Web Research
Juncai22/spring-ai-agent-learning
A skill your agent uses for requests related to web research; it provides a structured approach to conducting comprehensive web research
Non-interactive deep research pipeline for specialist subagents.
Install Researcher Workflow
$ npx skills add magnus919/hermes-profiles --skill researcher-workflow -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install magnus919/hermes-profiles researcher-workflow --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/magnus919/hermes-profiles.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/researcher-workflow .claude/skills/researcher-workflow && 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 "researcher-workflow" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/researcher-workflow into .claude/skills/researcher-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researcher-workflow", 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/magnus919/hermes-profiles/tree/main/skills/researcher-workflowType 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 magnus919/hermes-profiles --skill researcher-workflow -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install magnus919/hermes-profiles researcher-workflow --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/researcher-workflow .agents/skills/researcher-workflow && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "researcher-workflow" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/researcher-workflow into .agents/skills/researcher-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researcher-workflow", 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 magnus919/hermes-profiles --skill researcher-workflow -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install magnus919/hermes-profiles researcher-workflow --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/researcher-workflow .cursor/skills/researcher-workflow && 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 "researcher-workflow" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/researcher-workflow into .cursor/skills/researcher-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researcher-workflow", 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/magnus919/hermes-profiles.git --path skills/researcher-workflow--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 magnus919/hermes-profiles --skill researcher-workflow -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install magnus919/hermes-profiles researcher-workflow --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/researcher-workflow .gemini/skills/researcher-workflow && 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 "researcher-workflow" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/researcher-workflow into .gemini/skills/researcher-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researcher-workflow", 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 magnus919/hermes-profiles researcher-workflowInstalls 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 magnus919/hermes-profiles --skill researcher-workflow -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/researcher-workflow .github/skills/researcher-workflow && 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 "researcher-workflow" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/researcher-workflow into .github/skills/researcher-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researcher-workflow", 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 magnus919/hermes-profiles --skill researcher-workflow -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install magnus919/hermes-profiles researcher-workflow --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/researcher-workflow .opencode/skills/researcher-workflow && 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 "researcher-workflow" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/researcher-workflow into .opencode/skills/researcher-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "researcher-workflow", 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
researcher-workflow- GitHub stars
- 289
- Token cost
- ~1.1k tokens
- SKILL.md length
- 430 words
- Files
- 12 (incl. references)
- Skills in repo
- 31
- Repo updated
- First seen
- Licence
- MIT
At a glance
Non-interactive deep research pipeline for specialist subagents.
- The orchestrator
- SKILL.md covers Sub-Skills, Navigation, Pipeline Heuristics and Pitfalls
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Product-manager
What it does
Researcher Workflow is an agent skill from magnus919/hermes-profiles. Non-interactive deep research pipeline for specialist subagents. Use when the orchestrator, product-manager, or another profile assigns a research mission that requires systematic investigation with progressive disclosure. The researcher receives a brief, interpolates scope, executes multi-pass research via groktocrawl, evaluates gaps for recursion, and produces a layered artifact pyramid in /tmp/.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `AGENTS.md`, `README.md` and `decision-map.md`). Compatibility notes: Hermes Agent — designed for non-interactive subagent operation
It sits in Research & Science, covering Deep research and Subagents. The repository describes itself as: Curated Hermes Agent profiles for specialist swarms — opinionated, Hermes-optimized, artifact-pyramid native. The licence is MIT.
When your agent uses it
- The orchestrator
- Product-manager
- Another profile assigns a research mission that requires systematic investigation with progressive disclosure
Example prompts
- “/researcher-workflow”
Requirements
- Compatibility (from SKILL.md): Hermes Agent — designed for non-interactive subagent operation
What it can do on your machine
Read from SKILL.md and the folder at commit 867a555. 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
Links to these hosts (documentation or services it may open):
cognitect.comdocs.arc42.orgarc42.orgcs.ubc.cac4model.com
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.
Compatibility
Hermes Agent — designed for non-interactive subagent operation
From compatibility in the SKILL.md frontmatter.
Context cost
Researcher Workflow loads about 1.1k tokens when it runs, and up to ~1.6k if it reads all its reference files. Until then it costs about 105 tokens; SKILL.md has 430 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 magnus919/hermes-profiles at commit 867a555, republished under its MIT licence (© magnus919). 430 words, ~1,097 tokens.
Download SKILL.mdSave it as
.claude/skills/researcher-workflow/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.- name
- researcher-workflow
- description
- Non-interactive deep research pipeline for specialist subagents. Use when the orchestrator, product-manager, or another profile assigns a research mission that requires systematic investigation with progressive disclosure. The researcher receives a brief, interpolates scope, executes multi-pass research via groktocrawl, evaluates gaps for recursion, and produces a layered artifact pyramid in /tmp/.
- compatibility
- Hermes Agent — designed for non-interactive subagent operation
- metadata.tags
- workflow, bundle, research, subagent, pipeline, progressive-disclosure
- metadata.spec-version
- 1.0
Researcher Workflow
A 5-phase workflow for systematic deep research with progressive disclosure artifact output. Designed for the researcher specialist subagent profile when dispatched by an orchestrator.
RECEIVE MISSION → GATHER → EVALUATE GAPS → [RECURSE] → BUILD PYRAMID → DELIVERSub-Skills
| Phase | Skill | Trigger |
|---|---|---|
| Receive Mission | researcher-workflow/receive-mission | Orchestrator assigns a research brief — reformulate into explicit scope |
| Gather | researcher-workflow/research-gather | Execute research using groktocrawl suite exclusively |
| Evaluate Gaps | researcher-workflow/evaluate-gaps | Assess gathered material, decide on recursion depth |
| Build Pyramid | researcher-workflow/build-pyramid | Assemble progressive disclosure artifact files |
| Deliver | researcher-workflow/deliver-findings | Report back with absolute path references and layer descriptions |
Navigation
When this umbrella is loaded (by the researcher profile), identify which phase you're in, load the corresponding sub-skill via skill_view(), and follow its instructions. Each sub-skill documents its transition signals.
Pipeline Heuristics
- Entry: Always starts at Phase 1 (Receive Mission). The other phases cannot be entered directly.
- Recursion: Phase 3 (Evaluate Gaps) can loop back to Phase 2 (Gather) for targeted follow-up. This is the only non-linear path.
- Tool discipline: ALL web research goes through groktocrawl. The built-in web_search and web_extract tools are explicitly prohibited — they are insufficient and often broken. See references/tool-governance.md for the full fallback chain and rationale. Load with skill_view(name="researcher-workflow", file_path="references/tool-governance.md").
- Artifacts: Output is written to /tmp/researcher-workflow/
<mission-slug>/ as layered markdown files. Each layer links downward with descriptions so consuming agents can choose their depth. - State: No persistent state between phases. Each sub-skill reads the mission brief and artifact directory to determine context.
Pitfalls
Show full SKILL.md (204 more words)Show less
delegate_task timeout recovery
The Gather phase uses delegate_task to spawn subagents for parallel research. These subagents have a 600-second hard timeout. When a single monolithic research task times out, split into parallel sub-tasks (up to 3) each covering a distinct methodology, source, or angle. This succeeded for two of three parallel tasks in one real session; the third still timed out.
Second-line fallback when parallel sub-tasks also timeout: use direct groktocrawl scrape on known canonical URLs for the remaining sources. Note that groktocrawl agent and groktocrawl search may return empty results even when the server is functioning — agent sometimes returns "unable to find any relevant web pages" and search may be unconfigured. The reliable fallback is groktocrawl scrape <url> on each known canonical URL individually. Known URLs for common architecture-methodology sources:
- https://cognitect.com/blog/2011/11/15/documenting-architecture-decisions — Michael Nygard's original ADR post
- https://docs.arc42.org/ — arc42 template docs with all 12 sections listed
- https://arc42.org/canvas — arc42 Canvas (zip-version of full template)
- https://www.cs.ubc.ca/~gregor/teaching/papers/4+1view-architecture.pdf — Kruchten's original 1995 paper
- https://c4model.com — Simon Brown's C4 Model
Key recovery principle: When the subagent times out, the research question is still valid. Recover by reducing each subagent's scope (fewer sources per agent) and filling the gap with direct groktocrawl scrapes on specific URLs rather than re-delegating the same bundle.
© magnus919, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 11 other files (references) in skills/researcher-workflow of magnus919/hermes-profiles.
- SKILL.md
- AGENTS.md
- README.md
- decision-map.md
- manifest.yaml
- references/generated-from.md
- references/tool-governance.md
- skills/build-pyramid.md
- skills/deliver-findings.md
- skills/evaluate-gaps.md
- skills/receive-mission.md
- skills/research-gather.md
Open the folder on GitHubat commit 867a555
Compare with similar skills
Researcher Workflow 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 |
|---|---|---|---|---|---|---|
| Researcher Workflow this skillmagnus919/hermes-profiles | 289 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Web ResearchJuncai22/spring-ai-agent-learning | 124 | 2 repos | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Deep Research Teammalob/nix-config | 463 | — | ~5.8k | Automated safety check: Pass | MIT | |
| Deep Researchasgeirtj/system_prompts_leaks | 69k | — | ~3.3k | Automated safety check: Pass | CC0-1.0 | |
| Deep Research312362115/claude | 107 | — | ~6.6k | Automated safety check: Pass | MIT | |
| ULW Deep Researchcode-yeongyu/oh-my-openagent | 70k | — | ~14k | Automated safety check: Pass | Custom licence |
Similar skills
Deep Research Team
malob/nix-config
Coordinates a team of researcher agents across several rounds, with a lead who triages findings, assigns follow-ups and cross-checks key claims.
Deep Research
asgeirtj/system_prompts_leaks
A skill your agent uses when the user's prompt requires (1) researching a topic across multiple sources, comparing options or alternatives, analyzing trends or history, understanding markets or…
Deep Research
312362115/claude
深度调研技能：对任意命题进行系统性调研并输出专业研究报告. An agent skill from 312362115/claude.
ULW Deep Research
code-yeongyu/oh-my-openagent
Runs an exhaustive, team-based research session that stands up cooperating agents, debates findings and delivers a report where every claim has a citation or proof.
Deep Research
XiaomiMiMo/MiMo-Code
Runs a multi-source investigation with parallel sub-agents and built-in web tools, then writes one cited report. Meant for open-ended topics, not quick lookups.
More from magnus919/hermes-profiles
All 31 skills in this repoData Scientist
magnus919/hermes-profiles
PhD-level expertise in data science, statistics, and machine learning.
Brand Designer
magnus919/hermes-profiles
Create comprehensive brand identity documentation for any brand.
Sdd Authoring
magnus919/hermes-profiles
Specification authoring for AI-native SDD — writes formal specifications in structured formats (Gherkin, user stories, acceptance criteria), enforces spec quality gates, and produces…
Sdd Verification
magnus919/hermes-profiles
SDD acceptance criteria verification — maps specification acceptance criteria to tests, validates implementation output against spec requirements, and produces artifact-pyramid-compliant…
Sdd Work Decomposition
magnus919/hermes-profiles
SDD work decomposition — translates formal specifications into dependency-aware task plans with per-task acceptance criteria.
Artifact Pyramids
magnus919/hermes-profiles
Progressive disclosure for what AI agents produce. An agent skill from magnus919/hermes-profiles.
Related
Categories
Questions about Researcher Workflow
What does Researcher Workflow do?
Non-interactive deep research pipeline for specialist subagents. Researcher Workflow is an agent skill from magnus919/hermes-profiles. Non-interactive deep research pipeline for specialist subagents.
When should I use Researcher Workflow?
Researcher Workflow fits situations like: the orchestrator; product-manager; another profile assigns a research mission that requires systematic investigation with progressive disclosure.
How do I install Researcher Workflow in Claude Code?
Run `npx skills add magnus919/hermes-profiles --skill researcher-workflow -a claude-code`. Or copy the skill folder (skills/researcher-workflow in magnus919/hermes-profiles) into .claude/skills/researcher-workflow in your project. Claude Code loads it when a task matches its description.
How do I install Researcher Workflow in Codex?
Run `npx skills add magnus919/hermes-profiles --skill researcher-workflow -a codex`. Or copy the skill folder (skills/researcher-workflow in magnus919/hermes-profiles) into .agents/skills/researcher-workflow in your project. Codex loads it when a task matches its description.
Can I use Researcher Workflow 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 magnus919/hermes-profiles --skill researcher-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/researcher-workflow, .gemini/skills/researcher-workflow, .github/skills/researcher-workflow and .opencode/skills/researcher-workflow in your project.
What does Researcher Workflow need to run?
SKILL.md names no scripts, command-line tools or credentials: Researcher Workflow is instructions for the agent only. Compatibility (from SKILL.md): Hermes Agent — designed for non-interactive subagent operation.
Does Researcher Workflow access the network?
SKILL.md names 5 domains. As links in the text: cognitect.com, docs.arc42.org, arc42.org, cs.ubc.ca and c4model.com. This is read from the text; nothing was executed.
Is Researcher Workflow 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 Researcher Workflow use?
Researcher Workflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Researcher Workflow use?
About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 478 tokens, read only when the agent opens those files.
What are the alternatives to Researcher Workflow?
Skills that share tags, products or a category with Researcher Workflow: Web Research (Juncai22/spring-ai-agent-learning, 124 stars), Deep Research Team (malob/nix-config, 463 stars), Deep Research (asgeirtj/system_prompts_leaks, 69k stars) and Deep Research (312362115/claude, 107 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Researcher Workflow?
magnus919 (a GitHub user) maintains it in magnus919/hermes-profiles, which has 289 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on June 27, 2026.
Source: magnus919/hermes-profiles on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.