Root Cause Investigation
garrytan/gstack
Debugs in four phases (investigate, analyze, hypothesize, implement) under one rule: no fix is made until the root cause is found.
Verify the reported path, cause, and historical intent before choosing a fix.
Apache-2.0Auto-check passed
Install Resolve Investigate
$ npx skills add omnigent-ai/omnigent --skill resolve-investigate -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install omnigent-ai/omnigent resolve-investigate --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/omnigent-ai/omnigent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/dev/resolve-agent/skills/resolve-investigate .claude/skills/resolve-investigate && 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 "resolve-investigate" agent skill from https://github.com/omnigent-ai/omnigent/tree/main/dev/resolve-agent/skills/resolve-investigate into .claude/skills/resolve-investigate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-investigate", 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/omnigent-ai/omnigent/tree/main/dev/resolve-agent/skills/resolve-investigateType 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 omnigent-ai/omnigent --skill resolve-investigate -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install omnigent-ai/omnigent resolve-investigate --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/omnigent-ai/omnigent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/dev/resolve-agent/skills/resolve-investigate .agents/skills/resolve-investigate && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "resolve-investigate" agent skill from https://github.com/omnigent-ai/omnigent/tree/main/dev/resolve-agent/skills/resolve-investigate into .agents/skills/resolve-investigate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-investigate", 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 omnigent-ai/omnigent --skill resolve-investigate -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install omnigent-ai/omnigent resolve-investigate --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/omnigent-ai/omnigent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/dev/resolve-agent/skills/resolve-investigate .cursor/skills/resolve-investigate && 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 "resolve-investigate" agent skill from https://github.com/omnigent-ai/omnigent/tree/main/dev/resolve-agent/skills/resolve-investigate into .cursor/skills/resolve-investigate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-investigate", 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/omnigent-ai/omnigent.git --path dev/resolve-agent/skills/resolve-investigate--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 omnigent-ai/omnigent --skill resolve-investigate -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install omnigent-ai/omnigent resolve-investigate --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/omnigent-ai/omnigent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/dev/resolve-agent/skills/resolve-investigate .gemini/skills/resolve-investigate && 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 "resolve-investigate" agent skill from https://github.com/omnigent-ai/omnigent/tree/main/dev/resolve-agent/skills/resolve-investigate into .gemini/skills/resolve-investigate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-investigate", 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 omnigent-ai/omnigent resolve-investigateInstalls 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 omnigent-ai/omnigent --skill resolve-investigate -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/omnigent-ai/omnigent.git skills-src && mkdir -p .github/skills && cp -r skills-src/dev/resolve-agent/skills/resolve-investigate .github/skills/resolve-investigate && 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 "resolve-investigate" agent skill from https://github.com/omnigent-ai/omnigent/tree/main/dev/resolve-agent/skills/resolve-investigate into .github/skills/resolve-investigate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-investigate", 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 omnigent-ai/omnigent --skill resolve-investigate -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install omnigent-ai/omnigent resolve-investigate --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/omnigent-ai/omnigent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/dev/resolve-agent/skills/resolve-investigate .opencode/skills/resolve-investigate && 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 "resolve-investigate" agent skill from https://github.com/omnigent-ai/omnigent/tree/main/dev/resolve-agent/skills/resolve-investigate into .opencode/skills/resolve-investigate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-investigate", 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
resolve-investigate- GitHub stars
- 11k
- Token cost
- ~1.2k tokens
- SKILL.md length
- 637 words
- Files
- 1
- Skills in repo
- 19
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Verify the reported path, cause, and historical intent before choosing a fix.
- Works in 4 steps: Reconstruct the report. Read the report… → Distinguish symptom from cause. Trace… → Find the design intent. Read nearby… → …
- Calls git
What it does
Resolve Investigate is an agent skill from omnigent-ai/omnigent. Verify the reported path, cause, and historical intent before choosing a fix.
Its SKILL.md is about 1.2k 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: Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies… The licence is Apache-2.0.
Example prompts
- “/resolve-investigate”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Reconstruct the report. Read the report and relevant discussion, including
- Distinguish symptom from cause. Trace the actual path from trigger to
- Find the design intent. Read nearby tests and documentation, targeted
- Choose and explain. Preserve intended behavior when correcting the
What it can do on your machine
Read from SKILL.md and the folder at commit c6a81cd. 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
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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
Resolve Investigate loads about 1.2k tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 637 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 omnigent-ai/omnigent at commit c6a81cd, republished under its Apache-2.0 licence (© omnigent-ai). 637 words, ~1,177 tokens.
Download SKILL.mdSave it as
.claude/skills/resolve-investigate/SKILL.md (or your agent's skills folder).- name
- resolve-investigate
- description
- Verify the reported path, cause, and historical intent before choosing a fix.
Establish the cause and intended behavior
Use this in every mode before choosing assertions or changing code. Keep the
investigation proportional to the reported problem; reuse evidence that still
matches the checkout. Record concise findings in the existing root_cause,
fix_summary, and test_audit fields, not a separate report.
- Reconstruct the report. Read the report and relevant discussion, including linked evidence. Separate reported facts, observations, and hypotheses. Pin the entry point, build, harness, authentication mode/profile, configuration, and starting state. Mark unknowns; do not silently swap an OAuth user login for a service principal or PAT because they produce similar errors.
- Distinguish symptom from cause. Trace the actual path from trigger to failure. Treat the reporter's diagnosis, Repro leads, and proposed fixes as hypotheses. Check the strongest competing explanation suggested by code, logs, or history with an observation or focused test that distinguishes it. Explain why the selected cause accounts for the reported configuration and symptom. If no credible alternative emerges, say so briefly; do not invent one or implement a plausible generic fix without evidence. Exercise the reported configuration through the implementation being diagnosed. Controlled external services, clocks, and credentials are useful substitutes; replacing the suspected component with canned results assumes the cause instead of testing it. For example, a fake token factory proves how its caller handles those tokens, not how the configured credential provider behaves. Record which parts actually ran and which were substituted. A fail-before/pass-after test of that substitute does not confirm the incident.
- Find the design intent. Read nearby tests and documentation, targeted
git log -S/git blame, and relevant commit/PR discussion. Cite the source and revision; distinguish documented rationale from inference and note unavailable history. A fallback, fail-open path, default, or restriction may be deliberate. Do not reverse it just to satisfy a repro assertion. Check whether later decisions supersede the original rationale. - Choose and explain. Preserve intended behavior when correcting the defect. For a necessary policy change, explain the old behavior, the proposed behavior, affected users/configurations, alternatives, and supporting evidence. Existing tests are evidence of intent, not unquestionable policy. Repair unsupported repro expectations with the original evidence preserved; label tests of a proposed policy as such, not proof the old policy was a bug.
Show full SKILL.md (266 more words)Show less
PR review is the human decision boundary
Continue with the best-supported proposal within the authorized task. Ambiguous
design intent alone is not needs_more_info and does not require an interactive
question. Implement and validate the proposal; state assumptions and unresolved
tradeoffs in the PR and fix_summary so a maintainer can decide on concrete work.
If a material choice remains unresolved, use partially_fixed and list that
choice in remaining_work; do not claim fixed or approve the PR. In direct
author mode, open a draft with --draft and follow resolve-publish's draft
exception. For an existing PR, leave the supported recommendation on that PR,
continue independent work, and respect branch ownership and trusted human
reviews; do not create a replacement just to resolve a policy disagreement.
For workflow-owned publication, prepare the proposal body and incomplete handoff
under the supplied publisher contract; never bypass it or invent a draft flag.
For skip_push, leave the proposal in the local commit and handoff.
Apply the same distinction to an unverified cause. If a proposed fix is supported
only by a substitute configuration or canned failure, describe it as a hypothesis,
use partially_fixed, and name the missing discriminator in remaining_work.
When a reliable reproduction cannot be established, use the existing
needs_more_info outcome. Passing tests that assume the cause do not justify
fixed.
Concrete blockers still apply: missing required inputs or credentials, unsafe evidence, an unrecoverable verification environment, conflicting authoritative requests, or work outside authorization. Name the blocker and complete independent authorized work. Never weaken security controls, guess missing facts, silently expand scope, or claim an unrun check passed to get a proposal through review.
© omnigent-ai, 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 dev/resolve-agent/skills/resolve-investigate of omnigent-ai/omnigent.
Open the folder on GitHubat commit c6a81cd
Compare with similar skills
Resolve Investigate 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 |
|---|---|---|---|---|---|---|
| Resolve Investigate this skillomnigent-ai/omnigent | 11k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Root Cause Investigationgarrytan/gstack | 136k | — | ~12k | Automated safety check: Notes | MIT | |
| Reportmicrosoft/data-formulator | 18k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Reportalirezarezvani/claude-skills | 28k | 1 repos | ~727 | Automated safety check: Pass | MIT | |
| Root Cause Debugginggarrytan/gstack | 136k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Investigate CIClickHouse/ClickHouse | 50k | — | ~11k | Automated safety check: Notes | Apache-2.0 |
Similar skills
- Official
Report
microsoft/data-formulator
Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded…
Report
alirezarezvani/claude-skills
Generate test report. An agent skill from alirezarezvani/claude-skills.
Root Cause Debugging
garrytan/gstack
Investigates bugs, errors and stack traces in phases and requires a root-cause hypothesis to be confirmed before any fix is written.
Investigate CI
ClickHouse/ClickHouse
Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL.
Bugcrowd Reporting
sickn33/agentic-awesome-skills
Bugcrowd-specific reporting tactics complementing report-writing
More from omnigent-ai/omnigent
All 19 skills in this repoOmnigent Docker Compose Deploy
omnigent-ai/omnigent
Brings up the Omnigent server and Postgres as a Docker compose stack on any Docker host, and covers the Dockerfile's runtime and host build targets for extending it to a new platform.
Omnigent Framework Detection
omnigent-ai/omnigent
Scans Python agent code for framework imports and recommends the matching Omnigent executor type, or says when the framework is not natively supported yet.
Omnigent Load Test Runner
omnigent-ai/omnigent
Runs the Omnigent load test with real hosts and multi-turn sessions against a mocked LLM, then explains the latency results from summary.md.
Verify Omnigent End-to-End
omnigent-ai/omnigent
Spins up an isolated Omnigent server, runner and mock model to prove a user-facing behavior or bug fix with recorded evidence instead of reasoning from code.
Antigravity SDK End-to-End Testing
omnigent-ai/omnigent
Spins up a local Omnigent server and exercises the Antigravity (Gemini) SDK harness end to end: building agents, running real turns, smoke tests and bug-bashing.
Omnigent Agent Builder
omnigent-ai/omnigent
Gives patterns for generating a minimal, valid Omnigent agent directory: the config.yaml fields, the right executor type, and the files each agent needs.
Questions about Resolve Investigate
What does Resolve Investigate do?
Verify the reported path, cause, and historical intent before choosing a fix. Resolve Investigate is an agent skill from omnigent-ai/omnigent. Verify the reported path, cause, and historical intent before choosing a fix.
How do I install Resolve Investigate in Claude Code?
Run `npx skills add omnigent-ai/omnigent --skill resolve-investigate -a claude-code`. Or copy the skill folder (dev/resolve-agent/skills/resolve-investigate in omnigent-ai/omnigent) into .claude/skills/resolve-investigate in your project. Claude Code loads it when a task matches its description.
How do I install Resolve Investigate in Codex?
Run `npx skills add omnigent-ai/omnigent --skill resolve-investigate -a codex`. Or copy the skill folder (dev/resolve-agent/skills/resolve-investigate in omnigent-ai/omnigent) into .agents/skills/resolve-investigate in your project. Codex loads it when a task matches its description.
Can I use Resolve Investigate 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 omnigent-ai/omnigent --skill resolve-investigate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/resolve-investigate, .gemini/skills/resolve-investigate, .github/skills/resolve-investigate and .opencode/skills/resolve-investigate in your project.
What does Resolve Investigate need to run?
Going by SKILL.md and its folder, Resolve Investigate needs the command-line tools its instructions call (git).
Does Resolve Investigate access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Resolve Investigate 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 Resolve Investigate use?
Resolve Investigate 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 Resolve Investigate use?
About 1.2k tokens (SKILL.md is roughly 4.7k 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 Resolve Investigate?
Skills that share tags, products or a category with Resolve Investigate: Root Cause Investigation (garrytan/gstack, 136k stars), Report (microsoft/data-formulator, 18k stars), Report (alirezarezvani/claude-skills, 28k stars) and Root Cause Debugging (garrytan/gstack, 136k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Resolve Investigate?
omnigent-ai (a GitHub organization) maintains it in omnigent-ai/omnigent, which has 10,711 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 10, 2026.
Source: omnigent-ai/omnigent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.