Borrowing it
Nothing to install: this file belongs to CES-Ltd/TitanX. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CES-Ltd/TitanX/main/.claude/skills/pr-fix/SKILL.mdgit clone --depth 1 https://github.com/CES-Ltd/TitanXWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ces-ltd/titanx/pr-fix)<a href="https://agentmods.dev/skills/ces-ltd/titanx/pr-fix"><img src="https://agentmods.dev/badge/skills/ces-ltd/titanx/pr-fix/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ces-ltd/titanx/pr-fix"><img src="https://agentmods.dev/badge/skills/ces-ltd/titanx/pr-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.03114 |
| Opus 5.5 | $0.00026 | $0.01246 |
| Sonnet 5.5 | $0.00013 | $0.00623 |
| Haiku 4.5 | $0.00007 | $0.00311 |
Grade A, and why
pr-fix scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Fix Skill
Automated workflow to resolve all issues surfaced in a pr-review report — parse summary → detect PR status → create fix branch or checkout original branch → fix by priority → quality gate → commit → publish → verify.
Announce at start: "I'm using pr-fix skill to fix all review issues."
Usage
/pr-fix [pr_number]
pr_number is optional. The skill requires a pr-review report to be present in the current session.
Mode Detection
At the very start of execution, check $ARGUMENTS for the --automation flag:
# $ARGUMENTS example: "123 --automation" or "123"
AUTOMATION_MODE=false
if echo "$ARGUMENTS" | grep -q -- '--automation'; then
AUTOMATION_MODE=true
fi
In automation mode:
- Skip all yes/no confirmation prompts — follow the default best path
Steps
Step 0 — Locate the Review Report
The pr-review skill must have been executed in the current session. The review report (containing a "汇总" table) must be present in the conversation.
If no review report is found in the current session, abort immediately with:
No pr-review report found in this session. Please run
/pr-review <pr_number>first.
Extract the PR number from the report header:
## Code Review:<PR 标题> (#<PR_NUMBER>)
If pr_number is provided as an argument, use it to override the extracted number.
Step 1 — Parse the Summary Table
Locate the 汇总 section in the review report:
| # | 严重级别 | 文件 | 问题 |
| --- | ----------- | ----------- | ---- |
| 1 | 🔴 CRITICAL | `file.ts:N` | ... |
Build an ordered issue list, grouped by severity:
| Priority | Severity | Emoji |
|---|---|---|
| 1 | CRITICAL | 🔴 |
| 2 | HIGH | 🟠 |
| 3 | MEDIUM | 🟡 |
| 4 | LOW | 🔵 |
If the 汇总 table is empty, abort with:
No issues found in the review summary. Nothing to fix.
LOW issues: Skip — do not fix.
After filtering out LOW issues, if no CRITICAL / HIGH / MEDIUM issues remain, abort with:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 373 lines · 66 tokens per session scan A f93b99d3e060
pr-fix is a skill published in the GitHub repository CES-Ltd/TitanX (49 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 3,114 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
github-pr-review
Review one exact GitHub pull-request head from bounded changed-file patches and check evidence, producing source-line findings without posting or claiming tests ran.
code-reviewer
Becomes a senior code reviewer who evaluates pull requests and code changes for correctness, security, performance, and maintainability. Use when the user asks for code review, PR feedback, code quality assessment, or merge readiness evaluation. Do NOT use when writing new code, debugging runtime errors, designing…
code-review
Structured code review skill. Use when asked to "review this code", "review this PR", "check this diff", or when acting as a Hydra reviewer. Runs a multi-pass review with specialist focus areas and confidence-gated findings.
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.
code-quality
Drive static-analysis code quality in pi-agent-dashboard with Biome (analyze → fix → test), in changed-files or whole-repo mode. Use when asked to "improve code quality", "lint and fix", "clean up warnings", "fix Biome issues", "run static analysis", or when setting a code-quality goal. Skip for one-line edits.
verification
Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.