pc-rating-recovery
Inspect a PC SQL Server job stuck with the rate/quote request being processed, and explicitly reset an orphaned Quoting period to Draft in non-production.
Skill by Covcloud-LLC
Chalk Labs
Need help deploying pc-rating-recovery?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/covcloud-llc-pc-rating-recovery
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/pc-rating-recovery
What's inside
- Skill name
pc-rating-recovery- Description
- Inspect a PC SQL Server job stuck with the rate/quote request being processed, and explicitly reset an orphaned Quoting period to Draft in non-production. Use for stale rating or quoting locks after interrupted development requests, not active requests, production, rerating, async queue repair, or general status resets.
- License
- Apache-2.0
- Instructions
- 33 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (8)
- PROMPT.md
- README.md
- SKILL.md
- openai.yaml · agents/
- requirements.txt
- rating-recovery.py · scripts/
- rating-recovery-oracle.sql · sql/
- rating-recovery.sql · sql/
SKILL.md (first lines)
# Recover a stale non-production quoting job Read [README.md](README.md) for connection setup, outcomes and limitations. If the user wants SQL to run themselves without pc-tools, supply the complete [SQL Server batch](sql/rating-recovery.sql) and its README instructions. For Oracle, supply the [standalone translation](sql/rating-recovery-oracle.sql) and explain its unverified schema/time assumptions and concurrent-insert limitation. Do not claim Oracle support for the Python command. Keep preview defaults; providing either script is not authorization to execute it. 1. Reuse the user's authorized connection and exact job number, preserving leading zeros. Never guess a target database or expose credentials. Run the bundled `scripts/rating-recovery.py --job-number '<job>'` with `--pc-database-config <database-config.xml>` or the documented `PC_WS_*` variables. The default is inspection and rolls back without a write. 2. Report the selected period, status, BeanVersion, async work items and outcome. `eligible` means the database predicates match, not proof the job is idle. Do not clear other flags, repair queues, generate a quote, or rerate. 3. Apply only when the user has authorized the actual reset, confirms the target is non-production and the job has no ongoing rating/quoting/editing request. Creating this tool or investigating a job is not authorization to repair that job. Reuse explicit authorization already given; do not ask again unnecessarily. 4. For an authorized reset, add `--apply --acknowledge-non-production --expected-period-id <selected ID> --expected-bean-version <inspected version>`. Do not require or perform PC shutdown. Warn that the operator must keep this job idle and may need to reload it; SQL bypasses application callbacks/cache invalidation. The command refuses changed selection/version or any async work item. 5. Report `cleared` only when JSON says `committed: true`. `already-draft` is a no-op, not evidence of a previous repair by this tool. If `outcome-unknown` occurs, inspect again before considering another apply; never blindly retry. Do not treat a SQL success as proof that all application caches or pricing results are valid.
From Covcloud-LLC/pc-tools-public, Apache-2.0.
More from Covcloud-LLC/pc-tools-public
- 0.567score
pc-worksheet-normalization
Covcloud-LLC
Convert local PC worksheets XML into comparable JSON containing final scoped identifier values.
SkillAFreshness: AClaude Code +9 - 0.567score
pc-worksheet-comparison
Covcloud-LLC
Compare two local PC final-values v3 JSON captures from rating runs of the same job and quote branch, and write comparison JSON plus a Markdown report.
SkillAFreshness: AClaude Code +9 - 0.567score
pc-worksheet-extraction
Covcloud-LLC
Fetch the complete retained rating worksheets XML for a PC job number from SQL Server into a local file.
SkillAFreshness: AClaude Code +9 - 0.565score
pc-rating-process-extraction
Covcloud-LLC
Extract how one PC line is rated today by one engine (dispatch, call graph, units of work with their method bodies and ratebook routines, each unit's dataflow…
SkillAFreshness: AClaude Code +9 - 0.565score
pc-rating-workspace-extraction
Covcloud-LLC
Write one PC line's rating workspace (the objects its calc routines read and write, nested under the line object with each property's declared type and the PC…
SkillAFreshness: AClaude Code +9 - 0.565score
pc-ratebook-extraction
Covcloud-LLC
Turn one exported PC Rate Management (RTM) ratebook XML into an analysis set a human or an LLM can read (JSON for the book, its rate tables and calc routines…
SkillAFreshness: AClaude Code +9 - 0.565score
pc-rating-access-report
Covcloud-LLC
Collect one PC line's rating access report in any environment where the extraction skills are installed.
SkillAFreshness: AClaude Code +9 - 0.561score
pc-product-model-extraction
Covcloud-LLC
Extract one classic PC 10.2.3 product and line into validated native JSON, preserving declarations, entities, delegates, typelists and costs without…
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 19, 2026 (12 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/Covcloud-LLC/pc-tools-public
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Covcloud-LLC
- 0.567score
pc-worksheet-normalization
Covcloud-LLC
Convert local PC worksheets XML into comparable JSON containing final scoped identifier values.
SkillAFreshness: AClaude Code +9 - 0.567score
pc-worksheet-comparison
Covcloud-LLC
Compare two local PC final-values v3 JSON captures from rating runs of the same job and quote branch, and write comparison JSON plus a Markdown report.
SkillAFreshness: AClaude Code +9 - 0.567score
pc-worksheet-extraction
Covcloud-LLC
Fetch the complete retained rating worksheets XML for a PC job number from SQL Server into a local file.
SkillAFreshness: AClaude Code +9 - 0.565score
pc-rating-process-extraction
Covcloud-LLC
Extract how one PC line is rated today by one engine (dispatch, call graph, units of work with their method bodies and ratebook routines, each unit's dataflow…
SkillAFreshness: AClaude Code +9 - 0.565score
pc-rating-workspace-extraction
Covcloud-LLC
Write one PC line's rating workspace (the objects its calc routines read and write, nested under the line object with each property's declared type and the PC…
SkillAFreshness: AClaude Code +9 - 0.565score
pc-ratebook-extraction
Covcloud-LLC
Turn one exported PC Rate Management (RTM) ratebook XML into an analysis set a human or an LLM can read (JSON for the book, its rate tables and calc routines…
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get pc-rating-recovery running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
pc-rating-recovery skill. Agent Mart. https://agentmart.dev/skills/covcloud-llc-pc-rating-recovery (last updated 2026-10-24)