\", or runs\n  \u002Fprompts-check-for-signal.\nwhen-to-use: \"Designing or running a clean, high-leverage experiment or test whose outcome will materially update belief about a specific claim. Strong triggers: 'decisive test', 'falsify', 'prove or disprove', 'check for real signal', 'experiments\u002F folder'.\"\nargument-hint: \"\u003Chypothesis, claim, or research question to design a decisive test for>\"\nallowed-tools: [\"read_file\", \"grep\", \"list_dir\", \"write\", \"search_replace\", \"run_terminal_cmd\", \"web_search\"]\nmetadata:\n  short-description: \"Design and document a decisive falsifying\u002Fproving test for a claim (experiments\u002F isolation)\"\n  canonical-codex-skill: \"\u002FUsers\u002Fvelocityworks\u002F.codex\u002Fskills\u002Fprompts-check-for-signal\u002FSKILL.md\"\n  version: \"1.0.0\"\n---\n\n# Check for Signal — Grok Port\n\nDesign and document (and where possible execute) a clean, high-power test that can actually move the needle on a hypothesis instead of producing ambiguous or noisy results.\n\n## Purpose\n\nThe original prompt insists on **decisive** tests that \"definitively prove or falsify (never artificially)\" and requires strict workspace isolation plus conclusion-first documentation. This port makes the skill an active experiment designer and documenter inside the Grok tool environment.\n\n## Invocation\n\n```\n\u002Fprompts-check-for-signal \u003Chypothesis or claim description>\n```\n\nAny additional context in the conversation (prior results, existing code, data files) is part of the input material.\n\n## Core Contract (Preserved)\n\nGoal: Design and execute a test that will definitively prove or falsify (never artificially) the following hypothesis\u002Fclaim.\n\n- Create a **new folder under `experiments\u002F`** (or project-appropriate equivalent) for **all** artifacts and documentation.\n- **Do not modify any artifacts outside** of the new folder.\n- Meticulously document findings in `FINDINGS.md` that **leads with the conclusion**, followed by technical supporting evidence.\n\n## Grok Workflow\n\n1. **Clarify the Claim**\n   - Restate the exact hypothesis in the clearest, most falsifiable form possible.\n   - Surface hidden assumptions, scope, and what \"definitively\" would look like for this claim.\n\n2. **Design the Decisive Test**\n   - Choose the smallest, highest-power experiment or analysis that can produce a clear positive or negative result.\n   - Prefer deterministic or low-variance designs over statistical ones when both are viable (aligns with project AGENTS.md preference for deterministic reasoning).\n   - Define the success\u002Ffailure criteria in advance (what numbers, what structural property, what invariant violation, etc. would count as proof or falsification).\n   - Identify required inputs, controls, and how to make the result auditable.\n\n3. **Scaffold the Experiment Workspace**\n   - Target: `experiments\u002F\u003Ckebab-case-claim-slug>\u002F` or `experiments\u002Fsignal-\u003Cslug>\u002F`\n   - Create inside it (using `write`\u002F`search_replace`):\n     - `README.md` (hypothesis, test design, how to run)\n     - `FINDINGS.md` (template or initial entry — see format below)\n     - Any scripts, config, or small programs needed for the test (keep minimal)\n     - `Makefile` or run instructions if compilation\u002Fexecution is involved\n\n4. **Execute or Guide Execution (when possible)**\n   - Use available tools (`run_terminal_cmd`, code via write+exec patterns, web tools for data, etc.) to carry out the test.\n   - If full execution is not possible in the current turn, produce a complete, runnable recipe that a follow-up agent or human can execute with zero ambiguity.\n\n5. **Document Conclusion-First**\n   - The `FINDINGS.md` **must** open with a clear prose sentence or short paragraph stating the conclusion.\n   - Then provide the technical evidence, methodology, raw outputs, statistical or structural results, and any caveats.\n   - Example opening:\n     > \"The test falsifies the claim that chamber resets are uniformly distributed: in the 10,000-sample run, reset events clustered 3.2× more frequently immediately after leftmost-minimum transitions than expected under uniformity (p \u003C 0.001 via exact permutation test).\"\n\n6. **Verification & Audit Trail**\n   - Record exact commands, seeds (if any), tool calls, file hashes, and timestamps where relevant.\n   - Make it possible for a third party to reproduce the exact conclusion from the artifacts.\n\n## FINDINGS.md Required Shape\n\n```markdown\n# FINDINGS — \u003Cshort claim label>\n\n**Conclusion**: [One or two sentences that a reader can quote as the result. Lead with this.]\n\n**Hypothesis under test**: [restatement]\n\n**Test design**: [1-3 paragraphs describing the decisive procedure and why it has power]\n\n**Execution details**:\n- Date\u002Ftime\n- Exact commands \u002F scripts run\n- Inputs \u002F datasets \u002F parameters\n- Environment (if relevant)\n\n**Results**:\n[Tables, key numbers, structural observations, logs, images descriptions, etc.]\n\n**Interpretation**:\n[How the data supports or refutes the claim. Be quantitative where possible.]\n\n**Limitations & caveats**:\n[Honest statement of what the test does not cover]\n\n**Next actions** (optional):\n- ...\n```\n\n## Success Criteria\n\n- A new isolated `experiments\u002F...` folder exists containing the complete record.\n- `FINDINGS.md` literally leads with the conclusion in plain prose.\n- The test design is genuinely capable of producing a decisive (non-ambiguous) result.\n- No files were touched outside the experiments folder.\n- A later reader can understand exactly what was tested and what the outcome means without re-running the entire conversation.\n\n## Guardrails\n\n- \"Never artificially\" means do not design a test whose outcome is foreordained by construction or by cherry-picked data. If the only honest answer is \"this claim is currently untestable with available resources,\" say so clearly instead of forcing a weak test.\n- Prefer tests that can be executed deterministically or with full auditability.\n- In PGS contexts: tests should target PGS objects, invariants, or rule applications directly when the hypothesis touches them.\n- Workspace isolation is absolute — this skill does not \"helpfully\" edit files elsewhere in the project.\n\nThis port converts the original \"Check for Signal\" prompt into a disciplined experiment harness creator and conclusion-first reporter that works with Grok's full toolset.\n","# Check for Signal — Grok Port\n\nDesign and document (and where possible execute) a clean, high-power test that can actually move the needle on a hypothesis instead of producing ambiguous or noisy results.\n\n## Purpose\n\nThe original prompt insists on **decisive** tests that \"definitively prove or falsify (never artificially)\" and requires strict workspace isolation plus conclusion-first documentation. This port makes the skill an active experiment designer and documenter inside the Grok tool environment.\n\n## Invocation\n\n```\n\u002Fprompts-check-for-signal \u003Chypothesis or claim description>\n```\n\nAny additional context in the conversation (prior results, existing code, data files) is part of the input material.\n\n## Core Contract (Preserved)\n\nGoal: Design and execute a test that will definitively prove or falsify (never artificially) the following hypothesis\u002Fclaim.\n\n- Create a **new folder under `experiments\u002F`** (or project-appropriate equivalent) for **all** artifacts and documentation.\n- **Do not modify any artifacts outside** of the new folder.\n- Meticulously document findings in `FINDINGS.md` that **leads with the conclusion**, followed by technical supporting evidence.\n\n## Grok Workflow\n\n1. **Clarify the Claim**\n   - Restate the exact hypothesis in the clearest, most falsifiable form possible.\n   - Surface hidden assumptions, scope, and what \"definitively\" would look like for this claim.\n\n2. **Design the Decisive Test**\n   - Choose the smallest, highest-power experiment or analysis that can produce a clear positive or negative result.\n   - Prefer deterministic or low-variance designs over statistical ones when both are viable (aligns with project AGENTS.md preference for deterministic reasoning).\n   - Define the success\u002Ffailure criteria in advance (what numbers, what structural property, what invariant violation, etc. would count as proof or falsification).\n   - Identify required inputs, controls, and how to make the result auditable.\n\n3. **Scaffold the Experiment Workspace**\n   - Target: `experiments\u002F\u003Ckebab-case-claim-slug>\u002F` or `experiments\u002Fsignal-\u003Cslug>\u002F`\n   - Create inside it (using `write`\u002F`search_replace`):\n     - `README.md` (hypothesis, test design, how to run)\n     - `FINDINGS.md` (template or initial entry — see format below)\n     - Any scripts, config, or small programs needed for the test (keep minimal)\n     - `Makefile` or run instructions if compilation\u002Fexecution is involved\n\n4. **Execute or Guide Execution (when possible)**\n   - Use available tools (`run_terminal_cmd`, code via write+exec patterns, web tools for data, etc.) to carry out the test.\n   - If full execution is not possible in the current turn, produce a complete, runnable recipe that a follow-up agent or human can execute with zero ambiguity.\n\n5. **Document Conclusion-First**\n   - The `FINDINGS.md` **must** open with a clear prose sentence or short paragraph stating the conclusion.\n   - Then provide the technical evidence, methodology, raw outputs, statistical or structural results, and any caveats.\n   - Example opening:\n     > \"The test falsifies the claim that chamber resets are uniformly distributed: in the 10,000-sample run, reset events clustered 3.2× more frequently immediately after leftmost-minimum transitions than expected under uniformity (p \u003C 0.001 via exact permutation test).\"\n\n6. **Verification & Audit Trail**\n   - Record exact commands, seeds (if any), tool calls, file hashes, and timestamps where relevant.\n   - Make it possible for a third party to reproduce the exact conclusion from the artifacts.\n\n## FINDINGS.md Required Shape\n\n```markdown\n# FINDINGS — \u003Cshort claim label>\n\n**Conclusion**: [One or two sentences that a reader can quote as the result. Lead with this.]\n\n**Hypothesis under test**: [restatement]\n\n**Test design**: [1-3 paragraphs describing the decisive procedure and why it has power]\n\n**Execution details**:\n- Date\u002Ftime\n- Exact commands \u002F scripts run\n- Inputs \u002F datasets \u002F parameters\n- Environment (if relevant)\n\n**Results**:\n[Tables, key numbers, structural observations, logs, images descriptions, etc.]\n\n**Interpretation**:\n[How the data supports or refutes the claim. Be quantitative where possible.]\n\n**Limitations & caveats**:\n[Honest statement of what the test does not cover]\n\n**Next actions** (optional):\n- ...\n```\n\n## Success Criteria\n\n- A new isolated `experiments\u002F...` folder exists containing the complete record.\n- `FINDINGS.md` literally leads with the conclusion in plain prose.\n- The test design is genuinely capable of producing a decisive (non-ambiguous) result.\n- No files were touched outside the experiments folder.\n- A later reader can understand exactly what was tested and what the outcome means without re-running the entire conversation.\n\n## Guardrails\n\n- \"Never artificially\" means do not design a test whose outcome is foreordained by construction or by cherry-picked data. If the only honest answer is \"this claim is currently untestable with available resources,\" say so clearly instead of forcing a weak test.\n- Prefer tests that can be executed deterministically or with full auditability.\n- In PGS contexts: tests should target PGS objects, invariants, or rule applications directly when the hypothesis touches them.\n- Workspace isolation is absolute — this skill does not \"helpfully\" edit files elsewhere in the project.\n\nThis port converts the original \"Check for Signal\" prompt into a disciplined experiment harness creator and conclusion-first reporter that works with Grok's full toolset.\n",{"name":5,"metadata":24,"description":28,"when-to-use":29,"allowed-tools":30,"argument-hint":38},{"version":25,"short-description":26,"canonical-codex-skill":27},"1.0.0","Design and document a decisive falsifying\u002Fproving test for a claim (experiments\u002F isolation)","\u002FUsers\u002Fvelocityworks\u002F.codex\u002Fskills\u002Fprompts-check-for-signal\u002FSKILL.md","Apply the \"Check for Signal\" prompt-library workflow: given a hypothesis or claim, design and execute (or scaffold the execution of) a decisive test that definitively proves or falsifies the claim — never artificially. Create a new isolated folder under experiments\u002F (or equivalent), document everything in FINDINGS.md that **leads with the conclusion**, followed by technical supporting evidence. Do not modify artifacts outside the new folder. Use when the user says \"check for signal on this claim\", \"design a decisive test for\", \"falsify this hypothesis\", \"prove or disprove\", \"use check-for-signal\", or runs \u002Fprompts-check-for-signal.\n","Designing or running a clean, high-leverage experiment or test whose outcome will materially update belief about a specific claim. Strong triggers: 'decisive test', 'falsify', 'prove or disprove', 'check for real signal', 'experiments\u002F folder'.",[31,32,33,34,35,36,37],"read_file","grep","list_dir","write","search_replace","run_terminal_cmd","web_search","\u003Chypothesis, claim, or research question to design a decisive test for>","main","d9535210da9af28aa76bca80de80355197e1b6d6","skills\u002Fprompts-check-for-signal","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog","https:\u002F\u002Fgithub.com\u002Fzfifteen","I like to measure things.","2026-07-19 23:41:54",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add zfifteen\u002Fskills-catalog --skill prompts-check-for-signal",{"tool":52,"command":53},"bunx","bunx skills add zfifteen\u002Fskills-catalog --skill prompts-check-for-signal",{"tool":55,"command":56},"pnpm","pnpm dlx skills add zfifteen\u002Fskills-catalog --skill prompts-check-for-signal","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fprompts-check-for-signal\u002FSKILL.md",true,[],[61,68,75,82,91,98],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M79GXQ2PWPT2E4CJYHXVJ0YE","Zotero","Use Zotero Desktop from Codex to enable\u002Fprobe the local API, search a local Zotero library, list items\u002Fcollections\u002Ftags, export BibTeX, insert citation keys into LaTeX or Markdown drafts, read indexed full text when requested, and import BibTeX\u002FRIS records into Zotero through the connector server. Use when the user mentions Zotero, citations, references.bib, BibTeX export, local Zotero API, localhost:23119, or adding citations from a Zotero library.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fzotero\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M79GXN85NETKBE06865CWK6Z","zoom-apps-sdk","Use when using Apps SDK.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M79GXCYD7FGYS932J9N9RFFY","youtube","Obtain accurate, timestamped YouTube video transcripts (preferring manual captions over auto-generated) as the primary deliverable, then derive summaries, key claims, or notes from that transcript.  Use when the user provides a YouTube URL (or video ID) and wants the transcript, a faithful summary, key claims with attribution, timestamped notes, or \"what does this video actually say\".  The skill is transcript-first: never substitute metadata, title, description, or search snippets for the spoken content.  Triggers: \"youtube transcript\", \"get the transcript of this video\", \"summarize this youtube video\", \"what did they say in https:\u002F\u002Fyoutube.com\u002F...\", \"key claims from this talk\".","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M79GX8EXHHYM566BKR7MS778","yeet","Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M79GX2HFJPX84NMRE5VBTYX9","x-post-creator","Create X-ready post threads and co-located story packages from the active conversation or referenced project material. Use when the user says turn this into an X-post, \u002Fx-post, make this into an X thread, or wants plain-language social posts with supporting images saved to docs\u002Fx-posts\u002F[story-name]\u002F.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fx-post-creator\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M79GWXQT4HBT6QME6QSBZJFA","x-api","Search, read, and write X posts through the local X API MCP server (the same backend used by the Codex x-api skill). Use for searching X\u002Fx.com, reading threads and replies, creating lists, staging\u002Fpublishing posts for @alltheputs, finding high-visibility reply targets for research outreach, ingesting public context, or any request that mentions \u002Fx-api or \"search X\".","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fx-api\u002FSKILL.md",[],[]]