Grill
asgeirtj/system_prompts_leaks
Run an explicitly requested decision interview and record each settled decision in durable project documentation.
Run a multi-cycle research campaign — grill the question, decompose it into answerable sub-questions, investigate each against sources, then synthesize with confidence and gaps stated.
Apache-2.0Auto-check passed
Install Research Campaign
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill research-campaign -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Sidiora-Labs/centra-gideon-agent research-campaign --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/research-campaign .claude/skills/research-campaign && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "research-campaign" agent skill from https://github.com/Sidiora-Labs/centra-gideon-agent/tree/main/runtime/gideon/extensions/skills/bundled/research-campaign into .claude/skills/research-campaign/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-campaign", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Sidiora-Labs/centra-gideon-agent/tree/main/runtime/gideon/extensions/skills/bundled/research-campaignType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill research-campaign -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Sidiora-Labs/centra-gideon-agent research-campaign --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/research-campaign .agents/skills/research-campaign && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "research-campaign" agent skill from https://github.com/Sidiora-Labs/centra-gideon-agent/tree/main/runtime/gideon/extensions/skills/bundled/research-campaign into .agents/skills/research-campaign/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-campaign", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill research-campaign -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Sidiora-Labs/centra-gideon-agent research-campaign --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/research-campaign .cursor/skills/research-campaign && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "research-campaign" agent skill from https://github.com/Sidiora-Labs/centra-gideon-agent/tree/main/runtime/gideon/extensions/skills/bundled/research-campaign into .cursor/skills/research-campaign/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-campaign", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Sidiora-Labs/centra-gideon-agent.git --path runtime/gideon/extensions/skills/bundled/research-campaign--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill research-campaign -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Sidiora-Labs/centra-gideon-agent research-campaign --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/research-campaign .gemini/skills/research-campaign && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "research-campaign" agent skill from https://github.com/Sidiora-Labs/centra-gideon-agent/tree/main/runtime/gideon/extensions/skills/bundled/research-campaign into .gemini/skills/research-campaign/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-campaign", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Sidiora-Labs/centra-gideon-agent research-campaignInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill research-campaign -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/research-campaign .github/skills/research-campaign && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "research-campaign" agent skill from https://github.com/Sidiora-Labs/centra-gideon-agent/tree/main/runtime/gideon/extensions/skills/bundled/research-campaign into .github/skills/research-campaign/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-campaign", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill research-campaign -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Sidiora-Labs/centra-gideon-agent research-campaign --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/research-campaign .opencode/skills/research-campaign && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "research-campaign" agent skill from https://github.com/Sidiora-Labs/centra-gideon-agent/tree/main/runtime/gideon/extensions/skills/bundled/research-campaign into .opencode/skills/research-campaign/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-campaign", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
research-campaign- GitHub stars
- 217
- Token cost
- ~1.3k tokens
- SKILL.md length
- 678 words
- Files
- 1
- Skills in repo
- 24
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Run a multi-cycle research campaign — grill the question, decompose it into answerable sub-questions, investigate each against sources, then synthesize with confidence and gaps stated.
- Works in 4 steps: Grill the question → Decompose → Investigate → …
- Open questions that need real investigation rather than one lookup
- SKILL.md covers Phase 1 — Grill the question, Phase 2 — Decompose, Phase 3 — Investigate and Phase 4 — Synthesize, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Research Campaign is an agent skill from Sidiora-Labs/centra-gideon-agent. Run a multi-cycle research campaign — grill the question, decompose it into answerable sub-questions, investigate each against sources, then synthesize with confidence and gaps stated. Use for open questions that need real investigation rather than one lookup.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: The companion AI agent that learns, adapts and gets the work done no matter the task. The licence is Apache-2.0.
When your agent uses it
- Open questions that need real investigation rather than one lookup
Example prompts
- “/research-campaign”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit ca531ee. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Research Campaign loads about 1.3k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 678 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Sidiora-Labs/centra-gideon-agent at commit ca531ee, republished under its Apache-2.0 licence (© Sidiora-Labs). 678 words, ~1,256 tokens.
Download SKILL.mdSave it as
.claude/skills/research-campaign/SKILL.md (or your agent's skills folder).- name
- research-campaign
- description
- Run a multi-cycle research campaign — grill the question, decompose it into answerable sub-questions, investigate each against sources, then synthesize with confidence and gaps stated. Use for open questions that need real investigation rather than one lookup.
- always
- false
- triggers
- research campaign, do research on, deep dive into, investigate thoroughly, literature review, survey the landscape, decompose the question, multi cycle…
Research campaign
One search answers a lookup. An open question needs a campaign: grill, decompose, investigate, synthesize. The discipline is that each phase has an exit condition, so you stop when the question is answered rather than when you get tired of searching.
Phase 1 — Grill the question
Never start from the question as asked. Interrogate it first:
- What decision does this serve? The answer's required precision comes from the decision, not from the topic. "Which database" for a prototype and for a five-year platform bet are different questions.
- What would change your mind? Name it now. A campaign with no falsifier produces a conclusion that was decided before it started.
- What is already known? Restate the current belief explicitly, so the campaign can confirm or overturn something specific.
- What is out of scope? Write it down. Scope creep is what turns a campaign into a browsing session.
Exit condition: you can state the question in one sentence, plus the evidence that would falsify your current belief.
Phase 2 — Decompose
Break the question into sub-questions that are each independently answerable. A good sub-question has a knowable answer and a source type that would hold it. If you cannot name where the answer would live, the sub-question is still too abstract.
Mark each one: load-bearing (the conclusion changes if this changes) or supporting. Investigate load-bearing ones first, and be willing to stop early — if the first load-bearing answer settles the question, the rest is decoration.
Exit condition: a list of sub-questions, each with a source type and a load-bearing flag.
Phase 3 — Investigate
One sub-question at a time. For each:
- Prefer primary sources. A summary of a benchmark is not a benchmark.
- Record the answer, the source, and your confidence — and record contradictions as contradictions. Two sources disagreeing is a finding, not a problem to resolve by picking the more convenient one.
- Note what you looked for and did not find. An absent answer is evidence.
Run more cycles only while they change something. When a cycle adds sources but no new answers, the campaign is saturated.
Exit condition: every load-bearing sub-question answered or explicitly marked unanswerable.
Phase 4 — Synthesize
- Lead with the answer to the original question.
- Attach confidence to each claim, and derive it from the evidence you actually gathered — not from how much searching you did.
- State the gaps. An unstated gap becomes a claim you did not make.
- Revisit the Phase 1 falsifier: did you find it? If you never looked for it, the campaign is incomplete regardless of how much you found.
Show full SKILL.md (252 more words)Show less
Worked example
Question as asked: "Should we switch our queue to Kafka?"
Grilled: the decision is whether to spend a quarter on a migration. Current belief: the existing queue is the cause of our backlog incidents. Falsifier: if the incidents trace to consumer throughput rather than the broker, the migration addresses nothing. Out of scope: cost modelling, team training.
Decomposed:
| Sub-question | Source type | Load-bearing |
|---|---|---|
| What caused each of the last 6 backlog incidents? | Our own incident records | Yes |
| Does the current broker have a throughput ceiling we are near? | Our metrics + broker docs | Yes |
| What would the migration cost in engineer-weeks? | Comparable migrations, our code | No |
Investigated: the first sub-question showed 5 of 6 incidents were consumer-side (slow handlers, no backpressure); one was a broker restart. The second showed throughput at 12% of the documented ceiling.
Synthesized: "No — and the campaign stopped after two sub-questions because the first load-bearing answer settled it. 5 of 6 backlog incidents were consumer-side, and the broker runs at 12% of its ceiling; a broker swap would not have prevented any of them. The falsifier from Phase 1 was found, and it points at consumer backpressure. Confidence: high on incident attribution (primary records), medium on the ceiling figure (vendor documentation, not measured here). Gap: I did not cost the migration, because the answer no longer depends on it."
Note what the campaign did not do: it did not investigate the third sub-question, and it says so. Finishing a list is not the goal; answering the question is.
© Sidiora-Labs, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in runtime/gideon/extensions/skills/bundled/research-campaign of Sidiora-Labs/centra-gideon-agent.
Open the folder on GitHubat commit ca531ee
Compare with similar skills
Research Campaign next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Research Campaign this skillSidiora-Labs/centra-gideon-agent | 217 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Grillasgeirtj/system_prompts_leaks | 69k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Grill Menrwl/nx | 29k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Marketing Campaignaffaan-m/ECC | 277k | 1 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Grillingvinvcn/mattpocock-skills-zh-CN | 4.7k | — | ~226 | Automated safety check: Pass | MIT | |
| Campaign Analyticsalirezarezvani/claude-skills | 28k | 1 repos | ~2.1k | Automated safety check: Pass | MIT |
Similar skills
Grill Me
nrwl/nx
Grill the user relentlessly about a plan, design, decision, or set of review findings — working the decision tree in rounds until nothing is left silently assumed.
Marketing Campaign
affaan-m/ECC
End-to-end marketing campaign planning and execution. An agent skill from affaan-m/ECC.
Grilling
vinvcn/mattpocock-skills-zh-CN
围绕计划、decision 或 idea 持续追问用户。适用于用户想对自己的思路做压力测试，或使用任何 “grill” 触发措辞时。
Campaign Analytics
alirezarezvani/claude-skills
Calculates attribution, funnel and ROI figures for marketing campaigns with three Python scripts that need only the standard library.
Grill Me
feiskyer/claude-code-settings
针对方案或设计的高强度追问式面试（adversarial design review / grill session），暴露假设漏洞与缺失约束，过程中同步维护领域模型（术语表和 ADR）。手动调用 /grill-me。
More from Sidiora-Labs/centra-gideon-agent
All 24 skills in this repoArtifacts
Sidiora-Labs/centra-gideon-agent
Persist, version, and iterate on LLM-generated UI (widgets, HTML, markdown).
Best Of N
Sidiora-Labs/centra-gideon-agent
Sample several candidate answers in parallel, judge them against stated criteria, and present the winner with the runners-up kept one click away.
Document Authoring
Sidiora-Labs/centra-gideon-agent
Author a real document — a report, proposal, slide deck, spec, or paper — by settling audience, claim, and structure before drafting prose, then writing to that structure.
Editorial Document
Sidiora-Labs/centra-gideon-agent
Write long-form editorial documents as clean, semantic HTML saved as an artifact (kind=document) — reports, briefs, explainers, proposals, write-ups.
Gideon API
Sidiora-Labs/centra-gideon-agent
The operator's manual for DRIVING Gideon's API and tools — how to find an exact tool/route signature, the mandatory verify-after-mutate loop, and what NOT to hand-roll.
Infographic Syntax
Sidiora-Labs/centra-gideon-agent
Author infographics with the AntV declarative DSL — pick a template, fill a small indented data tree, and save as an artifact (kind=infographic) that renders to crisp SVG and streams as you write it.
Questions about Research Campaign
What does Research Campaign do?
Run a multi-cycle research campaign — grill the question, decompose it into answerable sub-questions, investigate each against sources, then synthesize with confidence and gaps stated. Research Campaign is an agent skill from Sidiora-Labs/centra-gideon-agent. Run a multi-cycle research campaign — grill the question, decompose it into answerable sub-questions, investigate each against sources, then synthesize with confidence and gaps stated.
When should I use Research Campaign?
Research Campaign fits situations like: open questions that need real investigation rather than one lookup.
How do I install Research Campaign in Claude Code?
Run `npx skills add Sidiora-Labs/centra-gideon-agent --skill research-campaign -a claude-code`. Or copy the skill folder (runtime/gideon/extensions/skills/bundled/research-campaign in Sidiora-Labs/centra-gideon-agent) into .claude/skills/research-campaign in your project. Claude Code loads it when a task matches its description.
How do I install Research Campaign in Codex?
Run `npx skills add Sidiora-Labs/centra-gideon-agent --skill research-campaign -a codex`. Or copy the skill folder (runtime/gideon/extensions/skills/bundled/research-campaign in Sidiora-Labs/centra-gideon-agent) into .agents/skills/research-campaign in your project. Codex loads it when a task matches its description.
Can I use Research Campaign in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Sidiora-Labs/centra-gideon-agent --skill research-campaign -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/research-campaign, .gemini/skills/research-campaign, .github/skills/research-campaign and .opencode/skills/research-campaign in your project.
What does Research Campaign need to run?
SKILL.md names no scripts, command-line tools or credentials: Research Campaign is instructions for the agent only.
Does Research Campaign access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Research Campaign safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Research Campaign use?
Research Campaign is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Research Campaign use?
About 1.3k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Research Campaign?
Skills that share tags, products or a category with Research Campaign: Grill (asgeirtj/system_prompts_leaks, 69k stars), Grill Me (nrwl/nx, 29k stars), Marketing Campaign (affaan-m/ECC, 277k stars) and Grilling (vinvcn/mattpocock-skills-zh-CN, 4.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Research Campaign?
Sidiora-Labs (a GitHub organization) maintains it in Sidiora-Labs/centra-gideon-agent, which has 217 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 8, 2026.
Source: Sidiora-Labs/centra-gideon-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.