Agent skill

Codexqa Rootcause Analyzer

by openqa-cn in openqa-cn/codexqa

Diagnoses exception root causes from stack traces, logs, call-chain dumps, and debug output using the CodexQA CLI for structured repo analysis.

Apache-2.0Auto-check passedDevelopment

Install Codexqa Rootcause Analyzer

skills CLI
$ npx skills add openqa-cn/codexqa --skill codexqa-rootcause-analyzer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install openqa-cn/codexqa codexqa-rootcause-analyzer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/openqa-cn/codexqa.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/codexqa-rootcause-analyzer .claude/skills/codexqa-rootcause-analyzer && rm -rf skills-src

Use ~/.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/

Facts

Skill name
codexqa-rootcause-analyzer
GitHub stars
152
Token cost
~2.6k tokens
SKILL.md length
1,054 words
Files
40 (incl. scripts, references, assets)
Skills in repo
14
Repo updated
First seen
Licence
Apache-2.0

At a glance

Diagnoses exception root causes from stack traces, logs, call-chain dumps, and debug output using the CodexQA CLI for structured repo analysis.

  • Works in 8 steps: Collect exception evidence and the code… → One process: run (or submit… → run writes brief.json, facts.json, and a… → …
  • The user mentions codexqa-rootcause-analyzer
  • SKILL.md covers Boundaries, Split of work, Happy path and Report rules (mandatory), plus 4 more sections
  • Runs JavaScript scripts from its folder; calls node, git and npm; reaches registry.npmjs.org

What it does

Codexqa Rootcause Analyzer is an agent skill from openqa-cn/codexqa. Diagnoses exception root causes from stack traces, logs, call-chain dumps, and debug output using the CodexQA CLI for structured repo analysis. Use when the user mentions codexqa-rootcause-analyzer, exception RCA, crash analysis, AI code diagnosis, stack diagnosis, 异常根因, 堆栈诊断, 崩溃分析, 异常诊断, or asks to turn an exception into a root-cause report. Not structure/impact analysis (that is codexqa-code-analyzer), not SAST + Agent LLM Detection code-risk scan reports (that is codexqa-defect-analyzer), and not CodexQA…

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 42 other files, including scripts, reference files and assets (for example `.meta.json`, `HOW_IT_WORKS.md` and `HOW_IT_WORKS.zh-CN.md`). Compatibility notes: Requires Node.js 22+ and git on PATH when cloning remotes. Talks to the @openqa-cn/codexqa CLI via npm (codexqa binary only); do not copy engine or skill…

It sits in Development, covering Root cause analysis, Static analysis and SAST and Code review. It works with Git and TypeScript. The repository describes itself as: codexqa: 11 local-first Agent Skills for Cursor, Claude Code, Codex & OpenClaw — change impact analysis, AI code review, defect scan, testcase generation, browser replay & RCA. The licence is Apache-2.0.

When your agent uses it

  • The user mentions codexqa-rootcause-analyzer
  • AI code diagnosis
  • Stack diagnosis
  • Asks to turn an exception into a root-cause report

Example prompts

  • “Use the codexqa-rootcause-analyzer skill to diagnose exception root causes from stack traces, logs, call-chain dumps, and debug output using the…”
  • “/codexqa-rootcause-analyzer”

Requirements

  • Node.js
  • Compatibility (from SKILL.md): Requires Node.js 22+ and git on PATH when cloning remotes. Talks to the `@openqa-cn/codexqa` CLI via npm (`codexqa` binary only); do not copy engine or skill source. Task data lives under this skill's `data/` directory.

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Collect exception evidence and the code location. Write an exception file if needed.
  2. One process: run (or submit --with-analyze) with --exception/--exception-file plus --git/--branch, --file, or --dir. Bare flags without…
  3. run writes brief.json, facts.json, and a heading-only report.draft.md. It does not author or persist report.md. parse-exception is already…
  4. If stdout has facts / factsPath, fill report.draft.md from facts.json in one pass (Report rules below). If codexqa.ready=true and brief…
  5. write-report --from-draft. If stdout has storyGaps, edit the draft once from that output and retry. Do not retry to shrink length.
  6. Show one English paragraph from stdout chat.en (the first line of Executive summary) plus paths to report.md / report.en.md / report.html…
  7. Observe stdout/meta timings after every CLI step. If a step is abnormally slow, diagnose that delay and fix it before continuing RCA.
  8. Skill defects (mandatory): if a step is wrong, truncates, skips a rule, or is flaky, first encode the rule in TypeScript (scripts/*.ts +…

What it can do on your machine

Read from SKILL.md and the folder at commit 7839542. 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

    Ships 1 file in scripts/ (JavaScript, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • node
    • git
    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • registry.npmjs.org

    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

    Requires Node.js 22+ and git on PATH when cloning remotes. Talks to the `@openqa-cn/codexqa` CLI via npm (`codexqa` binary only); do not copy engine or skill source. Task data lives under this skill's `data/` directory.

    From compatibility in the SKILL.md frontmatter.

Context cost

Codexqa Rootcause Analyzer loads about 2.6k tokens when it runs, and up to ~6.6k if it reads all its reference files. Until then it costs about 160 tokens; SKILL.md has 1,054 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~160
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.6k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from openqa-cn/codexqa at commit 7839542, republished under its Apache-2.0 licence (© openqa-cn). 1,054 words, ~2,599 tokens.

Download SKILL.mdSave it as .claude/skills/codexqa-rootcause-analyzer/SKILL.md (or your agent's skills folder). This skill also uses 39 other files; get the full folder from GitHub.
name
codexqa-rootcause-analyzer
description
Diagnoses exception root causes from stack traces, logs, call-chain dumps, and debug output using the CodexQA CLI for structured repo analysis. Use when the user mentions codexqa-rootcause-analyzer, exception RCA, crash analysis, AI code diagnosis, stack diagnosis, 异常根因, 堆栈诊断, 崩溃分析, 异常诊断, or asks to turn an exception into a root-cause report. Not structure/impact analysis (that is codexqa-code-analyzer), not SAST + Agent LLM Detection code-risk scan reports (that is codexqa-defect-analyzer), and not CodexQA evidence-pack HTML review (that is codexqa-code-reviewer). Former skill name: root-cause-diagnosis.
compatibility
Requires Node.js 22+ and git on PATH when cloning remotes. Talks to the `@openqa-cn/codexqa` CLI via npm (`codexqa` binary only); do not copy engine or skill source. Task data lives under this skill's `data/` directory.
license
Apache-2.0
metadata.author
open-source
metadata.version
0.0.1
metadata.open-standard
agentskills

Root Cause Diagnosis

Turns exception evidence into an English root-cause report. Structured understanding of the business codebase comes from the CodexQA CLI; this skill diagnoses on top of that analysis.

CLI: node {baseDir}/scripts/diagnose.ts ($SKILL_SCRIPT). Task data: {baseDir}/data/{taskId}/.

README.md / README.zh-CN.md / HOW_IT_WORKS.md / KNOWN_LIMITATIONS.md (and their .zh-CN twins) are human-facing. Do not load them at runtime.

Boundaries

NeedSkill
Symbol-graph change impact, callers, test gaps, entry riskcodexqa-code-analyzer
Exception RCA from stacks/logs on top of CLI analysisthis skill
SAST + Agent LLM Detection → report_scan.*codexqa-defect-analyzer
CodexQA evidence-pack + Agent LLM judgment → bilingual REVIEW-REPORT.htmlcodexqa-code-reviewer

Split of work

LayerOwns
TypeScript (draft-report)First-level English headings, extracted facts (facts.json), mechanical storyGaps
ModelReport narrative inside those headings, using only cited facts
TypeScript (write-report)Reject missing headings and story gaps. Do not reject on section length

Do not put exception-class fix wording in scripts/draft_report.ts. Mechanical defects stay in TypeScript; causal truth in this business domain stays with the model.

Happy path

run is seconds. Wall-clock is LLM round-trips. Do not load references/, other skills, --help, or scripts/*.ts before run. Do not invent Class#search:1 for → Class tails. Do not count 字 or trim to a hint.

  1. Collect exception evidence and the code location. Write an exception file if needed.
  2. One process: run (or submit --with-analyze) with --exception/--exception-file plus --git/--branch, --file, or --dir. Bare flags without run still run. Uploaded files and non-git folders are copied into data/<taskId>/repo and git-inited there only. Do not invent a git remote. Do not git init in the user's original path.
  3. run writes brief.json, facts.json, and a heading-only report.draft.md. It does not author or persist report.md. parse-exception is already done; skip unless parsed.json is missing.
  4. If stdout has facts / factsPath, fill report.draft.md from facts.json in one pass (Report rules below). If codexqa.ready=true and brief exists but facts are missing, draft-report --task-id then fill. Do not read analysis.json when brief/facts exist. Do not open ~/.codexqa/.
  5. write-report --from-draft. If stdout has storyGaps, edit the draft once from that output and retry. Do not retry to shrink length.
  6. Show one English paragraph from stdout chat.en (the first line of Executive summary) plus paths to report.md / report.en.md / report.html. If chat.en is empty, use that summary line. Do not paste the full document.
  7. Observe stdout/meta timings after every CLI step. If a step is abnormally slow, diagnose that delay and fix it before continuing RCA.
  8. Skill defects (mandatory): if a step is wrong, truncates, skips a rule, or is flaky, first encode the rule in TypeScript (scripts/*.ts + tests/*.test.ts) so later runs cannot regress. Keep an Agent-only note in this file only when the check cannot be decided without an LLM (for example: whether a causal sentence is true in this business domain). After the TS fix, re-run or draft-report before filling the report.

Abbreviated class-only → Foo frames expand to hinted types ending with Foo before staying weak.

Show full SKILL.md (577 more words)Show less

Report rules (mandatory)

English Markdown only. Same eight ## headings as references/report-template.md. No extra top-level headings. Do not write a Chinese report.

The Target column is a prompt hint for the model, not a write-report reject. Keep the report complete even if a section exceeds the hint.

SectionTarget (hint)Must contain
Executive summary100what failed, in-repo root, literal Confidence: high|medium|low
Symptom and exception facts100type, message gist, primary Class#method:line
Mapped call path300entry → each hop → extracted branch then-call → throw; mark weak frames
Root cause300earliest wrong contract in this repo, why that path ran; cite Class#method. Include race/contend only when facts.raceEvidence is true
Trigger100throw site; not the root cause
Contributing factors100factors grounded in facts (swallowKey, evidenceGaps); do not invent swallow / race / weak-frame claims
Suggested fix and verification100one fix + one verify; do not apply code
Confidence and gaps100use facts.confidence (high/medium); never write Confidence: high when facts say medium; one gap

Mapped call path and Root cause must tell the story: entry, hops, branch, and throw. Mention race/contend only when facts.raceEvidence is true. Cite catch-all swallow only when facts.swallowKey is set. Mark hypothesis when facts.lineDrift is non-empty; do not invent line-drift or weak-frame claims without facts. A slogan or a bare A→B→C is invalid. Do not paste facts.json as the report.

When facts.lineDrift is non-empty, Root cause must mark hypothesis. Trigger must cite the throw class and say it is not the root. Root must cite the throw class and (if extracted) the branch else-call.

write-report storyGaps (edit the draft once if rejected):

GapSectionRequired text
missing-confidenceExecutive summaryConfidence:
confidence-overstatedExecutive summarydo not write Confidence: high when facts.confidence is medium
mapped-missing-branch-thenMapped call pathfacts.branch.thenCall
mapped-missing-throwMapped call paththrow class from facts.throwKey
mapped-invented-weakMapped call pathdrop "weak frame" wording when facts.weakCount is 0
root-missing-branch-elseRoot causefacts.branch.elseCall
root-missing-throwRoot causethrow class
root-missing-raceRoot causeraced/race/contend — only when facts.raceEvidence=true
root-invented-raceRoot causeremove race/contend when facts.raceEvidence is false
root-missing-hypothesis-on-driftRoot causehypothesis when facts.lineDrift is non-empty
root-invented-line-driftRoot causedrop line-drift claims when facts.lineDrift is empty
contributing-missing-swallowContributing / Rootcite facts.swallowKey (or swallow wording) when set
contributing-invented-swallowContributing / Rootdrop swallow/catch-all claims when facts.swallowKey is null
trigger-missing-throwTriggerthrow class
trigger-missing-not-rootTriggernot the root (or not root)

Citations: one Class#method (or file:line) per causal claim. No SQL dumps, no numbered evidence lists, no whole-class pastes.

Chat: one English paragraph + paths to report.md / report.en.md. Do not paste the full document.

Entry

bash
node "$SKILL_SCRIPT" run --exception-file "$PATH" --dir "$LOCAL_DIR"
# uploaded business file (non-git OK; stack sibling sources in the same folder are bundled):
#   node "$SKILL_SCRIPT" run --exception-file "$PATH" --file /abs/path/OrderService.java
# remote:
#   node "$SKILL_SCRIPT" run --exception "$TEXT" --git "$GIT_URL" --branch "$BRANCH"
# already-open IDE / cwd:
#   node "$SKILL_SCRIPT" run --exception "$TEXT"
# stepwise (debug only):
node "$SKILL_SCRIPT" submit --exception-file "$PATH" --dir "$LOCAL_DIR"
node "$SKILL_SCRIPT" ensure-codexqa --task-id $TASK_ID --with-analyze
# fill data/<id>/report.draft.md from facts.json, then:
node "$SKILL_SCRIPT" write-report --task-id $TASK_ID --from-draft

Load order

Load each reference at most once, and never before run. Links from this file are one level deep.

FileWhen to load
references/workflow.mdStepwise debug, or facts missing after run
references/codexqa.mdBefore ensure-codexqa / analyze-frames when run did not index
references/exception-parse.mdBefore interpreting parsed.json when facts/brief are missing
references/report-template.mdBefore filling report.draft.md, only if Report rules above are not already in context

RCA rules

  • Distinguish trigger (the throw), root cause (earliest incorrect state/contract in this repo), and contributors.
  • Do not treat the last stack frame as the root cause.
  • Every causal claim cites Class#method or file:line. Do not add extra evidence lists.
  • Missing graph → hypothesis + how to verify. Never invent call edges.
  • After a real ensure-codexqa attempt with ready=false, grep is allowed and evidence is weak.

CodexQA (CLI only)

Install if missing: npm install -g @openqa-cn/codexqa --registry https://registry.npmjs.org/. Talk to the codexqa binary only (index / query / stats / repos). Do not copy engine or skill source into this skill. Details: references/codexqa.md.

© openqa-cn, 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

SKILL.md and 39 other files (scripts, references, assets) in skills/codexqa-rootcause-analyzer of openqa-cn/codexqa.

  • SKILL.md
  • .gitignore
  • .meta.json
  • HOW_IT_WORKS.md
  • HOW_IT_WORKS.zh-CN.md
  • KNOWN_LIMITATIONS.md
  • KNOWN_LIMITATIONS.zh-CN.md
  • README.md
  • README.zh-CN.md
  • assets/report-chrome.css
  • assets/report-chrome.js
  • data/.gitkeep
  • package.json
  • references/codexqa.md
  • references/exception-parse.md
  • references/report-template.md
  • references/workflow.md
  • scripts
  • … and 22 more

Open the folder on GitHubat commit 7839542

Compare with similar skills

Codexqa Rootcause Analyzer 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.

Codexqa Rootcause Analyzer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codexqa Rootcause Analyzer this skillopenqa-cn/codexqa152—~2.6kAutomated safety check: PassApache-2.0
Targeted Emergency Bug FixVeryGoodOpenSource/vgv-wingspan108—~1.9kAutomated safety check: PassMIT
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Debugging and Error Recoveryaddyosmani/agent-skills102k1 repos~2.6kAutomated safety check: PassMIT
Git History Bug Auditben-manes/caffeine18k—~3.3kAutomated safety check: PassApache-2.0
Trailmark Graph Evolutiontrailofbits/skills7.4k—~3.4kAutomated safety check: PassCC-BY-SA-4.0

Similar skills

  • Targeted Emergency Bug Fix

    VeryGoodOpenSource/vgv-wingspan

    Applies a minimal fix to an emergency bug through triage, root-cause location, a hotfix branch and a blast-radius check, with tests and review still required.

    108 GitHub stars~1.9k tokensUpdated 7 days ago
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Debugging and Error Recovery

    addyosmani/agent-skills

    Applies a stop-the-line rule and a step-by-step triage when tests fail, builds break or something stops working, aiming at the root cause instead of guesses.

    102k GitHub starsUsed in 1 repo~2.6k tokens
    DevelopmentAuto-check passed
  • Git History Bug Audit

    ben-manes/caffeine

    Audits a module by walking its git history commit by commit, tracking unresolved issues forward, and reporting the ones that survive to HEAD as findings.

    18k GitHub stars~3.3k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Trailmark Graph Evolution

    trailofbits/skills

    Official

    Compares Trailmark code graphs at two snapshots, such as commits, tags or directories, to surface attack paths, blast radius and taint changes that text diffs miss.

    7.4k GitHub stars~3.4k tokensUpdated 5 days ago
    SecurityAuto-check passed
  • Maps the hunkdiff/extension API for building Hunk terminal diff viewer extensions: panes, file views, commands, dialogs, themes, VCS backends and lifecycle events.

    9.5k GitHub stars~5.8k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from openqa-cn/codexqa

All 14 skills in this repo
  • Codexqa Code Wiki

    openqa-cn/codexqa

    Builds a local architecture wiki for a repository from the CodexQA symbol graph (no model needed): modules, who calls whom and how often, reading paths, and one self-contained HTML page.

    152 GitHub stars~1.3k tokensUpdated 4 days ago
    Auto-check passed
  • Constructs test data against real backends and writes it back into test cases as executable preconditions.

    152 GitHub stars~4.8k tokensUpdated 4 days ago
    Auto-check passed
  • Codexqa Skill Router

    openqa-cn/codexqa

    Auto-routes a user request to the matching codexqa skill, then ensures that skill is on disk and follows its SKILL.md.

    152 GitHub stars~2k tokensUpdated 4 days ago
    Auto-check passed
  • Generates test plans and test cases from local requirements for APP, Web, and server.

    152 GitHub stars~3.6k tokensUpdated 4 days ago
    Auto-check passed
  • Catalog

    openqa-cn/codexqa

    Constructs catalog products (standard or limited), catalog orders, and account-credit enrollment, including product-then-credit scenes.

    152 GitHub stars~514 tokensUpdated 4 days ago
    Auto-check passed
  • Codexqa Change Analysis

    openqa-cn/codexqa

    Change-impact analysis for one diff: use CodexQA diff indexing (index --diff-base tags nodes and files add / change / delete, then change-groups / symbol-diff / file-base) to write one HTML report…

    152 GitHub stars~3.1k tokensUpdated 4 days ago
    Auto-check passed

Works with

Questions about Codexqa Rootcause Analyzer

What does Codexqa Rootcause Analyzer do?

Diagnoses exception root causes from stack traces, logs, call-chain dumps, and debug output using the CodexQA CLI for structured repo analysis. Codexqa Rootcause Analyzer is an agent skill from openqa-cn/codexqa. Diagnoses exception root causes from stack traces, logs, call-chain dumps, and debug output using the CodexQA CLI for structured repo analysis.

When should I use Codexqa Rootcause Analyzer?

Codexqa Rootcause Analyzer fits situations like: the user mentions codexqa-rootcause-analyzer; AI code diagnosis; stack diagnosis; asks to turn an exception into a root-cause report.

How do I install Codexqa Rootcause Analyzer in Claude Code?

Run `npx skills add openqa-cn/codexqa --skill codexqa-rootcause-analyzer -a claude-code`. Or copy the skill folder (skills/codexqa-rootcause-analyzer in openqa-cn/codexqa) into .claude/skills/codexqa-rootcause-analyzer in your project. Claude Code loads it when a task matches its description.

How do I install Codexqa Rootcause Analyzer in Codex?

Run `npx skills add openqa-cn/codexqa --skill codexqa-rootcause-analyzer -a codex`. Or copy the skill folder (skills/codexqa-rootcause-analyzer in openqa-cn/codexqa) into .agents/skills/codexqa-rootcause-analyzer in your project. Codex loads it when a task matches its description.

Can I use Codexqa Rootcause Analyzer 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 openqa-cn/codexqa --skill codexqa-rootcause-analyzer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codexqa-rootcause-analyzer, .gemini/skills/codexqa-rootcause-analyzer, .github/skills/codexqa-rootcause-analyzer and .opencode/skills/codexqa-rootcause-analyzer in your project.

What does Codexqa Rootcause Analyzer need to run?

Going by SKILL.md and its folder, Codexqa Rootcause Analyzer needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node, git and npm). Our summary lists: Node.js. Compatibility (from SKILL.md): Requires Node.js 22+ and git on PATH when cloning remotes. Talks to the `@openqa-cn/codexqa` CLI via npm (`codexqa` binary only); do not copy engine or skill source. Task data lives under this skill's `data/` directory. .

Does Codexqa Rootcause Analyzer access the network?

SKILL.md names 1 domain. In commands or code: registry.npmjs.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Codexqa Rootcause Analyzer 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Codexqa Rootcause Analyzer use?

Codexqa Rootcause Analyzer is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Codexqa Rootcause Analyzer use?

About 2.6k tokens (SKILL.md is roughly 10k 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 4k tokens, read only when the agent opens those files.

What are the alternatives to Codexqa Rootcause Analyzer?

Skills that share tags, products or a category with Codexqa Rootcause Analyzer: Targeted Emergency Bug Fix (VeryGoodOpenSource/vgv-wingspan, 108 stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Debugging and Error Recovery (addyosmani/agent-skills, 102k stars) and Git History Bug Audit (ben-manes/caffeine, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codexqa Rootcause Analyzer?

openqa-cn (a GitHub organization) maintains it in openqa-cn/codexqa, which has 152 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 3, 2026.

Source: openqa-cn/codexqa on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.